@phdthesis{Zuo2017,
  author    = {Zuo, Zhe},
  title     = {From unstructured to structured: Context-based named entity mining from text},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412576},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 112},
  year      = {2017},
  abstract  = {With recent advances in the area of information extraction, automatically extracting structured information from a vast amount of unstructured textual data becomes an important task, which is infeasible for humans to capture all information manually. Named entities (e.g., persons, organizations, and locations), which are crucial components in texts, are usually the subjects of structured information from textual documents. Therefore, the task of named entity mining receives much attention. It consists of three major subtasks, which are named entity recognition, named entity linking, and relation extraction. These three tasks build up an entire pipeline of a named entity mining system, where each of them has its challenges and can be employed for further applications. As a fundamental task in the natural language processing domain, studies on named entity recognition have a long history, and many existing approaches produce reliable results. The task is aiming to extract mentions of named entities in text and identify their types. Named entity linking recently received much attention with the development of knowledge bases that contain rich information about entities. The goal is to disambiguate mentions of named entities and to link them to the corresponding entries in a knowledge base. Relation extraction, as the final step of named entity mining, is a highly challenging task, which is to extract semantic relations between named entities, e.g., the ownership relation between two companies. In this thesis, we review the state-of-the-art of named entity mining domain in detail, including valuable features, techniques, evaluation methodologies, and so on. Furthermore, we present two of our approaches that focus on the named entity linking and relation extraction tasks separately. To solve the named entity linking task, we propose the entity linking technique, BEL, which operates on a textual range of relevant terms and aggregates decisions from an ensemble of simple classifiers. Each of the classifiers operates on a randomly sampled subset of the above range. In extensive experiments on hand-labeled and benchmark datasets, our approach outperformed state-of-the-art entity linking techniques, both in terms of quality and efficiency. For the task of relation extraction, we focus on extracting a specific group of difficult relation types, business relations between companies. These relations can be used to gain valuable insight into the interactions between companies and perform complex analytics, such as predicting risk or valuating companies. Our semi-supervised strategy can extract business relations between companies based on only a few user-provided seed company pairs. By doing so, we also provide a solution for the problem of determining the direction of asymmetric relations, such as the ownership_of relation. We improve the reliability of the extraction process by using a holistic pattern identification method, which classifies the generated extraction patterns. Our experiments show that we can accurately and reliably extract new entity pairs occurring in the target relation by using as few as five labeled seed pairs.},
  language  = {en}
}
@phdthesis{Zieger2017,
  author    = {Zieger, Tobias},
  title     = {Self-adaptive data quality},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-410573},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 125},
  year      = {2017},
  abstract  = {Carrying out business processes successfully is closely linked to the quality of the data inventory in an organization. Lacks in data quality lead to problems: Incorrect address data prevents (timely) shipments to customers. Erroneous orders lead to returns and thus to unnecessary effort. Wrong pricing forces companies to miss out on revenues or to impair customer satisfaction. If orders or customer records cannot be retrieved, complaint management takes longer. Due to erroneous inventories, too few or too much supplies might be reordered. A special problem with data quality and the reason for many of the issues mentioned above are duplicates in databases. Duplicates are different representations of same real-world objects in a dataset. However, these representations differ from each other and are for that reason hard to match by a computer. Moreover, the number of required comparisons to find those duplicates grows with the square of the dataset size. To cleanse the data, these duplicates must be detected and removed. Duplicate detection is a very laborious process. To achieve satisfactory results, appropriate software must be created and configured (similarity measures, partitioning keys, thresholds, etc.). Both requires much manual effort and experience. This thesis addresses automation of parameter selection for duplicate detection and presents several novel approaches that eliminate the need for human experience in parts of the duplicate detection process. A pre-processing step is introduced that analyzes the datasets in question and classifies their attributes semantically. Not only do these annotations help understanding the respective datasets, but they also facilitate subsequent steps, for example, by selecting appropriate similarity measures or normalizing the data upfront. This approach works without schema information. Following that, we show a partitioning technique that strongly reduces the number of pair comparisons for the duplicate detection process. The approach automatically finds particularly suitable partitioning keys that simultaneously allow for effective and efficient duplicate retrieval. By means of a user study, we demonstrate that this technique finds partitioning keys that outperform expert suggestions and additionally does not need manual configuration. Furthermore, this approach can be applied independently of the attribute types. To measure the success of a duplicate detection process and to execute the described partitioning approach, a gold standard is required that provides information about the actual duplicates in a training dataset. This thesis presents a technique that uses existing duplicate detection results and crowdsourcing to create a near gold standard that can be used for the purposes above. Another part of the thesis describes and evaluates strategies how to reduce these crowdsourcing costs and to achieve a consensus with less effort.},
  language  = {en}
}
@phdthesis{Wolf2021,
  author    = {Wolf, Johannes},
  title     = {Analysis and visualization of transport infrastructure based on large-scale geospatial mobile mapping data},
  doi       = {10.25932/publishup-53612},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-536129},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 121},
  year      = {2021},
  abstract  = {3D point clouds are a universal and discrete digital representation of three-dimensional objects and environments. For geospatial applications, 3D point clouds have become a fundamental type of raw data acquired and generated using various methods and techniques. In particular, 3D point clouds serve as raw data for creating digital twins of the built environment. This thesis concentrates on the research and development of concepts, methods, and techniques for preprocessing, semantically enriching, analyzing, and visualizing 3D point clouds for applications around transport infrastructure. It introduces a collection of preprocessing techniques that aim to harmonize raw 3D point cloud data, such as point density reduction and scan profile detection. Metrics such as, e.g., local density, verticality, and planarity are calculated for later use. One of the key contributions tackles the problem of analyzing and deriving semantic information in 3D point clouds. Three different approaches are investigated: a geometric analysis, a machine learning approach operating on synthetically generated 2D images, and a machine learning approach operating on 3D point clouds without intermediate representation. In the first application case, 2D image classification is applied and evaluated for mobile mapping data focusing on road networks to derive road marking vector data. The second application case investigates how 3D point clouds can be merged with ground-penetrating radar data for a combined visualization and to automatically identify atypical areas in the data. For example, the approach detects pavement regions with developing potholes. The third application case explores the combination of a 3D environment based on 3D point clouds with panoramic imagery to improve visual representation and the detection of 3D objects such as traffic signs. The presented methods were implemented and tested based on software frameworks for 3D point clouds and 3D visualization. In particular, modules for metric computation, classification procedures, and visualization techniques were integrated into a modular pipeline-based C++ research framework for geospatial data processing, extended by Python machine learning scripts. All visualization and analysis techniques scale to large real-world datasets such as road networks of entire cities or railroad networks. The thesis shows that some use cases allow taking advantage of established image vision methods to analyze images rendered from mobile mapping data efficiently. The two presented semantic classification methods working directly on 3D point clouds are use case independent and show similar overall accuracy when compared to each other. While the geometry-based method requires less computation time, the machine learning-based method supports arbitrary semantic classes but requires training the network with ground truth data. Both methods can be used in combination to gradually build this ground truth with manual corrections via a respective annotation tool. This thesis contributes results for IT system engineering of applications, systems, and services that require spatial digital twins of transport infrastructure such as road networks and railroad networks based on 3D point clouds as raw data. It demonstrates the feasibility of fully automated data flows that map captured 3D point clouds to semantically classified models. This provides a key component for seamlessly integrated spatial digital twins in IT solutions that require up-to-date, object-based, and semantically enriched information about the built environment.},
  language  = {en}
}
@phdthesis{Vogel2018,
  author    = {Vogel, Thomas},
  title     = {Model-driven engineering of self-adaptive software},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-409755},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvi, 357},
  year      = {2018},
  abstract  = {The development of self-adaptive software requires the engineering of an adaptation engine that controls the underlying adaptable software by a feedback loop. State-of-the-art approaches prescribe the feedback loop in terms of numbers, how the activities (e.g., monitor, analyze, plan, and execute (MAPE)) and the knowledge are structured to a feedback loop, and the type of knowledge. Moreover, the feedback loop is usually hidden in the implementation or framework and therefore not visible in the architectural design. Additionally, an adaptation engine often employs runtime models that either represent the adaptable software or capture strategic knowledge such as reconfiguration strategies. State-of-the-art approaches do not systematically address the interplay of such runtime models, which would otherwise allow developers to freely design the entire feedback loop. This thesis presents ExecUtable RuntimE MegAmodels (EUREMA), an integrated model-driven engineering (MDE) solution that rigorously uses models for engineering feedback loops. EUREMA provides a domain-specific modeling language to specify and an interpreter to execute feedback loops. The language allows developers to freely design a feedback loop concerning the activities and runtime models (knowledge) as well as the number of feedback loops. It further supports structuring the feedback loops in the adaptation engine that follows a layered architectural style. Thus, EUREMA makes the feedback loops explicit in the design and enables developers to reason about design decisions. To address the interplay of runtime models, we propose the concept of a runtime megamodel, which is a runtime model that contains other runtime models as well as activities (e.g., MAPE) working on the contained models. This concept is the underlying principle of EUREMA. The resulting EUREMA (mega)models are kept alive at runtime and they are directly executed by the EUREMA interpreter to run the feedback loops. Interpretation provides the flexibility to dynamically adapt a feedback loop. In this context, EUREMA supports engineering self-adaptive software in which feedback loops run independently or in a coordinated fashion within the same layer as well as on top of each other in different layers of the adaptation engine. Moreover, we consider preliminary means to evolve self-adaptive software by providing a maintenance interface to the adaptation engine. This thesis discusses in detail EUREMA by applying it to different scenarios such as single, multiple, and stacked feedback loops for self-repairing and self-optimizing the mRUBiS application. Moreover, it investigates the design and expressiveness of EUREMA, reports on experiments with a running system (mRUBiS) and with alternative solutions, and assesses EUREMA with respect to quality attributes such as performance and scalability. The conducted evaluation provides evidence that EUREMA as an integrated and open MDE approach for engineering self-adaptive software seamlessly integrates the development and runtime environments using the same formalism to specify and execute feedback loops, supports the dynamic adaptation of feedback loops in layered architectures, and achieves an efficient execution of feedback loops by leveraging incrementality.},
  language  = {en}
}
@phdthesis{Vitagliano2024,
  author    = {Vitagliano, Gerardo},
  title     = {Modeling the structure of tabular files for data preparation},
  doi       = {10.25932/publishup-62435},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624351},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 114},
  year      = {2024},
  abstract  = {To manage tabular data files and leverage their content in a given downstream task, practitioners often design and execute complex transformation pipelines to prepare them. The complexity of such pipelines stems from different factors, including the nature of the preparation tasks, often exploratory or ad-hoc to specific datasets; the large repertory of tools, algorithms, and frameworks that practitioners need to master; and the volume, variety, and velocity of the files to be prepared. Metadata plays a fundamental role in reducing this complexity: characterizing a file assists end users in the design of data preprocessing pipelines, and furthermore paves the way for suggestion, automation, and optimization of data preparation tasks. Previous research in the areas of data profiling, data integration, and data cleaning, has focused on extracting and characterizing metadata regarding the content of tabular data files, i.e., about the records and attributes of tables. Content metadata are useful for the latter stages of a preprocessing pipeline, e.g., error correction, duplicate detection, or value normalization, but they require a properly formed tabular input. Therefore, these metadata are not relevant for the early stages of a preparation pipeline, i.e., to correctly parse tables out of files. In this dissertation, we turn our focus to what we call the structure of a tabular data file, i.e., the set of characters within a file that do not represent data values but are required to parse and understand the content of the file. We provide three different approaches to represent file structure, an explicit representation based on context-free grammars; an implicit representation based on file-wise similarity; and a learned representation based on machine learning. In our first contribution, we use the grammar-based representation to characterize a set of over 3000 real-world csv files and identify multiple structural issues that let files deviate from the csv standard, e.g., by having inconsistent delimiters or containing multiple tables. We leverage our learnings about real-world files and propose Pollock, a benchmark to test how well systems parse csv files that have a non-standard structure, without any previous preparation. We report on our experiments on using Pollock to evaluate the performance of 16 real-world data management systems. Following, we characterize the structure of files implicitly, by defining a measure of structural similarity for file pairs. We design a novel algorithm to compute this measure, which is based on a graph representation of the files' content. We leverage this algorithm and propose Mondrian, a graphical system to assist users in identifying layout templates in a dataset, classes of files that have the same structure, and therefore can be prepared by applying the same preparation pipeline. Finally, we introduce MaGRiTTE, a novel architecture that uses self-supervised learning to automatically learn structural representations of files in the form of vectorial embeddings at three different levels: cell level, row level, and file level. We experiment with the application of structural embeddings for several tasks, namely dialect detection, row classification, and data preparation efforts estimation. Our experimental results show that structural metadata, either identified explicitly on parsing grammars, derived implicitly as file-wise similarity, or learned with the help of machine learning architectures, is fundamental to automate several tasks, to scale up preparation to large quantities of files, and to provide repeatable preparation pipelines.},
  language  = {en}
}
@phdthesis{Traifeh2023,
  author    = {Traifeh, Hanadi},
  title     = {Design Thinking in the Arab world},
  doi       = {10.25932/publishup-59891},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598911},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 196},
  year      = {2023},
  abstract  = {Design Thinking is a human-centered approach to innovation that has become increasingly popular globally over the last decade. While the spread of Design Thinking is well understood and documented in the Western cultural contexts, particularly in Europe and the US due to the popularity of the Stanford-Potsdam Design Thinking education model, this is not the case when it comes to non-Western cultural contexts. This thesis fills a gap identified in the literature regarding how Design Thinking emerged, was perceived, adopted, and practiced in the Arab world. The culture in that part of the world differs from that of the Western context, which impacts the mindset of people and how they interact with Design Thinking tools and methods. A mixed-methods research approach was followed in which both quantitative and qualitative methods were employed. First, two methods were used in the quantitative phase: a social media analysis using Twitter as a source of data, and an online questionnaire. The results and analysis of the quantitative data informed the design of the qualitative phase in which two methods were employed: ten semi-structured interviews, and participant observation of seven Design Thinking training events. According to the analyzed data, the Arab world appears to have had an early, though relatively weak, and slow, adoption of Design Thinking since 2006. Increasing adoption, however, has been witnessed over the last decade, especially in Saudi Arabia, the United Arab Emirates and Egypt. The results also show that despite its limited spread, Design Thinking has been practiced the most in education, information technology and communication, administrative services, and the non-profit sectors. The way it is being practiced, though, is not fully aligned with how it is being practiced and taught in the US and Europe, as most people in the region do not necessarily believe in all mindset attributes introduced by the Stanford-Potsdam tradition. Practitioners in the Arab world also seem to shy away from the 'wild side' of Design Thinking in particular, and do not fully appreciate the connection between art-design, and science-engineering. This questions the role of the educational institutions in the region since -according to the findings- they appear to be leading the movement in promoting and developing Design Thinking in the Arab world. Nonetheless, it is notable that people seem to be aware of the positive impact of applying Design Thinking in the region, and its potential to bring meaningful transformation. However, they also seem to be concerned about the current cultural, social, political, and economic challenges that may challenge this transformation. Therefore, they call for more awareness and demand to create Arabic, culturally appropriate programs to respond to the local needs. On another note, the lack of Arabic content and local case studies on Design Thinking were identified by several interviewees and were also confirmed by the participant observation as major challenges that are slowing down the spread of Design Thinking or sometimes hampering capacity building in the region. Other challenges that were revealed by the study are: changing the mindset of people, the lack of dedicated Design Thinking spaces, and the need for clear instructions on how to apply Design Thinking methods and activities. The concept of time and how Arabs deal with it, gender management during trainings, and hierarchy and power dynamics among training participants are also among the identified challenges. Another key finding revealed by the study is the confirmation of التفكير التصميمي as the Arabic term to be most widely adopted in the region to refer to Design Thinking, since four other Arabic terms were found to be associated with Design Thinking. Based on the findings of the study, the thesis concludes by presenting a list of recommendations on how to overcome the mentioned challenges and what factors should be considered when designing and implementing culturally-customized Design Thinking training in the Arab region.},
  language  = {en}
}
@phdthesis{TorcatoMordido2021,
  author    = {Torcato Mordido, Gon{\c{c}}alo Filipe},
  title     = {Diversification, compression, and evaluation methods for generative adversarial networks},
  doi       = {10.25932/publishup-53546},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535460},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiii, 148},
  year      = {2021},
  abstract  = {Generative adversarial networks (GANs) have been broadly applied to a wide range of application domains since their proposal. In this thesis, we propose several methods that aim to tackle different existing problems in GANs. Particularly, even though GANs are generally able to generate high-quality samples, the diversity of the generated set is often sub-optimal. Moreover, the common increase of the number of models in the original GANs framework, as well as their architectural sizes, introduces additional costs. Additionally, even though challenging, the proper evaluation of a generated set is an important direction to ultimately improve the generation process in GANs. We start by introducing two diversification methods that extend the original GANs framework to multiple adversaries to stimulate sample diversity in a generated set. Then, we introduce a new post-training compression method based on Monte Carlo methods and importance sampling to quantize and prune the weights and activations of pre-trained neural networks without any additional training. The previous method may be used to reduce the memory and computational costs introduced by increasing the number of models in the original GANs framework. Moreover, we use a similar procedure to quantize and prune gradients during training, which also reduces the communication costs between different workers in a distributed training setting. We introduce several topology-based evaluation methods to assess data generation in different settings, namely image generation and language generation. Our methods retrieve both single-valued and double-valued metrics, which, given a real set, may be used to broadly assess a generated set or separately evaluate sample quality and sample diversity, respectively. Moreover, two of our metrics use locality-sensitive hashing to accurately assess the generated sets of highly compressed GANs. The analysis of the compression effects in GANs paves the way for their efficient employment in real-world applications. Given their general applicability, the methods proposed in this thesis may be extended beyond the context of GANs. Hence, they may be generally applied to enhance existing neural networks and, in particular, generative frameworks.},
  language  = {en}
}
@phdthesis{Teusner2021,
  author    = {Teusner, Ralf},
  title     = {Situational interventions and peer feedback in massive open online courses},
  doi       = {10.25932/publishup-50758},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-507587},
  school      = {Universit{\"a}t Potsdam},
  pages     = {178},
  year      = {2021},
  abstract  = {Massive Open Online Courses (MOOCs) open up new opportunities to learn a wide variety of skills online and are thus well suited for individual education, especially where proffcient teachers are not available locally. At the same time, modern society is undergoing a digital transformation, requiring the training of large numbers of current and future employees. Abstract thinking, logical reasoning, and the need to formulate instructions for computers are becoming increasingly relevant. A holistic way to train these skills is to learn how to program. Programming, in addition to being a mental discipline, is also considered a craft, and practical training is required to achieve mastery. In order to effectively convey programming skills in MOOCs, practical exercises are incorporated into the course curriculum to offer students the necessary hands-on experience to reach an in-depth understanding of the programming concepts presented. Our preliminary analysis showed that while being an integral and rewarding part of courses, practical exercises bear the risk of overburdening students who are struggling with conceptual misunderstandings and unknown syntax. In this thesis, we develop, implement, and evaluate different interventions with the aim to improve the learning experience, sustainability, and success of online programming courses. Data from four programming MOOCs, with a total of over 60,000 participants, are employed to determine criteria for practical programming exercises best suited for a given audience. Based on over five million executions and scoring runs from students' task submissions, we deduce exercise difficulties, students' patterns in approaching the exercises, and potential flaws in exercise descriptions as well as preparatory videos. The primary issue in online learning is that students face a social gap caused by their isolated physical situation. Each individual student usually learns alone in front of a computer and suffers from the absence of a pre-determined time structure as provided in traditional school classes. Furthermore, online learning usually presses students into a one-size-fits-all curriculum, which presents the same content to all students, regardless of their individual needs and learning styles. Any means of a personalization of content or individual feedback regarding problems they encounter are mostly ruled out by the discrepancy between the number of learners and the number of instructors. This results in a high demand for self-motivation and determination of MOOC participants. Social distance exists between individual students as well as between students and course instructors. It decreases engagement and poses a threat to learning success. Within this research, we approach the identified issues within MOOCs and suggest scalable technical solutions, improving social interaction and balancing content difficulty. Our contributions include situational interventions, approaches for personalizing educational content as well as concepts for fostering collaborative problem-solving. With these approaches, we reduce counterproductive struggles and create a universal improvement for future programming MOOCs. We evaluate our approaches and methods in detail to improve programming courses for students as well as instructors and to advance the state of knowledge in online education. Data gathered from our experiments show that receiving peer feedback on one's programming problems improves overall course scores by up to 17\%. Merely the act of phrasing a question about one's problem improved overall scores by about 14\%. The rate of students reaching out for help was significantly improved by situational just-in-time interventions. Request for Comment interventions increased the share of students asking for help by up to 158\%. Data from our four MOOCs further provide detailed insight into the learning behavior of students. We outline additional significant findings with regard to student behavior and demographic factors. Our approaches, the technical infrastructure, the numerous educational resources developed, and the data collected provide a solid foundation for future research.},
  language  = {en}
}
@phdthesis{Tan2023,
  author    = {Tan, Jing},
  title     = {Multi-Agent Reinforcement Learning for Interactive Decision-Making},
  doi       = {10.25932/publishup-60700},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-607000},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 135},
  year      = {2023},
  abstract  = {Distributed decision-making studies the choices made among a group of interactive and self-interested agents. Specifically, this thesis is concerned with the optimal sequence of choices an agent makes as it tries to maximize its achievement on one or multiple objectives in the dynamic environment. The optimization of distributed decision-making is important in many real-life applications, e.g., resource allocation (of products, energy, bandwidth, computing power, etc.) and robotics (heterogeneous agent cooperation on games or tasks), in various fields such as vehicular network, Internet of Things, smart grid, etc. This thesis proposes three multi-agent reinforcement learning algorithms combined with game-theoretic tools to study strategic interaction between decision makers, using resource allocation in vehicular network as an example. Specifically, the thesis designs an interaction mechanism based on second-price auction, incentivizes the agents to maximize multiple short-term and long-term, individual and system objectives, and simulates a dynamic environment with realistic mobility data to evaluate algorithm performance and study agent behavior. Theoretical results show that the mechanism has Nash equilibria, is a maximization of social welfare and Pareto optimal allocation of resources in a stationary environment. Empirical results show that in the dynamic environment, our proposed learning algorithms outperform state-of-the-art algorithms in single and multi-objective optimization, and demonstrate very good generalization property in significantly different environments. Specifically, with the long-term multi-objective learning algorithm, we demonstrate that by considering the long-term impact of decisions, as well as by incentivizing the agents with a system fairness reward, the agents achieve better results in both individual and system objectives, even when their objectives are private, randomized, and changing over time. Moreover, the agents show competitive behavior to maximize individual payoff when resource is scarce, and cooperative behavior in achieving a system objective when resource is abundant; they also learn the rules of the game, without prior knowledge, to overcome disadvantages in initial parameters (e.g., a lower budget). To address practicality concerns, the thesis also provides several computational performance improvement methods, and tests the algorithm in a single-board computer. Results show the feasibility of online training and inference in milliseconds. There are many potential future topics following this work. 1) The interaction mechanism can be modified into a double-auction, eliminating the auctioneer, resembling a completely distributed, ad hoc network; 2) the objectives are assumed to be independent in this thesis, there may be a more realistic assumption regarding correlation between objectives, such as a hierarchy of objectives; 3) current work limits information-sharing between agents, the setup befits applications with privacy requirements or sparse signaling; by allowing more information-sharing between the agents, the algorithms can be modified for more cooperative scenarios such as robotics.},
  language  = {en}
}
@phdthesis{Taleb2024,
  author    = {Taleb, Aiham},
  title     = {Self-supervised deep learning methods for medical image analysis},
  doi       = {10.25932/publishup-64408},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-644089},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 171},
  year      = {2024},
  abstract  = {Deep learning has seen widespread application in many domains, mainly for its ability to learn data representations from raw input data. Nevertheless, its success has so far been coupled with the availability of large annotated (labelled) datasets. This is a requirement that is difficult to fulfil in several domains, such as in medical imaging. Annotation costs form a barrier in extending deep learning to clinically-relevant use cases. The labels associated with medical images are scarce, since the generation of expert annotations of multimodal patient data at scale is non-trivial, expensive, and time-consuming. This substantiates the need for algorithms that learn from the increasing amounts of unlabeled data. Self-supervised representation learning algorithms offer a pertinent solution, as they allow solving real-world (downstream) deep learning tasks with fewer annotations. Self-supervised approaches leverage unlabeled samples to acquire generic features about different concepts, enabling annotation-efficient downstream task solving subsequently. Nevertheless, medical images present multiple unique and inherent challenges for existing self-supervised learning approaches, which we seek to address in this thesis: (i) medical images are multimodal, and their multiple modalities are heterogeneous in nature and imbalanced in quantities, e.g. MRI and CT; (ii) medical scans are multi-dimensional, often in 3D instead of 2D; (iii) disease patterns in medical scans are numerous and their incidence exhibits a long-tail distribution, so it is oftentimes essential to fuse knowledge from different data modalities, e.g. genomics or clinical data, to capture disease traits more comprehensively; (iv) Medical scans usually exhibit more uniform color density distributions, e.g. in dental X-Rays, than natural images. Our proposed self-supervised methods meet these challenges, besides significantly reducing the amounts of required annotations. We evaluate our self-supervised methods on a wide array of medical imaging applications and tasks. Our experimental results demonstrate the obtained gains in both annotation-efficiency and performance; our proposed methods outperform many approaches from related literature. Additionally, in case of fusion with genetic modalities, our methods also allow for cross-modal interpretability. In this thesis, not only we show that self-supervised learning is capable of mitigating manual annotation costs, but also our proposed solutions demonstrate how to better utilize it in the medical imaging domain. Progress in self-supervised learning has the potential to extend deep learning algorithms application to clinical scenarios.},
  language  = {en}
}
@phdthesis{Taeumel2020,
  author    = {Taeumel, Marcel},
  title     = {Data-driven tool construction in exploratory programming environments},
  doi       = {10.25932/publishup-44428},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-444289},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 299},
  year      = {2020},
  abstract  = {This work presents a new design for programming environments that promote the exploration of domain-specific software artifacts and the construction of graphical tools for such program comprehension tasks. In complex software projects, tool building is essential because domain- or task-specific tools can support decision making by representing concerns concisely with low cognitive effort. In contrast, generic tools can only support anticipated scenarios, which usually align with programming language concepts or well-known project domains. However, the creation and modification of interactive tools is expensive because the glue that connects data to graphics is hard to find, change, and test. Even if valuable data is available in a common format and even if promising visualizations could be populated, programmers have to invest many resources to make changes in the programming environment. Consequently, only ideas of predictably high value will be implemented. In the non-graphical, command-line world, the situation looks different and inspiring: programmers can easily build their own tools as shell scripts by configuring and combining filter programs to process data. We propose a new perspective on graphical tools and provide a concept to build and modify such tools with a focus on high quality, low effort, and continuous adaptability. That is, (1) we propose an object-oriented, data-driven, declarative scripting language that reduces the amount of and governs the effects of glue code for view-model specifications, and (2) we propose a scalable UI-design language that promotes short feedback loops in an interactive, graphical environment such as Morphic known from Self or Squeak/Smalltalk systems. We implemented our concept as a tool building environment, which we call VIVIDE, on top of Squeak/Smalltalk and Morphic. We replaced existing code browsing and debugging tools to iterate within our solution more quickly. In several case studies with undergraduate and graduate students, we observed that VIVIDE can be applied to many domains such as live language development, source-code versioning, modular code browsing, and multi-language debugging. Then, we designed a controlled experiment to measure the effect on the time to build tools. Several pilot runs showed that training is crucial and, presumably, takes days or weeks, which implies a need for further research. As a result, programmers as users can directly work with tangible representations of their software artifacts in the VIVIDE environment. Tool builders can write domain-specific scripts to populate views to approach comprehension tasks from different angles. Our novel perspective on graphical tools can inspire the creation of new trade-offs in modularity for both data providers and view designers.},
  language  = {en}
}
@phdthesis{Sukmana2022,
  author    = {Sukmana, Muhammad Ihsan Haikal},
  title     = {Security improvements for enterprise file sychronization and sharing system},
  doi       = {10.25932/publishup-54999},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-549996},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 213},
  year      = {2022},
  abstract  = {With the fast rise of cloud computing adoption in the past few years, more companies are migrating their confidential files from their private data center to the cloud to help enterprise's digital transformation process. Enterprise file synchronization and share (EFSS) is one of the solutions offered for enterprises to store their files in the cloud with secure and easy file sharing and collaboration between its employees. However, the rapidly increasing number of cyberattacks on the cloud might target company's files on the cloud to be stolen or leaked to the public. It is then the responsibility of the EFSS system to ensure the company's confidential files to only be accessible by authorized employees. CloudRAID is a secure personal cloud storage research collaboration project that provides data availability and confidentiality in the cloud. It combines erasure and cryptographic techniques to securely store files as multiple encrypted file chunks in various cloud service providers (CSPs). However, several aspects of CloudRAID's concept are unsuitable for secure and scalable enterprise cloud storage solutions, particularly key management system, location-based access control, multi-cloud storage management, and cloud file access monitoring. This Ph.D. thesis focuses on CloudRAID for Business (CfB) as it resolves four main challenges of CloudRAID's concept for a secure and scalable EFSS system. First, the key management system is implemented using the attribute-based encryption scheme to provide secure and scalable intra-company and inter-company file-sharing functionalities. Second, an Internet-based location file access control functionality is introduced to ensure files could only be accessed at pre-determined trusted locations. Third, a unified multi-cloud storage resource management framework is utilized to securely manage cloud storage resources available in various CSPs for authorized CfB stakeholders. Lastly, a multi-cloud storage monitoring system is introduced to monitor the activities of files in the cloud using the generated cloud storage log files from multiple CSPs. In summary, this thesis helps CfB system to provide holistic security for company's confidential files on the cloud-level, system-level, and file-level to ensure only authorized company and its employees could access the files.},
  language  = {en}
}
@phdthesis{Stojanovic2021,
  author    = {Stojanovic, Vladeta},
  title     = {Digital twins for indoor built environments},
  doi       = {10.25932/publishup-50913},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-509134},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxiii, 181},
  year      = {2021},
  abstract  = {One of the key challenges in modern Facility Management (FM) is to digitally reflect the current state of the built environment, referred to as-is or as-built versus as-designed representation. While the use of Building Information Modeling (BIM) can address the issue of digital representation, the generation and maintenance of BIM data requires a considerable amount of manual work and domain expertise. Another key challenge is being able to monitor the current state of the built environment, which is used to provide feedback and enhance decision making. The need for an integrated solution for all data associated with the operational life cycle of a building is becoming more pronounced as practices from Industry 4.0 are currently being evaluated and adopted for FM use. This research presents an approach for digital representation of indoor environments in their current state within the life cycle of a given building. Such an approach requires the fusion of various sources of digital data. The key to solving such a complex issue of digital data integration, processing and representation is with the use of a Digital Twin (DT). A DT is a digital duplicate of the physical environment, states, and processes. A DT fuses as-designed and as-built digital representations of built environment with as-is data, typically in the form of floorplans, point clouds and BIMs, with additional information layers pertaining to the current and predicted states of an indoor environment or a complete building (e.g., sensor data). The design, implementation and initial testing of prototypical DT software services for indoor environments is presented and described. These DT software services are implemented within a service-oriented paradigm, and their feasibility is presented through functioning and tested key software components within prototypical Service-Oriented System (SOS) implementations. The main outcome of this research shows that key data related to the built environment can be semantically enriched and combined to enable digital representations of indoor environments, based on the concept of a DT. Furthermore, the outcomes of this research show that digital data, related to FM and Architecture, Construction, Engineering, Owner and Occupant (AECOO) activity, can be combined, analyzed and visualized in real-time using a service-oriented approach. This has great potential to benefit decision making related to Operation and Maintenance (O\&M) procedures within the scope of the post-construction life cycle stages of typical office buildings.},
  language  = {en}
}
@phdthesis{Staubitz2020,
  author    = {Staubitz, Thomas},
  title     = {Gradable team assignments in large scale learning environments},
  doi       = {10.25932/publishup-47183},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471830},
  school      = {Universit{\"a}t Potsdam},
  pages     = {122},
  year      = {2020},
  abstract  = {Lifelong learning plays an increasingly important role in many societies. Technology is changing faster than ever and what has been important to learn today, may be obsolete tomorrow. The role of informal programs is becoming increasingly important. Particularly, Massive Open Online Courses have become popular among learners and instructors. In 2008, a group of Canadian education enthusiasts started the first Massive Open Online Courses or MOOCs to prove their cognitive theory of Connectivism. Around 2012, a variety of American start-ups redefined the concept of MOOCs. Instead of following the connectivist doctrine they returned to a more traditional approach. They focussed on video lecturing and combined this with a course forum that allowed the participants to discuss with each other and the teaching team. While this new version of the concept was enormously successful in terms of massiveness—hundreds of thousands of participants from all over the world joined the first of these courses—many educators criticized the re-lapse to the cognitivist model. In the early days, the evolving platforms often did not have more features than a video player, simple multiple-choice quizzes, and the course forum. It soon became a major interest of research to allow the scaling of more modern approaches of learning and teaching for the massiveness of these courses. Hands-on exercises, alternative forms of assessment, collaboration, and teamwork are some of the topics on the agenda. The insights provided by cognitive and pedagogical theories, however, do not necessarily always run in sync with the needs and the preferences of the majority of participants. While the former promote action-learning, hands-on-learning, competence-based-learning, project-based-learning, team-based-learning as the holy grail, many of the latter often rather prefer a more laid-back style of learning, sometimes referred to as edutainment. Obviously, given the large numbers of participants in these courses, there is not just one type of learners. Participants are not a homogeneous mass but a potpourri of individuals with a wildly heterogeneous mix of backgrounds, previous knowledge, familial and professional circumstances, countries of origin, gender, age, and so on. For the majority of participants, a full-time job and/or a family often just does not leave enough room for more time intensive tasks, such as practical exercises or teamwork. Others, however, particularly enjoy these hands-on or collaborative aspects of MOOCs. Furthermore, many subjects particularly require these possibilities and simply cannot be taught or learned in courses that lack collaborative or hands-on features. In this context, the thesis discusses how team assignments have been implemented on the HPI MOOC platform. During the recent years, several experiments have been conducted and a great amount of experience has been gained by employing team assignments in courses in areas, such as Object-Oriented Programming, Design Thinking, and Business Innovation on various instances of this platform: openHPI, openSAP, and mooc.house},
  language  = {en}
}
@phdthesis{Sianipar2020,
  author    = {Sianipar, Johannes Harungguan},
  title     = {Towards scalable and secure virtual laboratory for cybersecurity e-learning},
  doi       = {10.25932/publishup-50279},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-502793},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xviii, 156},
  year      = {2020},
  abstract  = {Distance Education or e-Learning platform should be able to provide a virtual laboratory to let the participants have hands-on exercise experiences in practicing their skill remotely. Especially in Cybersecurity e-Learning where the participants need to be able to attack or defend the IT System. To have a hands-on exercise, the virtual laboratory environment must be similar to the real operational environment, where an attack or a victim is represented by a node in a virtual laboratory environment. A node is usually represented by a Virtual Machine (VM). Scalability has become a primary issue in the virtual laboratory for cybersecurity e-Learning because a VM needs a significant and fix allocation of resources. Available resources limit the number of simultaneous users. Scalability can be increased by increasing the efficiency of using available resources and by providing more resources. Increasing scalability means increasing the number of simultaneous users. In this thesis, we propose two approaches to increase the efficiency of using the available resources. The first approach in increasing efficiency is by replacing virtual machines (VMs) with containers whenever it is possible. The second approach is sharing the load with the user-on-premise machine, where the user-on-premise machine represents one of the nodes in a virtual laboratory scenario. We also propose two approaches in providing more resources. One way to provide more resources is by using public cloud services. Another way to provide more resources is by gathering resources from the crowd, which is referred to as Crowdresourcing Virtual Laboratory (CRVL). In CRVL, the crowd can contribute their unused resources in the form of a VM, a bare metal system, an account in a public cloud, a private cloud and an isolated group of VMs, but in this thesis, we focus on a VM. The contributor must give the credential of the VM admin or root user to the CRVL system. We propose an architecture and methods to integrate or dis-integrate VMs from the CRVL system automatically. A Team placement algorithm must also be investigated to optimize the usage of resources and at the same time giving the best service to the user. Because the CRVL system does not manage the contributor host machine, the CRVL system must be able to make sure that the VM integration will not harm their system and that the training material will be stored securely in the contributor sides, so that no one is able to take the training material away without permission. We are investigating ways to handle this kind of threats. We propose three approaches to strengthen the VM from a malicious host admin. To verify the integrity of a VM before integration to the CRVL system, we propose a remote verification method without using any additional hardware such as the Trusted Platform Module chip. As the owner of the host machine, the host admins could have access to the VM's data via Random Access Memory (RAM) by doing live memory dumping, Spectre and Meltdown attacks. To make it harder for the malicious host admin in getting the sensitive data from RAM, we propose a method that continually moves sensitive data in RAM. We also propose a method to monitor the host machine by installing an agent on it. The agent monitors the hypervisor configurations and the host admin activities. To evaluate our approaches, we conduct extensive experiments with different settings. The use case in our approach is Tele-Lab, a Virtual Laboratory platform for Cyber Security e-Learning. We use this platform as a basis for designing and developing our approaches. The results show that our approaches are practical and provides enhanced security.},
  language  = {en}
}
@phdthesis{Shekhar2023,
  author    = {Shekhar, Sumit},
  title     = {Image and video processing based on intrinsic attributes},
  doi       = {10.25932/publishup-62004},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-620049},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 143},
  year      = {2023},
  abstract  = {Advancements in computer vision techniques driven by machine learning have facilitated robust and efficient estimation of attributes such as depth, optical flow, albedo, and shading. To encapsulate all such underlying properties associated with images and videos, we evolve the concept of intrinsic images towards intrinsic attributes. Further, rapid hardware growth in the form of high-quality smartphone cameras, readily available depth sensors, mobile GPUs, or dedicated neural processing units have made image and video processing pervasive. In this thesis, we explore the synergies between the above two advancements and propose novel image and video processing techniques and systems based on them. To begin with, we investigate intrinsic image decomposition approaches and analyze how they can be implemented on mobile devices. We propose an approach that considers not only diffuse reflection but also specular reflection; it allows us to decompose an image into specularity, albedo, and shading on a resource constrained system (e.g., smartphones or tablets) using the depth data provided by the built-in depth sensors. In addition, we explore how on-device depth data can further be used to add an immersive dimension to 2D photos, e.g., showcasing parallax effects via 3D photography. In this regard, we develop a novel system for interactive 3D photo generation and stylization on mobile devices. Further, we investigate how adaptive manipulation of baseline-albedo (i.e., chromaticity) can be used for efficient visual enhancement under low-lighting conditions. The proposed technique allows for interactive editing of enhancement settings while achieving improved quality and performance. We analyze the inherent optical flow and temporal noise as intrinsic properties of a video. We further propose two new techniques for applying the above intrinsic attributes for the purpose of consistent video filtering. To this end, we investigate how to remove temporal inconsistencies perceived as flickering artifacts. One of the techniques does not require costly optical flow estimation, while both provide interactive consistency control. Using intrinsic attributes for image and video processing enables new solutions for mobile devices - a pervasive visual computing device - and will facilitate novel applications for Augmented Reality (AR), 3D photography, and video stylization. The proposed low-light enhancement techniques can also improve the accuracy of high-level computer vision tasks (e.g., face detection) under low-light conditions. Finally, our approach for consistent video filtering can extend a wide range of image-based processing for videos.},
  language  = {en}
}
@phdthesis{Seidel2021,
  author    = {Seidel, Karen},
  title     = {Modelling binary classification with computability theory},
  doi       = {10.25932/publishup-52998},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-529988},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, 120},
  year      = {2021},
  abstract  = {We investigate models for incremental binary classification, an example for supervised online learning. Our starting point is a model for human and machine learning suggested by E.M.Gold. In the first part, we consider incremental learning algorithms that use all of the available binary labeled training data in order to compute the current hypothesis. For this model, we observe that the algorithm can be assumed to always terminate and that the distribution of the training data does not influence learnability. This is still true if we pose additional delayable requirements that remain valid despite a hypothesis output delayed in time. Additionally, we consider the non-delayable requirement of consistent learning. Our corresponding results underpin the claim for delayability being a suitable structural property to describe and collectively investigate a major part of learning success criteria. Our first theorem states the pairwise implications or incomparabilities between an established collection of delayable learning success criteria, the so-called complete map. Especially, the learning algorithm can be assumed to only change its last hypothesis in case it is inconsistent with the current training data. Such a learning behaviour is called conservative. By referring to learning functions, we obtain a hierarchy of approximative learning success criteria. Hereby we allow an increasing finite number of errors of the hypothesized concept by the learning algorithm compared with the concept to be learned. Moreover, we observe a duality depending on whether vacillations between infinitely many different correct hypotheses are still considered a successful learning behaviour. This contrasts the vacillatory hierarchy for learning from solely positive information. We also consider a hypothesis space located between the two most common hypothesis space types in the nearby relevant literature and provide the complete map. In the second part, we model more efficient learning algorithms. These update their hypothesis referring to the current datum and without direct regress to past training data. We focus on iterative (hypothesis based) and BMS (state based) learning algorithms. Iterative learning algorithms use the last hypothesis and the current datum in order to infer the new hypothesis. Past research analyzed, for example, the above mentioned pairwise relations between delayable learning success criteria when learning from purely positive training data. We compare delayable learning success criteria with respect to iterative learning algorithms, as well as learning from either exclusively positive or binary labeled data. The existence of concept classes that can be learned by an iterative learning algorithm but not in a conservative way had already been observed, showing that conservativeness is restrictive. An additional requirement arising from cognitive science research \%and also observed when training neural networks is U-shapedness, stating that the learning algorithm does diverge from a correct hypothesis. We show that forbidding U-shapes also restricts iterative learners from binary labeled data. In order to compute the next hypothesis, BMS learning algorithms refer to the currently observed datum and the actual state of the learning algorithm. For learning algorithms equipped with an infinite amount of states, we provide the complete map. A learning success criterion is semantic if it still holds, when the learning algorithm outputs other parameters standing for the same classifier. Syntactic (non-semantic) learning success criteria, for example conservativeness and syntactic non-U-shapedness, restrict BMS learning algorithms. For proving the equivalence of the syntactic requirements, we refer to witness-based learning processes. In these, every change of the hypothesis is justified by a later on correctly classified witness from the training data. Moreover, for every semantic delayable learning requirement, iterative and BMS learning algorithms are equivalent. In case the considered learning success criterion incorporates syntactic non-U-shapedness, BMS learning algorithms can learn more concept classes than iterative learning algorithms. The proofs are combinatorial, inspired by investigating formal languages or employ results from computability theory, such as infinite recursion theorems (fixed point theorems).},
  language  = {en}
}
@phdthesis{Schirneck2022,
  author    = {Schirneck, Friedrich Martin},
  title     = {Enumeration algorithms in data profiling},
  doi       = {10.25932/publishup-55672},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-556726},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 192},
  year      = {2022},
  abstract  = {Data profiling is the extraction of metadata from relational databases. An important class of metadata are multi-column dependencies. They come associated with two computational tasks. The detection problem is to decide whether a dependency of a given type and size holds in a database. The discovery problem instead asks to enumerate all valid dependencies of that type. We investigate the two problems for three types of dependencies: unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We first treat the parameterized complexity of the detection variants. We prove that the detection of UCCs and FDs, respectively, is W[2]-complete when parameterized by the size of the dependency. The detection of INDs is shown to be one of the first natural W[3]-complete problems. We further settle the enumeration complexity of the three discovery problems by presenting parsimonious equivalences with well-known enumeration problems. Namely, the discovery of UCCs is equivalent to the famous transversal hypergraph problem of enumerating the hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. Finally, the discovery of INDs is shown to be equivalent to enumerating the satisfying assignments of antimonotone, 3-normalized Boolean formulas. In the remainder of the thesis, we design and analyze discovery algorithms for unique column combinations. Since this is as hard as the general transversal hypergraph problem, it is an open question whether the UCCs of a database can be computed in output-polynomial time in the worst case. For the analysis, we therefore focus on instances that are structurally close to databases in practice, most notably, inputs that have small solutions. The equivalence between UCCs and hitting sets transfers the computational hardness, but also allows us to apply ideas from hypergraph theory to data profiling. We devise an discovery algorithm that runs in polynomial space on arbitrary inputs and achieves polynomial delay whenever the maximum size of any minimal UCC is bounded. Central to our approach is the extension problem for minimal hitting sets, that is, to decide for a set of vertices whether they are contained in any minimal solution. We prove that this is yet another problem that is complete for the complexity class W[3], when parameterized by the size of the set that is to be extended. We also give several conditional lower bounds under popular hardness conjectures such as the Strong Exponential Time Hypothesis (SETH). The lower bounds suggest that the running time of our algorithm for the extension problem is close to optimal. We further conduct an empirical analysis of our discovery algorithm on real-world databases to confirm that the hitting set perspective on data profiling has merits also in practice. We show that the resulting enumeration times undercut their theoretical worst-case bounds on practical data, and that the memory consumption of our method is much smaller than that of previous solutions. During the analysis we make two observations about the connection between databases and their corresponding hypergraphs. On the one hand, the hypergraph representations containing all relevant information are usually significantly smaller than the original inputs. On the other hand, obtaining those hypergraphs is the actual bottleneck of any practical application. The latter often takes much longer than enumerating the solutions, which is in stark contrast to the fact that the preprocessing is guaranteed to be polynomial while the enumeration may take exponential time. To make the first observation rigorous, we introduce a maximum-entropy model for non-uniform random hypergraphs and prove that their expected number of minimal hyperedges undergoes a phase transition with respect to the total number of edges. The result also explains why larger databases may have smaller hypergraphs. Motivated by the second observation, we present a new kind of UCC discovery algorithm called Hitting Set Enumeration with Partial Information and Validation (HPIValid). It utilizes the fast enumeration times in practice in order to speed up the computation of the corresponding hypergraph. This way, we sidestep the bottleneck while maintaining the advantages of the hitting set perspective. An exhaustive empirical evaluation shows that HPIValid outperforms the current state of the art in UCC discovery. It is capable of processing databases that were previously out of reach for data profiling.},
  language  = {en}
}
@phdthesis{Sapegin2018,
  author    = {Sapegin, Andrey},
  title     = {High-Speed Security Log Analytics Using Hybrid Outlier Detection},
  doi       = {10.25932/publishup-42611},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-426118},
  school      = {Universit{\"a}t Potsdam},
  pages     = {162},
  year      = {2018},
  abstract  = {The rapid development and integration of Information Technologies over the last decades influenced all areas of our life, including the business world. Yet not only the modern enterprises become digitalised, but also security and criminal threats move into the digital sphere. To withstand these threats, modern companies must be aware of all activities within their computer networks. The keystone for such continuous security monitoring is a Security Information and Event Management (SIEM) system that collects and processes all security-related log messages from the entire enterprise network. However, digital transformations and technologies, such as network virtualisation and widespread usage of mobile communications, lead to a constantly increasing number of monitored devices and systems. As a result, the amount of data that has to be processed by a SIEM system is increasing rapidly. Besides that, in-depth security analysis of the captured data requires the application of rather sophisticated outlier detection algorithms that have a high computational complexity. Existing outlier detection methods often suffer from performance issues and are not directly applicable for high-speed and high-volume analysis of heterogeneous security-related events, which becomes a major challenge for modern SIEM systems nowadays. This thesis provides a number of solutions for the mentioned challenges. First, it proposes a new SIEM system architecture for high-speed processing of security events, implementing parallel, in-memory and in-database processing principles. The proposed architecture also utilises the most efficient log format for high-speed data normalisation. Next, the thesis offers several novel high-speed outlier detection methods, including generic Hybrid Outlier Detection that can efficiently be used for Big Data analysis. Finally, the special User Behaviour Outlier Detection is proposed for better threat detection and analysis of particular user behaviour cases. The proposed architecture and methods were evaluated in terms of both performance and accuracy, as well as compared with classical architecture and existing algorithms. These evaluations were performed on multiple data sets, including simulated data, well-known public intrusion detection data set, and real data from the large multinational enterprise. The evaluation results have proved the high performance and efficacy of the developed methods. All concepts proposed in this thesis were integrated into the prototype of the SIEM system, capable of high-speed analysis of Big Security Data, which makes this integrated SIEM platform highly relevant for modern enterprise security applications.},
  language  = {en}
}
@phdthesis{Santuber2023,
  author    = {Santuber, Joaquin},
  title     = {Designing for digital justice},
  doi       = {10.25932/publishup-60417},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604178},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xviii, 183},
  year      = {2023},
  abstract  = {At the beginning of 2020, with COVID-19, courts of justice worldwide had to move online to continue providing judicial service. Digital technologies materialized the court practices in ways unthinkable shortly before the pandemic creating resonances with judicial and legal regulation, as well as frictions. A better understanding of the dynamics at play in the digitalization of courts is paramount for designing justice systems that serve their users better, ensure fair and timely dispute resolutions, and foster access to justice. Building on three major bodies of literature —e-justice, digitalization and organization studies, and design research— Designing for Digital Justice takes a nuanced approach to account for human and more-than-human agencies. Using a qualitative approach, I have studied in depth the digitalization of Chilean courts during the pandemic, specifically between April 2020 and September 2022. Leveraging a comprehensive source of primary and secondary data, I traced back the genealogy of the novel materializations of courts' practices structured by the possibilities offered by digital technologies. In five (5) cases studies, I show in detail how the courts got to 1) work remotely, 2) host hearings via videoconference, 3) engage with users via social media (i.e., Facebook and Chat Messenger), 4) broadcast a show with judges answering questions from users via Facebook Live, and 5) record, stream, and upload judicial hearings to YouTube to fulfil the publicity requirement of criminal hearings. The digitalization of courts during the pandemic is characterized by a suspended normativity, which makes innovation possible yet presents risks. While digital technologies enabled the judiciary to provide services continuously, they also created the risk of displacing traditional judicial and legal regulation. Contributing to liminal innovation and digitalization research, Designing for Digital Justice theorizes four phases: 1) the pre-digitalization phase resulting in the development of regulation, 2) the hotspot of digitalization resulting in the extension of regulation, 3) the digital innovation redeveloping regulation (moving to a new, preliminary phase), and 4) the permanence of temporal practices displacing regulation. Contributing to design research Designing for Digital Justice provides new possibilities for innovation in the courts, focusing at different levels to better address tensions generated by digitalization. Fellow researchers will find in these pages a sound theoretical advancement at the intersection of digitalization and justice with novel methodological references. Practitioners will benefit from the actionable governance framework Designing for Digital Justice Model, which provides three fields of possibilities for action to design better justice systems. Only by taking into account digital, legal, and social factors can we design better systems that promote access to justice, the rule of law, and, ultimately social peace.},
  language  = {en}
}
@phdthesis{Sakizloglou2023,
  author    = {Sakizloglou, Lucas},
  title     = {Evaluating temporal queries over history-aware architectural runtime models},
  doi       = {10.25932/publishup-60439},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604396},
  school      = {Universit{\"a}t Potsdam},
  pages     = {v, 168},
  year      = {2023},
  abstract  = {In model-driven engineering, the adaptation of large software systems with dynamic structure is enabled by architectural runtime models. Such a model represents an abstract state of the system as a graph of interacting components. Every relevant change in the system is mirrored in the model and triggers an evaluation of model queries, which search the model for structural patterns that should be adapted. This thesis focuses on a type of runtime models where the expressiveness of the model and model queries is extended to capture past changes and their timing. These history-aware models and temporal queries enable more informed decision-making during adaptation, as they support the formulation of requirements on the evolution of the pattern that should be adapted. However, evaluating temporal queries during adaptation poses significant challenges. First, it implies the capability to specify and evaluate requirements on the structure, as well as the ordering and timing in which structural changes occur. Then, query answers have to reflect that the history-aware model represents the architecture of a system whose execution may be ongoing, and thus answers may depend on future changes. Finally, query evaluation needs to be adequately fast and memory-efficient despite the increasing size of the history---especially for models that are altered by numerous, rapid changes. The thesis presents a query language and a querying approach for the specification and evaluation of temporal queries. These contributions aim to cope with the challenges of evaluating temporal queries at runtime, a prerequisite for history-aware architectural monitoring and adaptation which has not been systematically treated by prior model-based solutions. The distinguishing features of our contributions are: the specification of queries based on a temporal logic which encodes structural patterns as graphs; the provision of formally precise query answers which account for timing constraints and ongoing executions; the incremental evaluation which avoids the re-computation of query answers after each change; and the option to discard history that is no longer relevant to queries. The query evaluation searches the model for occurrences of a pattern whose evolution satisfies a temporal logic formula. Therefore, besides model-driven engineering, another related research community is runtime verification. The approach differs from prior logic-based runtime verification solutions by supporting the representation and querying of structure via graphs and graph queries, respectively, which is more efficient for queries with complex patterns. We present a prototypical implementation of the approach and measure its speed and memory consumption in monitoring and adaptation scenarios from two application domains, with executions of an increasing size. We assess scalability by a comparison to the state-of-the-art from both related research communities. The implementation yields promising results, which pave the way for sophisticated history-aware self-adaptation solutions and indicate that the approach constitutes a highly effective technique for runtime monitoring on an architectural level.},
  language  = {en}
}
@phdthesis{Roumen2023,
  author    = {Roumen, Thijs},
  title     = {Portable models for laser cutting},
  doi       = {10.25932/publishup-57814},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-578141},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xx, 170},
  year      = {2023},
  abstract  = {Laser cutting is a fast and precise fabrication process. This makes laser cutting a powerful process in custom industrial production. Since the patents on the original technology started to expire, a growing community of tech-enthusiasts embraced the technology and started sharing the models they fabricate online. Surprisingly, the shared models appear to largely be one-offs (e.g., they proudly showcase what a single person can make in one afternoon). For laser cutting to become a relevant mainstream phenomenon (as opposed to the current tech enthusiasts and industry users), it is crucial to enable users to reproduce models made by more experienced modelers, and to build on the work of others instead of creating one-offs. We create a technological basis that allows users to build on the work of others—a progression that is currently held back by the use of exchange formats that disregard mechanical differences between machines and therefore overlook implications with respect to how well parts fit together mechanically (aka engineering fit). For the field to progress, we need a machine-independent sharing infrastructure. In this thesis, we outline three approaches that together get us closer to this: (1) 2D cutting plans that are tolerant to machine variations. Our initial take is a minimally invasive approach: replacing machine-specific elements in cutting plans with more tolerant elements using mechanical hacks like springs and wedges. The resulting models fabricate on any consumer laser cutter and in a range of materials. (2) sharing models in 3D. To allow building on the work of others, we build a 3D modeling environment for laser cutting (kyub). After users design a model, they export their 3D models to 2D cutting plans optimized for the machine and material at hand. We extend this volumetric environment with tools to edit individual plates, allowing users to leverage the efficiency of volumetric editing while having control over the most detailed elements in laser-cutting (plates) (3) converting legacy 2D cutting plans to 3D models. To handle legacy models, we build software to interactively reconstruct 3D models from 2D cutting plans. This allows users to reuse the models in more productive ways. We revisit this by automating the assembly process for a large subset of models. The above-mentioned software composes a larger system (kyub, 140,000 lines of code). This system integration enables the push towards actual use, which we demonstrate through a range of workshops where users build complex models such as fully functional guitars. By simplifying sharing and re-use and the resulting increase in model complexity, this line of work forms a small step to enable personal fabrication to scale past the maker phenomenon, towards a mainstream phenomenon—the same way that other fields, such as print (postscript) and ultimately computing itself (portable programming languages, etc.) reached mass adoption.},
  language  = {en}
}
@phdthesis{Rothenberger2022,
  author    = {Rothenberger, Ralf},
  title     = {Satisfiability thresholds for non-uniform random k-SAT},
  doi       = {10.25932/publishup-54970},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-549702},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 163},
  year      = {2022},
  abstract  = {Boolean Satisfiability (SAT) is one of the problems at the core of theoretical computer science. It was the first problem proven to be NP-complete by Cook and, independently, by Levin. Nowadays it is conjectured that SAT cannot be solved in sub-exponential time. Thus, it is generally assumed that SAT and its restricted version k-SAT are hard to solve. However, state-of-the-art SAT solvers can solve even huge practical instances of these problems in a reasonable amount of time. Why is SAT hard in theory, but easy in practice? One approach to answering this question is investigating the average runtime of SAT. In order to analyze this average runtime the random k-SAT model was introduced. The model generates all k-SAT instances with n variables and m clauses with uniform probability. Researching random k-SAT led to a multitude of insights and tools for analyzing random structures in general. One major observation was the emergence of the so-called satisfiability threshold: A phase transition point in the number of clauses at which the generated formulas go from asymptotically almost surely satisfiable to asymptotically almost surely unsatisfiable. Additionally, instances around the threshold seem to be particularly hard to solve. In this thesis we analyze a more general model of random k-SAT that we call non-uniform random k-SAT. In contrast to the classical model each of the n Boolean variables now has a distinct probability of being drawn. For each of the m clauses we draw k variables according to the variable distribution and choose their signs uniformly at random. Non-uniform random k-SAT gives us more control over the distribution of Boolean variables in the resulting formulas. This allows us to tailor distributions to the ones observed in practice. Notably, non-uniform random k-SAT contains the previously proposed models random k-SAT, power-law random k-SAT and geometric random k-SAT as special cases. We analyze the satisfiability threshold in non-uniform random k-SAT depending on the variable probability distribution. Our goal is to derive conditions on this distribution under which an equivalent of the satisfiability threshold conjecture holds. We start with the arguably simpler case of non-uniform random 2-SAT. For this model we show under which conditions a threshold exists, if it is sharp or coarse, and what the leading constant of the threshold function is. These are exactly the three ingredients one needs in order to prove or disprove the satisfiability threshold conjecture. For non-uniform random k-SAT with k=3 we only prove sufficient conditions under which a threshold exists. We also show some properties of the variable probabilities under which the threshold is sharp in this case. These are the first results on the threshold behavior of non-uniform random k-SAT.},
  language  = {en}
}
@phdthesis{Rohloff2021,
  author    = {Rohloff, Tobias},
  title     = {Learning analytics at scale},
  doi       = {10.25932/publishup-52623},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-526235},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvii, 138, lxvii},
  year      = {2021},
  abstract  = {Digital technologies are paving the way for innovative educational approaches. The learning format of Massive Open Online Courses (MOOCs) provides a highly accessible path to lifelong learning while being more affordable and flexible than face-to-face courses. Thereby, thousands of learners can enroll in courses mostly without admission restrictions, but this also raises challenges. Individual supervision by teachers is barely feasible, and learning persistence and success depend on students' self-regulatory skills. Here, technology provides the means for support. The use of data for decision-making is already transforming many fields, whereas in education, it is still a young research discipline. Learning Analytics (LA) is defined as the measurement, collection, analysis, and reporting of data about learners and their learning contexts with the purpose of understanding and improving learning and learning environments. The vast amount of data that MOOCs produce on the learning behavior and success of thousands of students provides the opportunity to study human learning and develop approaches addressing the demands of learners and teachers. The overall purpose of this dissertation is to investigate the implementation of LA at the scale of MOOCs and to explore how data-driven technology can support learning and teaching in this context. To this end, several research prototypes have been iteratively developed for the HPI MOOC Platform. Hence, they were tested and evaluated in an authentic real-world learning environment. Most of the results can be applied on a conceptual level to other MOOC platforms as well. The research contribution of this thesis thus provides practical insights beyond what is theoretically possible. In total, four system components were developed and extended: (1) The Learning Analytics Architecture: A technical infrastructure to collect, process, and analyze event-driven learning data based on schema-agnostic pipelining in a service-oriented MOOC platform. (2) The Learning Analytics Dashboard for Learners: A tool for data-driven support of self-regulated learning, in particular to enable learners to evaluate and plan their learning activities, progress, and success by themselves. (3) Personalized Learning Objectives: A set of features to better connect learners' success to their personal intentions based on selected learning objectives to offer guidance and align the provided data-driven insights about their learning progress. (4) The Learning Analytics Dashboard for Teachers: A tool supporting teachers with data-driven insights to enable the monitoring of their courses with thousands of learners, identify potential issues, and take informed action. For all aspects examined in this dissertation, related research is presented, development processes and implementation concepts are explained, and evaluations are conducted in case studies. Among other findings, the usage of the learner dashboard in combination with personalized learning objectives demonstrated improved certification rates of 11.62\% to 12.63\%. Furthermore, it was observed that the teacher dashboard is a key tool and an integral part for teaching in MOOCs. In addition to the results and contributions, general limitations of the work are discussed—which altogether provide a solid foundation for practical implications and future research.},
  language  = {en}
}
@phdthesis{Risch2020,
  author    = {Risch, Julian},
  title     = {Reader comment analysis on online news platforms},
  doi       = {10.25932/publishup-48922},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489222},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 135},
  year      = {2020},
  abstract  = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. However, the misuse by spammers, haters, and trolls raises doubts about whether the benefits justify the costs of the time-consuming content moderation. As a consequence, many platforms limited or even shut down comment sections completely. In this thesis, we present deep learning approaches for comment classification, recommendation, and prediction to foster respectful and engaging online discussions. The main focus is on two kinds of comments: toxic comments, which make readers leave a discussion, and engaging comments, which make readers join a discussion. First, we discourage and remove toxic comments, e.g., insults or threats. To this end, we present a semi-automatic comment moderation process, which is based on fine-grained text classification models and supports moderators. Our experiments demonstrate that data augmentation, transfer learning, and ensemble learning allow training robust classifiers even on small datasets. To establish trust in the machine-learned models, we reveal which input features are decisive for their output with attribution-based explanation methods. Second, we encourage and highlight engaging comments, e.g., serious questions or factual statements. We automatically identify the most engaging comments, so that readers need not scroll through thousands of comments to find them. The model training process builds on upvotes and replies as a measure of reader engagement. We also identify comments that address the article authors or are otherwise relevant to them to support interactions between journalists and their readership. Taking into account the readers' interests, we further provide personalized recommendations of discussions that align with their favored topics or involve frequent co-commenters. Our models outperform multiple baselines and recent related work in experiments on comment datasets from different platforms.},
  language  = {en}
}
@phdthesis{Richter2018,
  author    = {Richter, Rico},
  title     = {Concepts and techniques for processing and rendering of massive 3D point clouds},
  doi       = {10.25932/publishup-42330},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-423304},
  school      = {Universit{\"a}t Potsdam},
  pages     = {v, 131},
  year      = {2018},
  abstract  = {Remote sensing technology, such as airborne, mobile, or terrestrial laser scanning, and photogrammetric techniques, are fundamental approaches for efficient, automatic creation of digital representations of spatial environments. For example, they allow us to generate 3D point clouds of landscapes, cities, infrastructure networks, and sites. As essential and universal category of geodata, 3D point clouds are used and processed by a growing number of applications, services, and systems such as in the domains of urban planning, landscape architecture, environmental monitoring, disaster management, virtual geographic environments as well as for spatial analysis and simulation. While the acquisition processes for 3D point clouds become more and more reliable and widely-used, applications and systems are faced with more and more 3D point cloud data. In addition, 3D point clouds, by their very nature, are raw data, i.e., they do not contain any structural or semantics information. Many processing strategies common to GIS such as deriving polygon-based 3D models generally do not scale for billions of points. GIS typically reduce data density and precision of 3D point clouds to cope with the sheer amount of data, but that results in a significant loss of valuable information at the same time. This thesis proposes concepts and techniques designed to efficiently store and process massive 3D point clouds. To this end, object-class segmentation approaches are presented to attribute semantics to 3D point clouds, used, for example, to identify building, vegetation, and ground structures and, thus, to enable processing, analyzing, and visualizing 3D point clouds in a more effective and efficient way. Similarly, change detection and updating strategies for 3D point clouds are introduced that allow for reducing storage requirements and incrementally updating 3D point cloud databases. In addition, this thesis presents out-of-core, real-time rendering techniques used to interactively explore 3D point clouds and related analysis results. All techniques have been implemented based on specialized spatial data structures, out-of-core algorithms, and GPU-based processing schemas to cope with massive 3D point clouds having billions of points. All proposed techniques have been evaluated and demonstrated their applicability to the field of geospatial applications and systems, in particular for tasks such as classification, processing, and visualization. Case studies for 3D point clouds of entire cities with up to 80 billion points show that the presented approaches open up new ways to manage and apply large-scale, dense, and time-variant 3D point clouds as required by a rapidly growing number of applications and systems.},
  language  = {en}
}
@phdthesis{Richly2024,
  author    = {Richly, Keven},
  title     = {Memory-efficient data management for spatio-temporal applications},
  doi       = {10.25932/publishup-63547},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635473},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 181},
  year      = {2024},
  abstract  = {The wide distribution of location-acquisition technologies means that large volumes of spatio-temporal data are continuously being accumulated. Positioning systems such as GPS enable the tracking of various moving objects' trajectories, which are usually represented by a chronologically ordered sequence of observed locations. The analysis of movement patterns based on detailed positional information creates opportunities for applications that can improve business decisions and processes in a broad spectrum of industries (e.g., transportation, traffic control, or medicine). Due to the large data volumes generated in these applications, the cost-efficient storage of spatio-temporal data is desirable, especially when in-memory database systems are used to achieve interactive performance requirements. To efficiently utilize the available DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes structures). By considering horizontal data partitioning, we can independently apply different tuning options on a fine-grained level. However, the selection of cost and performance-balancing configurations is challenging, due to the vast number of possible setups consisting of mutually dependent individual decisions. In this thesis, we introduce multiple approaches to improve spatio-temporal data management by automatically optimizing diverse tuning options for the application-specific access patterns and data characteristics. Our contributions are as follows: (1) We introduce a novel approach to determine fine-grained table configurations for spatio-temporal workloads. Our linear programming (LP) approach jointly optimizes the (i) data compression, (ii) ordering, (iii) indexing, and (iv) tiering. We propose different models which address cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload, memory budgets, and data characteristics. To yield maintainable and robust configurations, we further extend our LP-based approach to incorporate reconfiguration costs as well as optimizations for multiple potential workload scenarios. (2) To optimize the storage layout of timestamps in columnar databases, we present a heuristic approach for the workload-driven combined selection of a data layout and compression scheme. By considering attribute decomposition strategies, we are able to apply application-specific optimizations that reduce the memory footprint and improve performance. (3) We introduce an approach that leverages past trajectory data to improve the dispatch processes of transportation network companies. Based on location probabilities, we developed risk-averse dispatch strategies that reduce critical delays. (4) Finally, we used the use case of a transportation network company to evaluate our database optimizations on a real-world dataset. We demonstrate that workload-driven fine-grained optimizations allow us to reduce the memory footprint (up to 71\% by equal performance) or increase the performance (up to 90\% by equal memory size) compared to established rule-based heuristics. Individually, our contributions provide novel approaches to the current challenges in spatio-temporal data mining and database research. Combining them allows in-memory databases to store and process spatio-temporal data more cost-efficiently.},
  language  = {en}
}
@phdthesis{Rezaei2019,
  author    = {Rezaei, Mina},
  title     = {Deep representation learning from imbalanced medical imaging},
  doi       = {10.25932/publishup-44275},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-442759},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxviii, 160},
  year      = {2019},
  abstract  = {Medical imaging plays an important role in disease diagnosis, treatment planning, and clinical monitoring. One of the major challenges in medical image analysis is imbalanced training data, in which the class of interest is much rarer than the other classes. Canonical machine learning algorithms suppose that the number of samples from different classes in the training dataset is roughly similar or balance. Training a machine learning model on an imbalanced dataset can introduce unique challenges to the learning problem. A model learned from imbalanced training data is biased towards the high-frequency samples. The predicted results of such networks have low sensitivity and high precision. In medical applications, the cost of misclassification of the minority class could be more than the cost of misclassification of the majority class. For example, the risk of not detecting a tumor could be much higher than referring to a healthy subject to a doctor. The current Ph.D. thesis introduces several deep learning-based approaches for handling class imbalanced problems for learning multi-task such as disease classification and semantic segmentation. At the data-level, the objective is to balance the data distribution through re-sampling the data space: we propose novel approaches to correct internal bias towards fewer frequency samples. These approaches include patient-wise batch sampling, complimentary labels, supervised and unsupervised minority oversampling using generative adversarial networks for all. On the other hand, at algorithm-level, we modify the learning algorithm to alleviate the bias towards majority classes. In this regard, we propose different generative adversarial networks for cost-sensitive learning, ensemble learning, and mutual learning to deal with highly imbalanced imaging data. We show evidence that the proposed approaches are applicable to different types of medical images of varied sizes on different applications of routine clinical tasks, such as disease classification and semantic segmentation. Our various implemented algorithms have shown outstanding results on different medical imaging challenges.},
  language  = {en}
}
@phdthesis{Repke2022,
  author    = {Repke, Tim},
  title     = {Machine-learning-assisted corpus exploration and visualisation},
  doi       = {10.25932/publishup-56263},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-562636},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 131},
  year      = {2022},
  abstract  = {Text collections, such as corpora of books, research articles, news, or business documents are an important resource for knowledge discovery. Exploring large document collections by hand is a cumbersome but necessary task to gain new insights and find relevant information. Our digitised society allows us to utilise algorithms to support the information seeking process, for example with the help of retrieval or recommender systems. However, these systems only provide selective views of the data and require some prior knowledge to issue meaningful queries and asses a system's response. The advancements of machine learning allow us to reduce this gap and better assist the information seeking process. For example, instead of sighting countless business documents by hand, journalists and investigator scan employ natural language processing techniques, such as named entity recognition. Al-though this greatly improves the capabilities of a data exploration platform, the wealth of information is still overwhelming. An overview of the entirety of a dataset in the form of a two-dimensional map-like visualisation may help to circumvent this issue. Such overviews enable novel interaction paradigms for users, which are similar to the exploration of digital geographical maps. In particular, they can provide valuable context by indicating how apiece of information fits into the bigger picture.This thesis proposes algorithms that appropriately pre-process heterogeneous documents and compute the layout for datasets of all kinds. Traditionally, given high-dimensional semantic representations of the data, so-called dimensionality reduction algorithms are usedto compute a layout of the data on a two-dimensional canvas. In this thesis, we focus on text corpora and go beyond only projecting the inherent semantic structure itself. Therefore,we propose three dimensionality reduction approaches that incorporate additional information into the layout process: (1) a multi-objective dimensionality reduction algorithm to jointly visualise semantic information with inherent network information derived from the underlying data; (2) a comparison of initialisation strategies for different dimensionality reduction algorithms to generate a series of layouts for corpora that grow and evolve overtime; (3) and an algorithm that updates existing layouts by incorporating user feedback provided by pointwise drag-and-drop edits. This thesis also contains system prototypes to demonstrate the proposed technologies, including pre-processing and layout of the data and presentation in interactive user interfaces.},
  language  = {en}
}
@phdthesis{Renz2020,
  author    = {Renz, Jan},
  title     = {Lebensbegleitendes Lernen in einer digitalen Welt},
  doi       = {10.25932/publishup-47257},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-472573},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 184},
  year      = {2020},
  abstract  = {In unserer digitalisierten Welt verlagert sich das Lernen in die Cloud. Vom Unterricht in der Schule und der Tafel zum Tablet, hin zu einem lebenslangen Lernen in der Arbeitswelt und sogar dar{\"u}ber hinaus. Wie erfolgreich und attraktiv dieses zeitgem{\"a}ße Lernen erfolgt, h{\"a}ngt nicht unwesentlich von den technologischen M{\"o}glichkeiten ab, die digitale Lernplattformen rund um MOOCs und Schul-Clouds bieten. Bei deren Weiterentwicklung sollten statt {\"o}konomischen Messgr{\"o}ßen und KPIs die Lernenden und ihre Lernerfahrungen im Vordergrund stehen. Hierf{\"u}r wurde ein Optimierungsframework entwickelt, das f{\"u}r die Entwicklung von Lernplattformen anhand verschiedener qualitativer und quantitative Methoden Verbesserungen identifiziert, priorisiert und deren Beurteilung und Umsetzung steuert. Datengest{\"u}tzte Entscheidungen sollten auf einer ausreichenden Datenbasis aufbauen. Moderne Web-Anwendungen bestehen aber oft aus mehreren Microservices mit jeweils eigener Datenhaltung. Viele Daten sind daher nicht mehr einfach zug{\"a}nglich. Daher wird in dieser Arbeit ein Learning Analytics Dienst eingef{\"u}hrt, der diese Daten sammelt und verarbeitet. Darauf aufbauend werden Metriken eingef{\"u}hrt, auf deren Grundlage die erfassten Daten nutzbar werden und die somit zu verschiedenen Zwecken verwendet werden k{\"o}nnen. Neben der Visualisierung der Daten in Dashboards werden die Daten f{\"u}r eine automatisierte Qualit{\"a}tskontrolle herangezogen. So kann festgestellt werden, wenn Tests zu schwierig oder die soziale Interaktion in einem MOOC zu gering ist. Die vorgestellte Infrastruktur l{\"a}sst sich aber auch verwenden, um verschiedene A/B/n-Tests durchzuf{\"u}hren. In solchen Tests gibt es mehrere Varianten, die an verschiedene Nutzergruppen in einem kontrollierten Experiment erprobt werden. Dank der vorgestellten Testinfrastruktur, die in der HPI MOOC Plattform eingebaut wurde, kann ermittelt werden, ob sich f{\"u}r diese Gruppen statistisch signifikante {\"A}nderungen in der Nutzung feststellen lassen. Dies wurde mit f{\"u}nf verschiedenen Verbesserungen der HPI MOOC Plattform evaluiert, auf der auch openHPI und openSAP basieren. Dabei konnte gezeigt werden, dass sich Lernende mit reaktivierenden Mails zur{\"u}ck in den Kurs holen lassen. Es ist prim{\"a}r die Kommunikation der unbearbeiteten Lerninhalte des Nutzers, die eine reaktivierende Wirkung hat. Auch {\"U}bersichtsmails, die die Forenaktivit{\"a}t zusammenfassen, haben einen positiven Effekt erzielt. Ein gezieltes On-Boarding kann dazu f{\"u}hren, dass die Nutzer die Plattform besser verstehen und hierdurch aktiver sind. Der vierte Test konnte zeigen, dass die Zuordnung von Forenfragen zu einem bestimmten Zeitpunkt im Video und die grafische Anzeige dieser Informationen zu einer erh{\"o}hten Forenaktivit{\"a}t f{\"u}hrt. Auch die experimentelle Erprobung von unterschiedlichen Lernmaterialien, wie sie im f{\"u}nften Test durchgef{\"u}hrt wurde, ist in MOOCs hilfreich, um eine Verbesserung der Kursmaterialien zu erreichen. Neben diesen funktionalen Verbesserungen wird untersucht wie MOOC Plattformen und Schul-Clouds einen Nutzen bieten k{\"o}nnen, wenn Nutzern nur eine schwache oder unzuverl{\"a}ssige Internetanbindung zur Verf{\"u}gung steht (wie dies in vielen deutschen Schulen der Fall ist). Hier wird gezeigt, dass durch ein geschicktes Vorausladen von Daten die Internetanbindungen entlastet werden k{\"o}nnen. Teile der Lernanwendungen funktionieren dank dieser Anpassungen, selbst wenn keine Verbindung zum Internet besteht. Als Letztes wird gezeigt, wie Endger{\"a}te sich in einem lokalen Peer-to-Peer CDN gegenseitig mit Daten versorgen k{\"o}nnen, ohne dass diese aus dem Internet heruntergeladen werden m{\"u}ssen.},
  language  = {de}
}
@phdthesis{Quinzan2023,
  author    = {Quinzan, Francesco},
  title     = {Combinatorial problems and scalability in artificial intelligence},
  doi       = {10.25932/publishup-61111},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-611114},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 141},
  year      = {2023},
  abstract  = {Modern datasets often exhibit diverse, feature-rich, unstructured data, and they are massive in size. This is the case of social networks, human genome, and e-commerce databases. As Artificial Intelligence (AI) systems are increasingly used to detect pattern in data and predict future outcome, there are growing concerns on their ability to process large amounts of data. Motivated by these concerns, we study the problem of designing AI systems that are scalable to very large and heterogeneous data-sets. Many AI systems require to solve combinatorial optimization problems in their course of action. These optimization problems are typically NP-hard, and they may exhibit additional side constraints. However, the underlying objective functions often exhibit additional properties. These properties can be exploited to design suitable optimization algorithms. One of these properties is the well-studied notion of submodularity, which captures diminishing returns. Submodularity is often found in real-world applications. Furthermore, many relevant applications exhibit generalizations of this property. In this thesis, we propose new scalable optimization algorithms for combinatorial problems with diminishing returns. Specifically, we focus on three problems, the Maximum Entropy Sampling problem, Video Summarization, and Feature Selection. For each problem, we propose new algorithms that work at scale. These algorithms are based on a variety of techniques, such as forward step-wise selection and adaptive sampling. Our proposed algorithms yield strong approximation guarantees, and the perform well experimentally. We first study the Maximum Entropy Sampling problem. This problem consists of selecting a subset of random variables from a larger set, that maximize the entropy. By using diminishing return properties, we develop a simple forward step-wise selection optimization algorithm for this problem. Then, we study the problem of selecting a subset of frames, that represent a given video. Again, this problem corresponds to a submodular maximization problem. We provide a new adaptive sampling algorithm for this problem, suitable to handle the complex side constraints imposed by the application. We conclude by studying Feature Selection. In this case, the underlying objective functions generalize the notion of submodularity. We provide a new adaptive sequencing algorithm for this problem, based on the Orthogonal Matching Pursuit paradigm. Overall, we study practically relevant combinatorial problems, and we propose new algorithms to solve them. We demonstrate that these algorithms are suitable to handle massive datasets. However, our analysis is not problem-specific, and our results can be applied to other domains, if diminishing return properties hold. We hope that the flexibility of our framework inspires further research into scalability in AI.},
  language  = {en}
}
@phdthesis{Pufahl2018,
  author    = {Pufahl, Luise},
  title     = {Modeling and executing batch activities in business processes},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-408013},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 163},
  year      = {2018},
  abstract  = {Business process automation improves organizations' efficiency to perform work. Therefore, a business process is first documented as a process model which then serves as blueprint for a number of process instances representing the execution of specific business cases. In existing business process management systems, process instances run independently from each other. However, in practice, instances are also collected in groups at certain process activities for a combined execution to improve the process performance. Currently, this so-called batch processing is executed manually or supported by external software. Only few research proposals exist to explicitly represent and execute batch processing needs in business process models. These works also lack a comprehensive understanding of requirements. This thesis addresses the described issues by providing a basic concept, called batch activity. It allows an explicit representation of batch processing configurations in process models and provides a corresponding execution semantics, thereby easing automation. The batch activity groups different process instances based on their data context and can synchronize their execution over one or as well multiple process activities. The concept is conceived based on a requirements analysis considering existing literature on batch processing from different domains and industry examples. Further, this thesis provides two extensions: First, a flexible batch configuration concept, based on event processing techniques, is introduced to allow run time adaptations of batch configurations. Second, a concept for collecting and batching activity instances of multiple different process models is given. Thereby, the batch configuration is centrally defined, independently of the process models, which is especially beneficial for organizations with large process model collections. This thesis provides a technical evaluation as well as a validation of the presented concepts. A prototypical implementation in an existing open-source BPMS shows that with a few extensions, batch processing is enabled. Further, it demonstrates that the consolidated view of several work items in one user form can improve work efficiency. The validation, in which the batch activity concept is applied to different use cases in a simulated environment, implies cost-savings for business processes when a suitable batch configuration is used. For the validation, an extensible business process simulator was developed. It enables process designers to study the influence of a batch activity in a process with regards to its performance.},
  language  = {en}
}
@phdthesis{Podlesny2023,
  author    = {Podlesny, Nikolai Jannik},
  title     = {Quasi-identifier discovery to prevent privacy violating inferences in large high dimensional datasets},
  doi       = {10.25932/publishup-58784},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-587843},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvi, 140},
  year      = {2023},
  abstract  = {Personal data privacy is considered to be a fundamental right. It forms a part of our highest ethical standards and is anchored in legislation and various best practices from the technical perspective. Yet, protecting against personal data exposure is a challenging problem from the perspective of generating privacy-preserving datasets to support machine learning and data mining operations. The issue is further compounded by the fact that devices such as consumer wearables and sensors track user behaviours on such a fine-grained level, thereby accelerating the formation of multi-attribute and large-scale high-dimensional datasets. In recent years, increasing news coverage regarding de-anonymisation incidents, including but not limited to the telecommunication, transportation, financial transaction, and healthcare sectors, have resulted in the exposure of sensitive private information. These incidents indicate that releasing privacy-preserving datasets requires serious consideration from the pre-processing perspective. A critical problem that appears in this regard is the time complexity issue in applying syntactic anonymisation methods, such as k-anonymity, l-diversity, or t-closeness to generating privacy-preserving data. Previous studies have shown that this problem is NP-hard. This thesis focuses on large high-dimensional datasets as an example of a special case of data that is characteristically challenging to anonymise using syntactic methods. In essence, large high-dimensional data contains a proportionately large number of attributes in proportion to the population of attribute values. Applying standard syntactic data anonymisation approaches to generating privacy-preserving data based on such methods results in high information-loss, thereby rendering the data useless for analytics operations or in low privacy due to inferences based on the data when information loss is minimised. We postulate that this problem can be resolved effectively by searching for and eliminating all the quasi-identifiers present in a high-dimensional dataset. Essentially, we quantify the privacy-preserving data sharing problem as the Find-QID problem. Further, we show that despite the complex nature of absolute privacy, the discovery of QID can be achieved reliably for large datasets. The risk of private data exposure through inferences can be circumvented, and both can be practicably achieved without the need for high-performance computers. For this purpose, we present, implement, and empirically assess both mathematical and engineering optimisation methods for a deterministic discovery of privacy-violating inferences. This includes a greedy search scheme by efficiently queuing QID candidates based on their tuple characteristics, projecting QIDs on Bayesian inferences, and countering Bayesian network's state-space-explosion with an aggregation strategy taken from multigrid context and vectorised GPU acceleration. Part of this work showcases magnitudes of processing acceleration, particularly in high dimensions. We even achieve near real-time runtime for currently impractical applications. At the same time, we demonstrate how such contributions could be abused to de-anonymise Kristine A. and Cameron R. in a public Twitter dataset addressing the US Presidential Election 2020. Finally, this work contributes, implements, and evaluates an extended and generalised version of the novel syntactic anonymisation methodology, attribute compartmentation. Attribute compartmentation promises sanitised datasets without remaining quasi-identifiers while minimising information loss. To prove its functionality in the real world, we partner with digital health experts to conduct a medical use case study. As part of the experiments, we illustrate that attribute compartmentation is suitable for everyday use and, as a positive side effect, even circumvents a common domain issue of base rate neglect.},
  language  = {en}
}
@phdthesis{Perscheid2023,
  author    = {Perscheid, Cindy},
  title     = {Integrative biomarker detection using prior knowledge on gene expression data sets},
  doi       = {10.25932/publishup-58241},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-582418},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 197},
  year      = {2023},
  abstract  = {Gene expression data is analyzed to identify biomarkers, e.g. relevant genes, which serve for diagnostic, predictive, or prognostic use. Traditional approaches for biomarker detection select distinctive features from the data based exclusively on the signals therein, facing multiple shortcomings in regards to overfitting, biomarker robustness, and actual biological relevance. Prior knowledge approaches are expected to address these issues by incorporating prior biological knowledge, e.g. on gene-disease associations, into the actual analysis. However, prior knowledge approaches are currently not widely applied in practice because they are often use-case specific and seldom applicable in a different scope. This leads to a lack of comparability of prior knowledge approaches, which in turn makes it currently impossible to assess their effectiveness in a broader context. Our work addresses the aforementioned issues with three contributions. Our first contribution provides formal definitions for both prior knowledge and the flexible integration thereof into the feature selection process. Central to these concepts is the automatic retrieval of prior knowledge from online knowledge bases, which allows for streamlining the retrieval process and agreeing on a uniform definition for prior knowledge. We subsequently describe novel and generalized prior knowledge approaches that are flexible regarding the used prior knowledge and applicable to varying use case domains. Our second contribution is the benchmarking platform Comprior. Comprior applies the aforementioned concepts in practice and allows for flexibly setting up comprehensive benchmarking studies for examining the performance of existing and novel prior knowledge approaches. It streamlines the retrieval of prior knowledge and allows for combining it with prior knowledge approaches. Comprior demonstrates the practical applicability of our concepts and further fosters the overall development and comparability of prior knowledge approaches. Our third contribution is a comprehensive case study on the effectiveness of prior knowledge approaches. For that, we used Comprior and tested a broad range of both traditional and prior knowledge approaches in combination with multiple knowledge bases on data sets from multiple disease domains. Ultimately, our case study constitutes a thorough assessment of a) the suitability of selected knowledge bases for integration, b) the impact of prior knowledge being applied at different integration levels, and c) the improvements in terms of classification performance, biological relevance, and overall robustness. In summary, our contributions demonstrate that generalized concepts for prior knowledge and a streamlined retrieval process improve the applicability of prior knowledge approaches. Results from our case study show that the integration of prior knowledge positively affects biomarker results, particularly regarding their robustness. Our findings provide the first in-depth insights on the effectiveness of prior knowledge approaches and build a valuable foundation for future research.},
  language  = {en}
}
@phdthesis{Perlich2019,
  author    = {Perlich, Anja},
  title     = {Digital collaborative documentation in mental healthcare},
  doi       = {10.25932/publishup-44029},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-440292},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 135},
  year      = {2019},
  abstract  = {With the growth of information technology, patient attitudes are shifting - away from passively receiving care towards actively taking responsibility for their well- being. Handling doctor-patient relationships collaboratively and providing patients access to their health information are crucial steps in empowering patients. In mental healthcare, the implicit consensus amongst practitioners has been that sharing medical records with patients may have an unpredictable, harmful impact on clinical practice. In order to involve patients more actively in mental healthcare processes, Tele-Board MED (TBM) allows for digital collaborative documentation in therapist-patient sessions. The TBM software system offers a whiteboard-inspired graphical user interface that allows therapist and patient to jointly take notes during the treatment session. Furthermore, it provides features to automatically reuse the digital treatment session notes for the creation of treatment session summaries and clinical case reports. This thesis presents the development of the TBM system and evaluates its effects on 1) the fulfillment of the therapist's duties of clinical case documentation, 2) patient engagement in care processes, and 3) the therapist-patient relationship. Following the design research methodology, TBM was developed and tested in multiple evaluation studies in the domains of cognitive behavioral psychotherapy and addiction care. The results show that therapists are likely to use TBM with patients if they have a technology-friendly attitude and when its use suits the treatment context. Support in carrying out documentation duties as well as fulfilling legal requirements contributes to therapist acceptance. Furthermore, therapists value TBM as a tool to provide a discussion framework and quick access to worksheets during treatment sessions. Therapists express skepticism, however, regarding technology use in patient sessions and towards complete record transparency in general. Patients expect TBM to improve the communication with their therapist and to offer a better recall of discussed topics when taking a copy of their notes home after the session. Patients are doubtful regarding a possible distraction of the therapist and usage in situations when relationship-building is crucial. When applied in a clinical environment, collaborative note-taking with TBM encourages patient engagement and a team feeling between therapist and patient. Furthermore, it increases the patient's acceptance of their diagnosis, which in turn is an important predictor for therapy success. In summary, TBM has a high potential to deliver more than documentation support and record transparency for patients, but also to contribute to a collaborative doctor-patient relationship. This thesis provides design implications for the development of digital collaborative documentation systems in (mental) healthcare as well as recommendations for a successful implementation in clinical practice.},
  language  = {en}
}
@phdthesis{Papenbrock2017,
  author    = {Papenbrock, Thorsten},
  title     = {Data profiling - efficient discovery of dependencies},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406705},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, ii, 141},
  year      = {2017},
  abstract  = {Data profiling is the computer science discipline of analyzing a given dataset for its metadata. The types of metadata range from basic statistics, such as tuple counts, column aggregations, and value distributions, to much more complex structures, in particular inclusion dependencies (INDs), unique column combinations (UCCs), and functional dependencies (FDs). If present, these statistics and structures serve to efficiently store, query, change, and understand the data. Most datasets, however, do not provide their metadata explicitly so that data scientists need to profile them. While basic statistics are relatively easy to calculate, more complex structures present difficult, mostly NP-complete discovery tasks; even with good domain knowledge, it is hardly possible to detect them manually. Therefore, various profiling algorithms have been developed to automate the discovery. None of them, however, can process datasets of typical real-world size, because their resource consumptions and/or execution times exceed effective limits. In this thesis, we propose novel profiling algorithms that automatically discover the three most popular types of complex metadata, namely INDs, UCCs, and FDs, which all describe different kinds of key dependencies. The task is to extract all valid occurrences from a given relational instance. The three algorithms build upon known techniques from related work and complement them with algorithmic paradigms, such as divide \& conquer, hybrid search, progressivity, memory sensitivity, parallelization, and additional pruning to greatly improve upon current limitations. Our experiments show that the proposed algorithms are orders of magnitude faster than related work. They are, in particular, now able to process datasets of real-world, i.e., multiple gigabytes size with reasonable memory and time consumption. Due to the importance of data profiling in practice, industry has built various profiling tools to support data scientists in their quest for metadata. These tools provide good support for basic statistics and they are also able to validate individual dependencies, but they lack real discovery features even though some fundamental discovery techniques are known for more than 15 years. To close this gap, we developed Metanome, an extensible profiling platform that incorporates not only our own algorithms but also many further algorithms from other researchers. With Metanome, we make our research accessible to all data scientists and IT-professionals that are tasked with data profiling. Besides the actual metadata discovery, the platform also offers support for the ranking and visualization of metadata result sets. Being able to discover the entire set of syntactically valid metadata naturally introduces the subsequent task of extracting only the semantically meaningful parts. This is challenge, because the complete metadata results are surprisingly large (sometimes larger than the datasets itself) and judging their use case dependent semantic relevance is difficult. To show that the completeness of these metadata sets is extremely valuable for their usage, we finally exemplify the efficient processing and effective assessment of functional dependencies for the use case of schema normalization.},
  language  = {en}
}
@phdthesis{Pape2021,
  author    = {Pape, Tobias},
  title     = {Efficient compound values in virtual machines},
  doi       = {10.25932/publishup-49913},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-499134},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxix, 242},
  year      = {2021},
  abstract  = {Compound values are not universally supported in virtual machine (VM)-based programming systems and languages. However, providing data structures with value characteristics can be beneficial. On one hand, programming systems and languages can adequately represent physical quantities with compound values and avoid inconsistencies, for example, in representation of large numbers. On the other hand, just-in-time (JIT) compilers, which are often found in VMs, can rely on the fact that compound values are immutable, which is an important property in optimizing programs. Considering this, compound values have an optimization potential that can be put to use by implementing them in VMs in a way that is efficient in memory usage and execution time. Yet, optimized compound values in VMs face certain challenges: to maintain consistency, it should not be observable by the program whether compound values are represented in an optimized way by a VM; an optimization should take into account, that the usage of compound values can exhibit certain patterns at run-time; and that necessary value-incompatible properties due to implementation restrictions should be reduced. We propose a technique to detect and compress common patterns of compound value usage at run-time to improve memory usage and execution speed. Our approach identifies patterns of frequent compound value references and introduces abbreviated forms for them. Thus, it is possible to store multiple inter-referenced compound values in an inlined memory representation, reducing the overhead of metadata and object references. We extend our approach by a notion of limited mutability, using cells that act as barriers for our approach and provide a location for shared, mutable access with the possibility of type specialization. We devise an extension to our approach that allows us to express automatic unboxing of boxed primitive data types in terms of our initial technique. We show that our approach is versatile enough to express another optimization technique that relies on values, such as Booleans, that are unique throughout a programming system. Furthermore, we demonstrate how to re-use learned usage patterns and optimizations across program runs, thus reducing the performance impact of pattern recognition. We show in a best-case prototype that the implementation of our approach is feasible and can also be applied to general purpose programming systems, namely implementations of the Racket language and Squeak/Smalltalk. In several micro-benchmarks, we found that our approach can effectively reduce memory consumption and improve execution speed.},
  language  = {en}
}
@phdthesis{Nikaj2019,
  author    = {Nikaj, Adriatik},
  title     = {Restful choreographies},
  doi       = {10.25932/publishup-43890},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-438903},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 146},
  year      = {2019},
  abstract  = {Business process management has become a key instrument to organize work as many companies represent their operations in business process models. Recently, business process choreography diagrams have been introduced as part of the Business Process Model and Notation standard to represent interactions between business processes, run by different partners. When it comes to the interactions between services on the Web, Representational State Transfer (REST) is one of the primary architectural styles employed by web services today. Ideally, the RESTful interactions between participants should implement the interactions defined at the business choreography level. The problem, however, is the conceptual gap between the business process choreography diagrams and RESTful interactions. Choreography diagrams, on the one hand, are modeled from business domain experts with the purpose of capturing, communicating and, ideally, driving the business interactions. RESTful interactions, on the other hand, depend on RESTful interfaces that are designed by web engineers with the purpose of facilitating the interaction between participants on the internet. In most cases however, business domain experts are unaware of the technology behind web service interfaces and web engineers tend to overlook the overall business goals of web services. While there is considerable work on using process models during process implementation, there is little work on using choreography models to implement interactions between business processes. This thesis addresses this research gap by raising the following research question: How to close the conceptual gap between business process choreographies and RESTful interactions? This thesis offers several research contributions that jointly answer the research question. The main research contribution is the design of a language that captures RESTful interactions between participants---RESTful choreography modeling language. Formal completeness properties (with respect to REST) are introduced to validate its instances, called RESTful choreographies. A systematic semi-automatic method for deriving RESTful choreographies from business process choreographies is proposed. The method employs natural language processing techniques to translate business interactions into RESTful interactions. The effectiveness of the approach is shown by developing a prototypical tool that evaluates the derivation method over a large number of choreography models. In addition, the thesis proposes solutions towards implementing RESTful choreographies. In particular, two RESTful service specifications are introduced for aiding, respectively, the execution of choreographies' exclusive gateways and the guidance of RESTful interactions.},
  language  = {en}
}
@phdthesis{Niephaus2022,
  author    = {Niephaus, Fabio},
  title     = {Exploratory tool-building platforms for polyglot virtual machines},
  doi       = {10.25932/publishup-57177},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-571776},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxi, 249},
  year      = {2022},
  abstract  = {Polyglot programming allows developers to use multiple programming languages within the same software project. While it is common to use more than one language in certain programming domains, developers also apply polyglot programming for other purposes such as to re-use software written in other languages. Although established approaches to polyglot programming come with significant limitations, for example, in terms of performance and tool support, developers still use them to be able to combine languages. Polyglot virtual machines (VMs) such as GraalVM provide a new level of polyglot programming, allowing languages to directly interact with each other. This reduces the amount of glue code needed to combine languages, results in better performance, and enables tools such as debuggers to work across languages. However, only a little research has focused on novel tools that are designed to support developers in building software with polyglot VMs. One reason is that tool-building is often an expensive activity, another one is that polyglot VMs are still a moving target as their use cases and requirements are not yet well understood. In this thesis, we present an approach that builds on existing self-sustaining programming systems such as Squeak/Smalltalk to enable exploratory programming, a practice for exploring and gathering software requirements, and re-use their extensive tool-building capabilities in the context of polyglot VMs. Based on TruffleSqueak, our implementation for the GraalVM, we further present five case studies that demonstrate how our approach helps tool developers to design and build tools for polyglot programming. We further show that TruffleSqueak can also be used by application developers to build and evolve polyglot applications at run-time and by language and runtime developers to understand the dynamic behavior of GraalVM languages and internals. Since our platform allows all these developers to apply polyglot programming, it can further help to better understand the advantages, use cases, requirements, and challenges of polyglot VMs. Moreover, we demonstrate that our approach can also be applied to other polyglot VMs and that insights gained through it are transferable to other programming systems. We conclude that our research on tools for polyglot programming is an important step toward making polyglot VMs more approachable for developers in practice. With good tool support, we believe polyglot VMs can make it much more common for developers to take advantage of multiple languages and their ecosystems when building software.},
  language  = {en}
}
@phdthesis{Najafi2023,
  author    = {Najafi, Pejman},
  title     = {Leveraging data science \& engineering for advanced security operations},
  doi       = {10.25932/publishup-61225},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-612257},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 180},
  year      = {2023},
  abstract  = {The Security Operations Center (SOC) represents a specialized unit responsible for managing security within enterprises. To aid in its responsibilities, the SOC relies heavily on a Security Information and Event Management (SIEM) system that functions as a centralized repository for all security-related data, providing a comprehensive view of the organization's security posture. Due to the ability to offer such insights, SIEMS are considered indispensable tools facilitating SOC functions, such as monitoring, threat detection, and incident response. Despite advancements in big data architectures and analytics, most SIEMs fall short of keeping pace. Architecturally, they function merely as log search engines, lacking the support for distributed large-scale analytics. Analytically, they rely on rule-based correlation, neglecting the adoption of more advanced data science and machine learning techniques. This thesis first proposes a blueprint for next-generation SIEM systems that emphasize distributed processing and multi-layered storage to enable data mining at a big data scale. Next, with the architectural support, it introduces two data mining approaches for advanced threat detection as part of SOC operations. First, a novel graph mining technique that formulates threat detection within the SIEM system as a large-scale graph mining and inference problem, built on the principles of guilt-by-association and exempt-by-reputation. The approach entails the construction of a Heterogeneous Information Network (HIN) that models shared characteristics and associations among entities extracted from SIEM-related events/logs. Thereon, a novel graph-based inference algorithm is used to infer a node's maliciousness score based on its associations with other entities in the HIN. Second, an innovative outlier detection technique that imitates a SOC analyst's reasoning process to find anomalies/outliers. The approach emphasizes explainability and simplicity, achieved by combining the output of simple context-aware univariate submodels that calculate an outlier score for each entry. Both approaches were tested in academic and real-world settings, demonstrating high performance when compared to other algorithms as well as practicality alongside a large enterprise's SIEM system. This thesis establishes the foundation for next-generation SIEM systems that can enhance today's SOCs and facilitate the transition from human-centric to data-driven security operations.},
  language  = {en}
}
@phdthesis{Meinig2019,
  author    = {Meinig, Michael},
  title     = {Bedrohungsanalyse f{\"u}r milit{\"a}rische Informationstechnik},
  doi       = {10.25932/publishup-44160},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441608},
  school      = {Universit{\"a}t Potsdam},
  pages     = {X, 137},
  year      = {2019},
  abstract  = {Risiken f{\"u}r Cyberressourcen k{\"o}nnen durch unbeabsichtigte oder absichtliche Bedrohungen entstehen. Dazu geh{\"o}ren Insider-Bedrohungen von unzufriedenen oder nachl{\"a}ssigen Mitarbeitern und Partnern, eskalierende und aufkommende Bedrohungen aus aller Welt, die stetige Weiterentwicklung der Angriffstechnologien und die Entstehung neuer und zerst{\"o}rerischer Angriffe. Informationstechnik spielt mittlerweile in allen Bereichen des Lebens eine entscheidende Rolle, u. a. auch im Bereich des Milit{\"a}rs. Ein ineffektiver Schutz von Cyberressourcen kann hier Sicherheitsvorf{\"a}lle und Cyberattacken erleichtern, welche die kritischen Vorg{\"a}nge st{\"o}ren, zu unangemessenem Zugriff, Offenlegung, {\"A}nderung oder Zerst{\"o}rung sensibler Informationen f{\"u}hren und somit die nationale Sicherheit, das wirtschaftliche Wohlergehen sowie die {\"o}ffentliche Gesundheit und Sicherheit gef{\"a}hrden. Oftmals ist allerdings nicht klar, welche Bedrohungen konkret vorhanden sind und welche der kritischen Systemressourcen besonders gef{\"a}hrdet ist. In dieser Dissertation werden verschiedene Analyseverfahren f{\"u}r Bedrohungen in milit{\"a}rischer Informationstechnik vorgeschlagen und in realen Umgebungen getestet. Dies bezieht sich auf Infrastrukturen, IT-Systeme, Netze und Anwendungen, welche Verschlusssachen (VS)/Staatsgeheimnisse verarbeiten, wie zum Beispiel bei milit{\"a}rischen oder Regierungsorganisationen. Die Besonderheit an diesen Organisationen ist das Konzept der Informationsr{\"a}ume, in denen verschiedene Datenelemente, wie z. B. Papierdokumente und Computerdateien, entsprechend ihrer Sicherheitsempfindlichkeit eingestuft werden, z. B. „STRENG GEHEIM", „GEHEIM", „VS-VERTRAULICH", „VS-NUR-F{\"U}R-DEN-DIENSTGEBRAUCH" oder „OFFEN". Die Besonderheit dieser Arbeit ist der Zugang zu eingestuften Informationen aus verschiedenen Informationsr{\"a}umen und der Prozess der Freigabe dieser. Jede in der Arbeit entstandene Ver{\"o}ffentlichung wurde mit Angeh{\"o}rigen in der Organisation besprochen, gegengelesen und freigegeben, so dass keine eingestuften Informationen an die {\"O}ffentlichkeit gelangen. Die Dissertation beschreibt zun{\"a}chst Bedrohungsklassifikationsschemen und Angreiferstrategien, um daraus ein ganzheitliches, strategiebasiertes Bedrohungsmodell f{\"u}r Organisationen abzuleiten. Im weiteren Verlauf wird die Erstellung und Analyse eines Sicherheitsdatenflussdiagramms definiert, welches genutzt wird, um in eingestuften Informationsr{\"a}umen operationelle Netzknoten zu identifizieren, die aufgrund der Bedrohungen besonders gef{\"a}hrdet sind. Die spezielle, neuartige Darstellung erm{\"o}glicht es, erlaubte und verbotene Informationsfl{\"u}sse innerhalb und zwischen diesen Informationsr{\"a}umen zu verstehen. Aufbauend auf der Bedrohungsanalyse werden im weiteren Verlauf die Nachrichtenfl{\"u}sse der operationellen Netzknoten auf Verst{\"o}ße gegen Sicherheitsrichtlinien analysiert und die Ergebnisse mit Hilfe des Sicherheitsdatenflussdiagramms anonymisiert dargestellt. Durch Anonymisierung der Sicherheitsdatenflussdiagramme ist ein Austausch mit externen Experten zur Diskussion von Sicherheitsproblematiken m{\"o}glich. Der dritte Teil der Arbeit zeigt, wie umfangreiche Protokolldaten der Nachrichtenfl{\"u}sse dahingehend untersucht werden k{\"o}nnen, ob eine Reduzierung der Menge an Daten m{\"o}glich ist. Dazu wird die Theorie der groben Mengen aus der Unsicherheitstheorie genutzt. Dieser Ansatz wird in einer Fallstudie, auch unter Ber{\"u}cksichtigung von m{\"o}glichen auftretenden Anomalien getestet und ermittelt, welche Attribute in Protokolldaten am ehesten redundant sind.},
  language  = {de}
}
@phdthesis{Marx2024,
  author    = {Marx, Carolin Valerie},
  title     = {Escalation of commitment in information systems projects: a cognitive-affective perspective},
  doi       = {10.25932/publishup-62696},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-626969},
  school      = {Universit{\"a}t Potsdam},
  pages     = {174},
  year      = {2024},
  abstract  = {While information systems (IS) projects are pivotal in guiding organizational strategies and sustaining competitive advantages, they frequently overrun budgets, extend beyond timelines, and experience high failure rates. This dissertation delves into the psychological micro-foundations of human behavior - specifically cognition and emotion - in relation to a prevalent issue in IS project management: the tendency to persist with failing courses of action, also called escalation of commitment (EoC). Through a mixed-methods research approach, this study investigates the emotional and cognitive bases of decision-making during IS project escalation and its evolution over time. The results of a psychophysiological laboratory experiment provide evidence for the predictions on the role of negative and complex situational integral emotions of Cognitive Dissonance over Coping Theory and add to a better understanding of how escalation tendencies change during sequential decision-making due to cognitive learning effects. Using psychophysiological measures, including data triangulation between electrodermal and cardiovascular activity and AI-based analysis of facial micro-expressions, this research reveals physiological markers of behavioral escalation tendencies. Complementing the experiment, a qualitative analysis using free-form narration during decision-making simulations shows that decision-makers employ varied cognitive reasoning patterns to justify escalating behaviors, suggesting a sequence of four distinct cognitive phases. By integrating both qualitative and quantitative findings, this dissertation offers a comprehensive theoretical framework of how cognition and emotion shape behavioral EoC over time. I propose that escalation is a cyclical adaptation of mental models, distinguished by shifts in cognitive reasoning patterns, temporal cognition mode variations, and interactions with situational emotions and their anticipation. The primary contribution of this dissertation lies in disentangling the emotional and cognitive mechanisms that drive IS project escalation. The findings provide the basis for developing de-escalation strategies, thereby helping to improve decision-making under uncertainty. Stakeholders involved in IS projects that get "off track" should be aware of the tendency to persist with failing courses of action and the importance of the underlying emotional and cognitive dynamics.},
  language  = {de}
}
@phdthesis{Marwecki2021,
  author    = {Marwecki, Sebastian},
  title     = {Virtualizing physical space},
  doi       = {10.25932/publishup-52033},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-520332},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 128},
  year      = {2021},
  abstract  = {The true cost for virtual reality is not the hardware, but the physical space it requires, as a one-to-one mapping of physical space to virtual space allows for the most immersive way of navigating in virtual reality. Such "real-walking" requires physical space to be of the same size and the same shape of the virtual world represented. This generally prevents real-walking applications from running on any space that they were not designed for. To reduce virtual reality's demand for physical space, creators of such applications let users navigate virtual space by means of a treadmill, altered mappings of physical to virtual space, hand-held controllers, or gesture-based techniques. While all of these solutions succeed at reducing virtual reality's demand for physical space, none of them reach the same level of immersion that real-walking provides. Our approach is to virtualize physical space: instead of accessing physical space directly, we allow applications to express their need for space in an abstract way, which our software systems then map to the physical space available. We allow real-walking applications to run in spaces of different size, different shape, and in spaces containing different physical objects. We also allow users immersed in different virtual environments to share the same space. Our systems achieve this by using a tracking volume-independent representation of real-walking experiences — a graph structure that expresses the spatial and logical relationships between virtual locations, virtual elements contained within those locations, and user interactions with those elements. When run in a specific physical space, this graph representation is used to define a custom mapping of the elements of the virtual reality application and the physical space by parsing the graph using a constraint solver. To re-use space, our system splits virtual scenes and overlap virtual geometry. The system derives this split by means of hierarchically clustering of our virtual objects as nodes of our bi-partite directed graph that represents the logical ordering of events of the experience. We let applications express their demands for physical space and use pre-emptive scheduling between applications to have them share space. We present several application examples enabled by our system. They all enable real-walking, despite being mapped to physical spaces of different size and shape, containing different physical objects or other users. We see substantial real-world impact in our systems. Today's commercial virtual reality applications are generally designing to be navigated using less immersive solutions, as this allows them to be operated on any tracking volume. While this is a commercial necessity for the developers, it misses out on the higher immersion offered by real-walking. We let developers overcome this hurdle by allowing experiences to bring real-walking to any tracking volume, thus potentially bringing real-walking to consumers. Die eigentlichen Kosten f{\"u}r Virtual Reality Anwendungen entstehen nicht prim{\"a}r durch die erforderliche Hardware, sondern durch die Nutzung von physischem Raum, da die eins-zu-eins Abbildung von physischem auf virtuellem Raum die immersivste Art von Navigation erm{\"o}glicht. Dieses als „Real-Walking" bezeichnete Erlebnis erfordert hinsichtlich Gr{\"o}ße und Form eine Entsprechung von physischem Raum und virtueller Welt. Resultierend daraus k{\"o}nnen Real-Walking-Anwendungen nicht an Orten angewandt werden, f{\"u}r die sie nicht entwickelt wurden. Um den Bedarf an physischem Raum zu reduzieren, lassen Entwickler von Virtual Reality-Anwendungen ihre Nutzer auf verschiedene Arten navigieren, etwa mit Hilfe eines Laufbandes, verf{\"a}lschten Abbildungen von physischem zu virtuellem Raum, Handheld-Controllern oder gestenbasierten Techniken. All diese L{\"o}sungen reduzieren zwar den Bedarf an physischem Raum, erreichen jedoch nicht denselben Grad an Immersion, den Real-Walking bietet. Unser Ansatz zielt darauf, physischen Raum zu virtualisieren: Anstatt auf den physischen Raum direkt zuzugreifen, lassen wir Anwendungen ihren Raumbedarf auf abstrakte Weise formulieren, den unsere Softwaresysteme anschließend auf den verf{\"u}gbaren physischen Raum abbilden. Dadurch erm{\"o}glichen wir Real-Walking-Anwendungen R{\"a}ume mit unterschiedlichen Gr{\"o}ßen und Formen und R{\"a}ume, die unterschiedliche physische Objekte enthalten, zu nutzen. Wir erm{\"o}glichen auch die zeitgleiche Nutzung desselben Raums durch mehrere Nutzer verschiedener Real-Walking-Anwendungen. Unsere Systeme erreichen dieses Resultat durch eine Repr{\"a}sentation von Real-Walking-Erfahrungen, die unabh{\"a}ngig sind vom gegebenen Trackingvolumen - eine Graphenstruktur, die die r{\"a}umlichen und logischen Beziehungen zwischen virtuellen Orten, den virtuellen Elementen innerhalb dieser Orte, und Benutzerinteraktionen mit diesen Elementen, ausdr{\"u}ckt. Bei der Instanziierung der Anwendung in einem bestimmten physischen Raum wird diese Graphenstruktur und ein Constraint Solver verwendet, um eine individuelle Abbildung der virtuellen Elemente auf den physischen Raum zu erreichen. Zur mehrmaligen Verwendung des Raumes teilt unser System virtuelle Szenen und {\"u}berlagert virtuelle Geometrie. Das System leitet diese Aufteilung anhand eines hierarchischen Clusterings unserer virtuellen Objekte ab, die als Knoten unseres bi-partiten, gerichteten Graphen die logische Reihenfolge aller Ereignisse repr{\"a}sentieren. Wir verwenden pr{\"a}emptives Scheduling zwischen den Anwendungen f{\"u}r die zeitgleiche Nutzung von physischem Raum. Wir stellen mehrere Anwendungsbeispiele vor, die Real-Walking erm{\"o}glichen - in physischen R{\"a}umen mit unterschiedlicher Gr{\"o}ße und Form, die verschiedene physische Objekte oder weitere Nutzer enthalten. Wir sehen in unseren Systemen substantielles Potential. Heutige Virtual Reality-Anwendungen sind bisher zwar so konzipiert, dass sie auf einem beliebigen Trackingvolumen betrieben werden k{\"o}nnen, aber aus kommerzieller Notwendigkeit kein Real-Walking beinhalten. Damit entgeht Entwicklern die Gelegenheit eine h{\"o}here Immersion herzustellen. Indem wir es erm{\"o}glichen, Real-Walking auf jedes Trackingvolumen zu bringen, geben wir Entwicklern die M{\"o}glichkeit Real-Walking zu ihren Nutzern zu bringen.},
  language  = {en}
}
@phdthesis{Mandal2019,
  author    = {Mandal, Sankalita},
  title     = {Event handling in business processes},
  doi       = {10.25932/publishup-44170},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441700},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 151},
  year      = {2019},
  abstract  = {Business process management (BPM) deals with modeling, executing, monitoring, analyzing, and improving business processes. During execution, the process communicates with its environment to get relevant contextual information represented as events. Recent development of big data and the Internet of Things (IoT) enables sources like smart devices and sensors to generate tons of events which can be filtered, grouped, and composed to trigger and drive business processes. The industry standard Business Process Model and Notation (BPMN) provides several event constructs to capture the interaction possibilities between a process and its environment, e.g., to instantiate a process, to abort an ongoing activity in an exceptional situation, to take decisions based on the information carried by the events, as well as to choose among the alternative paths for further process execution. The specifications of such interactions are termed as event handling. However, in a distributed setup, the event sources are most often unaware of the status of process execution and therefore, an event is produced irrespective of the process being ready to consume it. BPMN semantics does not support such scenarios and thus increases the chance of processes getting delayed or getting in a deadlock by missing out on event occurrences which might still be relevant. The work in this thesis reviews the challenges and shortcomings of integrating real-world events into business processes, especially the subscription management. The basic integration is achieved with an architecture consisting of a process modeler, a process engine, and an event processing platform. Further, points of subscription and unsubscription along the process execution timeline are defined for different BPMN event constructs. Semantic and temporal dependencies among event subscription, event occurrence, event consumption and event unsubscription are considered. To this end, an event buffer with policies for updating the buffer, retrieving the most suitable event for the current process instance, and reusing the event has been discussed that supports issuing of early subscription. The Petri net mapping of the event handling model provides our approach with a translation of semantics from a business process perspective. Two applications based on this formal foundation are presented to support the significance of different event handling configurations on correct process execution and reachability of a process path. Prototype implementations of the approaches show that realizing flexible event handling is feasible with minor extensions of off-the-shelf process engines and event platforms.},
  language  = {en}
}
@phdthesis{Loster2021,
  author    = {Loster, Michael},
  title     = {Knowledge base construction with machine learning methods},
  doi       = {10.25932/publishup-50145},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-501459},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 130},
  year      = {2021},
  abstract  = {Modern knowledge bases contain and organize knowledge from many different topic areas. Apart from specific entity information, they also store information about their relationships amongst each other. Combining this information results in a knowledge graph that can be particularly helpful in cases where relationships are of central importance. Among other applications, modern risk assessment in the financial sector can benefit from the inherent network structure of such knowledge graphs by assessing the consequences and risks of certain events, such as corporate insolvencies or fraudulent behavior, based on the underlying network structure. As public knowledge bases often do not contain the necessary information for the analysis of such scenarios, the need arises to create and maintain dedicated domain-specific knowledge bases. This thesis investigates the process of creating domain-specific knowledge bases from structured and unstructured data sources. In particular, it addresses the topics of named entity recognition (NER), duplicate detection, and knowledge validation, which represent essential steps in the construction of knowledge bases. As such, we present a novel method for duplicate detection based on a Siamese neural network that is able to learn a dataset-specific similarity measure which is used to identify duplicates. Using the specialized network architecture, we design and implement a knowledge transfer between two deduplication networks, which leads to significant performance improvements and a reduction of required training data. Furthermore, we propose a named entity recognition approach that is able to identify company names by integrating external knowledge in the form of dictionaries into the training process of a conditional random field classifier. In this context, we study the effects of different dictionaries on the performance of the NER classifier. We show that both the inclusion of domain knowledge as well as the generation and use of alias names results in significant performance improvements. For the validation of knowledge represented in a knowledge base, we introduce Colt, a framework for knowledge validation based on the interactive quality assessment of logical rules. In its most expressive implementation, we combine Gaussian processes with neural networks to create Colt-GP, an interactive algorithm for learning rule models. Unlike other approaches, Colt-GP uses knowledge graph embeddings and user feedback to cope with data quality issues of knowledge bases. The learned rule model can be used to conditionally apply a rule and assess its quality. Finally, we present CurEx, a prototypical system for building domain-specific knowledge bases from structured and unstructured data sources. Its modular design is based on scalable technologies, which, in addition to processing large datasets, ensures that the modules can be easily exchanged or extended. CurEx offers multiple user interfaces, each tailored to the individual needs of a specific user group and is fully compatible with the Colt framework, which can be used as part of the system. We conduct a wide range of experiments with different datasets to determine the strengths and weaknesses of the proposed methods. To ensure the validity of our results, we compare the proposed methods with competing approaches.},
  language  = {en}
}
@phdthesis{Lorson2024,
  author    = {Lorson, Annalena},
  title     = {Understanding early stage evolution of digital innovation units in manufacturing companies},
  doi       = {10.25932/publishup-63914},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-639141},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XI, 149},
  year      = {2024},
  abstract  = {The dynamic landscape of digital transformation entails an impact on industrial-age manufacturing companies that goes beyond product offerings, changing operational paradigms, and requiring an organization-wide metamorphosis. An initiative to address the given challenges is the creation of Digital Innovation Units (DIUs) - departments or distinct legal entities that use new structures and practices to develop digital products, services, and business models and support or drive incumbents' digital transformation. With more than 300 units in German-speaking countries alone and an increasing number of scientific publications, DIUs have become a widespread phenomenon in both research and practice. This dissertation examines the evolution process of DIUs in the manufacturing industry during their first three years of operation, through an extensive longitudinal single-case study and several cross-case syntheses of seven DIUs. Building on the lenses of organizational change and development, time, and socio-technical systems, this research provides insights into the fundamentals, temporal dynamics, socio-technical interactions, and relational dynamics of a DIU's evolution process. Thus, the dissertation promotes a dynamic understanding of DIUs and adds a two-dimensional perspective to the often one-dimensional view of these units and their interactions with the main organization throughout the startup and growth phases of a DIU. Furthermore, the dissertation constructs a phase model that depicts the early stages of DIU evolution based on these findings and by incorporating literature from information systems research. As a result, it illustrates the progressive intensification of collaboration between the DIU and the main organization. After being implemented, the DIU sparks initial collaboration and instigates change within (parts of) the main organization. Over time, it adapts to the corporate environment to some extent, responding to changing circumstances in order to contribute to long-term transformation. Temporally, the DIU drives the early phases of cooperation and adaptation in particular, while the main organization triggers the first major evolutionary step and realignment of the DIU. Overall, the thesis identifies DIUs as malleable organizational structures that are crucial for digital transformation. Moreover, it provides guidance for practitioners on the process of building a new DIU from scratch or optimizing an existing one.},
  language  = {en}
}
@phdthesis{Lopes2018,
  author    = {Lopes, Pedro},
  title     = {Interactive Systems Based on Electrical Muscle Stimulation},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-421165},
  school      = {Universit{\"a}t Potsdam},
  pages     = {171},
  year      = {2018},
  abstract  = {How can interactive devices connect with users in the most immediate and intimate way? This question has driven interactive computing for decades. Throughout the last decades, we witnessed how mobile devices moved computing into users' pockets, and recently, wearables put computing in constant physical contact with the user's skin. In both cases moving the devices closer to users allowed devices to sense more of the user, and thus act more personal. The main question that drives our research is: what is the next logical step? Some researchers argue that the next generation of interactive devices will move past the user's skin and be directly implanted inside the user's body. This has already happened in that we have pacemakers, insulin pumps, etc. However, we argue that what we see is not devices moving towards the inside of the user's body, but rather towards the body's biological "interface" they need to address in order to perform their function. To implement our vision, we created a set of devices that intentionally borrow parts of the user's body for input and output, rather than adding more technology to the body. In this dissertation we present one specific flavor of such devices, i.e., devices that borrow the user's muscles. We engineered I/O devices that interact with the user by reading and controlling muscle activity. To achieve the latter, our devices are based on medical-grade signal generators and electrodes attached to the user's skin that send electrical impulses to the user's muscles; these impulses then cause the user's muscles to contract. While electrical muscle stimulation (EMS) devices have been used to regenerate lost motor functions in rehabilitation medicine since the 1960s, in this dissertation, we propose a new perspective: EMS as a means for creating interactive systems. We start by presenting seven prototypes of interactive devices that we have created to illustrate several benefits of EMS. These devices form two main categories: (1) Devices that allow users eyes-free access to information by means of their proprioceptive sense, such as the value of a variable in a computer system, a tool, or a plot; (2) Devices that increase immersion in virtual reality by simulating large forces, such as wind, physical impact, or walls and heavy objects. Then, we analyze the potential of EMS to build interactive systems that miniaturize well and discuss how they leverage our proprioceptive sense as an I/O modality. We proceed by laying out the benefits and disadvantages of both EMS and mechanical haptic devices, such as exoskeletons. We conclude by sketching an outline for future research on EMS by listing open technical, ethical and philosophical questions that we left unanswered.},
  language  = {en}
}
@phdthesis{Lindinger2023,
  author    = {Lindinger, Jakob},
  title     = {Variational inference for composite Gaussian process models},
  doi       = {10.25932/publishup-60444},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604441},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 122},
  year      = {2023},
  abstract  = {Most machine learning methods provide only point estimates when being queried to predict on new data. This is problematic when the data is corrupted by noise, e.g. from imperfect measurements, or when the queried data point is very different to the data that the machine learning model has been trained with. Probabilistic modelling in machine learning naturally equips predictions with corresponding uncertainty estimates which allows a practitioner to incorporate information about measurement noise into the modelling process and to know when not to trust the predictions. A well-understood, flexible probabilistic framework is provided by Gaussian processes that are ideal as building blocks of probabilistic models. They lend themself naturally to the problem of regression, i.e., being given a set of inputs and corresponding observations and then predicting likely observations for new unseen inputs, and can also be adapted to many more machine learning tasks. However, exactly inferring the optimal parameters of such a Gaussian process model (in a computationally tractable manner) is only possible for regression tasks in small data regimes. Otherwise, approximate inference methods are needed, the most prominent of which is variational inference. In this dissertation we study models that are composed of Gaussian processes embedded in other models in order to make those more flexible and/or probabilistic. The first example are deep Gaussian processes which can be thought of as a small network of Gaussian processes and which can be employed for flexible regression. The second model class that we study are Gaussian process state-space models. These can be used for time-series modelling, i.e., the task of being given a stream of data ordered by time and then predicting future observations. For both model classes the state-of-the-art approaches offer a trade-off between expressive models and computational properties (e.g. speed or convergence properties) and mostly employ variational inference. Our goal is to improve inference in both models by first getting a deep understanding of the existing methods and then, based on this, to design better inference methods. We achieve this by either exploring the existing trade-offs or by providing general improvements applicable to multiple methods. We first provide an extensive background, introducing Gaussian processes and their sparse (approximate and efficient) variants. We continue with a description of the models under consideration in this thesis, deep Gaussian processes and Gaussian process state-space models, including detailed derivations and a theoretical comparison of existing methods. Then we start analysing deep Gaussian processes more closely: Trading off the properties (good optimisation versus expressivity) of state-of-the-art methods in this field, we propose a new variational inference based approach. We then demonstrate experimentally that our new algorithm leads to better calibrated uncertainty estimates than existing methods. Next, we turn our attention to Gaussian process state-space models, where we closely analyse the theoretical properties of existing methods.The understanding gained in this process leads us to propose a new inference scheme for general Gaussian process state-space models that incorporates effects on multiple time scales. This method is more efficient than previous approaches for long timeseries and outperforms its comparison partners on data sets in which effects on multiple time scales (fast and slowly varying dynamics) are present. Finally, we propose a new inference approach for Gaussian process state-space models that trades off the properties of state-of-the-art methods in this field. By combining variational inference with another approximate inference method, the Laplace approximation, we design an efficient algorithm that outperforms its comparison partners since it achieves better calibrated uncertainties.},
  language  = {en}
}
@phdthesis{Limberger2024,
  author    = {Limberger, Daniel},
  title     = {Concepts and techniques for 3D-embedded treemaps and their application to software visualization},
  doi       = {10.25932/publishup-63201},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-632014},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 118},
  year      = {2024},
  abstract  = {This thesis addresses concepts and techniques for interactive visualization of hierarchical data using treemaps. It explores (1) how treemaps can be embedded in 3D space to improve their information content and expressiveness, (2) how the readability of treemaps can be improved using level-of-detail and degree-of-interest techniques, and (3) how to design and implement a software framework for the real-time web-based rendering of treemaps embedded in 3D. With a particular emphasis on their application, use cases from software analytics are taken to test and evaluate the presented concepts and techniques. Concerning the first challenge, this thesis shows that a 3D attribute space offers enhanced possibilities for the visual mapping of data compared to classical 2D treemaps. In particular, embedding in 3D allows for improved implementation of visual variables (e.g., by sketchiness and color weaving), provision of new visual variables (e.g., by physically based materials and in situ templates), and integration of visual metaphors (e.g., by reference surfaces and renderings of natural phenomena) into the three-dimensional representation of treemaps. For the second challenge—the readability of an information visualization—the work shows that the generally higher visual clutter and increased cognitive load typically associated with three-dimensional information representations can be kept low in treemap-based representations of both small and large hierarchical datasets. By introducing an adaptive level-of-detail technique, we cannot only declutter the visualization results, thereby reducing cognitive load and mitigating occlusion problems, but also summarize and highlight relevant data. Furthermore, this approach facilitates automatic labeling, supports the emphasis on data outliers, and allows visual variables to be adjusted via degree-of-interest measures. The third challenge is addressed by developing a real-time rendering framework with WebGL and accumulative multi-frame rendering. The framework removes hardware constraints and graphics API requirements, reduces interaction response times, and simplifies high-quality rendering. At the same time, the implementation effort for a web-based deployment of treemaps is kept reasonable. The presented visualization concepts and techniques are applied and evaluated for use cases in software analysis. In this domain, data about software systems, especially about the state and evolution of the source code, does not have a descriptive appearance or natural geometric mapping, making information visualization a key technology here. In particular, software source code can be visualized with treemap-based approaches because of its inherently hierarchical structure. With treemaps embedded in 3D, we can create interactive software maps that visually map, software metrics, software developer activities, or information about the evolution of software systems alongside their hierarchical module structure. Discussions on remaining challenges and opportunities for future research for 3D-embedded treemaps and their applications conclude the thesis.},
  language  = {en}
}
@phdthesis{Lazaridou2021,
  author    = {Lazaridou, Konstantina},
  title     = {Revealing hidden patterns in political news and social media with machine learning},
  doi       = {10.25932/publishup-50273},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-502734},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 140},
  year      = {2021},
  abstract  = {As part of our everyday life we consume breaking news and interpret it based on our own viewpoints and beliefs. We have easy access to online social networking platforms and news media websites, where we inform ourselves about current affairs and often post about our own views, such as in news comments or social media posts. The media ecosystem enables opinions and facts to travel from news sources to news readers, from news article commenters to other readers, from social network users to their followers, etc. The views of the world many of us have depend on the information we receive via online news and social media. Hence, it is essential to maintain accurate, reliable and objective online content to ensure democracy and verity on the Web. To this end, we contribute to a trustworthy media ecosystem by analyzing news and social media in the context of politics to ensure that media serves the public interest. In this thesis, we use text mining, natural language processing and machine learning techniques to reveal underlying patterns in political news articles and political discourse in social networks. Mainstream news sources typically cover a great amount of the same news stories every day, but they often place them in a different context or report them from different perspectives. In this thesis, we are interested in how distinct and predictable newspaper journalists are, in the way they report the news, as a means to understand and identify their different political beliefs. To this end, we propose two models that classify text from news articles to their respective original news source, i.e., reported speech and also news comments. Our goal is to capture systematic quoting and commenting patterns by journalists and news commenters respectively, which can lead us to the newspaper where the quotes and comments are originally published. Predicting news sources can help us understand the potential subjective nature behind news storytelling and the magnitude of this phenomenon. Revealing this hidden knowledge can restore our trust in media by advancing transparency and diversity in the news. Media bias can be expressed in various subtle ways in the text and it is often challenging to identify these bias manifestations correctly, even for humans. However, media experts, e.g., journalists, are a powerful resource that can help us overcome the vague definition of political media bias and they can also assist automatic learners to find the hidden bias in the text. Due to the enormous technological advances in artificial intelligence, we hypothesize that identifying political bias in the news could be achieved through the combination of sophisticated deep learning modelsxi and domain expertise. Therefore, our second contribution is a high-quality and reliable news dataset annotated by journalists for political bias and a state-of-the-art solution for this task based on curriculum learning. Our aim is to discover whether domain expertise is necessary for this task and to provide an automatic solution for this traditionally manually-solved problem. User generated content is fundamentally different from news articles, e.g., messages are shorter, they are often personal and opinionated, they refer to specific topics and persons, etc. Regarding political and socio-economic news, individuals in online communities make use of social networks to keep their peers up-to-date and to share their own views on ongoing affairs. We believe that social media is also an as powerful instrument for information flow as the news sources are, and we use its unique characteristic of rapid news coverage for two applications. We analyze Twitter messages and debate transcripts during live political presidential debates to automatically predict the topics that Twitter users discuss. Our goal is to discover the favoured topics in online communities on the dates of political events as a way to understand the political subjects of public interest. With the up-to-dateness of microblogs, an additional opportunity emerges, namely to use social media posts and leverage the real-time verity about discussed individuals to find their locations. That is, given a person of interest that is mentioned in online discussions, we use the wisdom of the crowd to automatically track her physical locations over time. We evaluate our approach in the context of politics, i.e., we predict the locations of US politicians as a proof of concept for important use cases, such as to track people that are national risks, e.g., warlords and wanted criminals.},
  language  = {en}
}