@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{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{Cheng2018,
  author    = {Cheng, Lung-Pan},
  title     = {Human actuation},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-418371},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 85},
  year      = {2018},
  abstract  = {Ever since the conception of the virtual reality headset in 1968, many researchers have argued that the next step in virtual reality is to allow users to not only see and hear, but also feel virtual worlds. One approach is to use mechanical equipment to provide haptic feedback, e.g., robotic arms, exoskeletons and motion platforms. However, the size and the weight of such mechanical equipment tends to be proportional to its target's size and weight, i.e., providing human-scale haptic feedback requires human-scale equipment, often restricting them to arcades and lab environments. The key idea behind this dissertation is to bypass mechanical equipment by instead leveraging human muscle power. We thus create software systems that orchestrate humans in doing such mechanical labor—this is what we call human actuation. A potential benefit of such systems is that humans are more generic, flexible, and versatile than machines. This brings a wide range of haptic feedback to modern virtual reality systems. We start with a proof-of-concept system—Haptic Turk, focusing on delivering motion experiences just like a motion platform. All Haptic Turk setups consist of a user who is supported by one or more human actuators. The user enjoys an interactive motion simulation such as a hang glider experience, but the motion is generated by those human actuators who manually lift, tilt, and push the user's limbs or torso. To get the timing and force right, timed motion instructions in a format familiar from rhythm games are generated by the system. Next, we extend the concept of human actuation from 3-DoF to 6-DoF virtual reality where users have the freedom to walk around. TurkDeck tackles this problem by orchestrating a group of human actuators to reconfigure a set of passive props on the fly while the user is progressing in the virtual environment. TurkDeck schedules human actuators by their distances from the user, and instructs them to reconfigure the props to the right place on the right time using laser projection and voice output. Our studies in Haptic Turk and TurkDeck showed that human actuators enjoyed the experience but not as much as users. To eliminate the need of dedicated human actuators, Mutual Turk makes everyone a user by exchanging mechanical actuation between two or more users. Mutual Turk's main functionality is that it orchestrates the users so as to actuate props at just the right moment and with just the right force to produce the correct feedback in each other's experience. Finally, we further eliminate the need of another user, making human actuation applicable to single-user experiences. iTurk makes the user constantly reconfigure and animate otherwise passive props. This allows iTurk to provide virtual worlds with constantly varying or even animated haptic effects, even though the only animate entity present in the system is the user. Our demo experience features one example each of iTurk's two main types of props, i.e., reconfigurable props (the foldable board from TurkDeck) and animated props (the pendulum). We conclude this dissertation by summarizing the findings of our explorations and pointing out future directions. We discuss the development of human actuation compare to traditional machine actuation, the possibility of combining human and machine actuators and interaction models that involve more human actuators.},
  language  = {en}
}
@phdthesis{Kruse2018,
  author    = {Kruse, Sebastian},
  title     = {Scalable data profiling},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412521},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 156},
  year      = {2018},
  abstract  = {Data profiling is the act of extracting structural metadata from datasets. Structural metadata, such as data dependencies and statistics, can support data management operations, such as data integration and data cleaning. Data management often is the most time-consuming activity in any data-related project. Its support is extremely valuable in our data-driven world, so that more time can be spent on the actual utilization of the data, e. g., building analytical models. In most scenarios, however, structural metadata is not given and must be extracted first. Therefore, efficient data profiling methods are highly desirable. Data profiling is a computationally expensive problem; in fact, most dependency discovery problems entail search spaces that grow exponentially in the number of attributes. To this end, this thesis introduces novel discovery algorithms for various types of data dependencies - namely inclusion dependencies, conditional inclusion dependencies, partial functional dependencies, and partial unique column combinations - that considerably improve over state-of-the-art algorithms in terms of efficiency and that scale to datasets that cannot be processed by existing algorithms. The key to those improvements are not only algorithmic innovations, such as novel pruning rules or traversal strategies, but also algorithm designs tailored for distributed execution. While distributed data profiling has been mostly neglected by previous works, it is a logical consequence on the face of recent hardware trends and the computational hardness of dependency discovery. To demonstrate the utility of data profiling for data management, this thesis furthermore presents Metacrate, a database for structural metadata. Its salient features are its flexible data model, the capability to integrate various kinds of structural metadata, and its rich metadata analytics library. We show how to perform a data anamnesis of unknown, complex datasets based on this technology. In particular, we describe in detail how to reconstruct the schemata and assess their quality as part of the data anamnesis. The data profiling algorithms and Metacrate have been carefully implemented, integrated with the Metanome data profiling tool, and are available as free software. In that way, we intend to allow for easy repeatability of our research results and also provide them for actual usage in real-world data-related projects.},
  language  = {en}
}
@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{Bazhenova2018,
  author    = {Bazhenova, Ekaterina},
  title     = {Discovery of Decision Models Complementary to Process Models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-410020},
  school      = {Universit{\"a}t Potsdam},
  year      = {2018},
  abstract  = {Business process management is an acknowledged asset for running an organization in a productive and sustainable way. One of the most important aspects of business process management, occurring on a daily basis at all levels, is decision making. In recent years, a number of decision management frameworks have appeared in addition to existing business process management systems. More recently, Decision Model and Notation (DMN) was developed by the OMG consortium with the aim of complementing the widely used Business Process Model and Notation (BPMN). One of the reasons for the emergence of DMN is the increasing interest in the evolving paradigm known as the separation of concerns. This paradigm states that modeling decisions complementary to processes reduces process complexity by externalizing decision logic from process models and importing it into a dedicated decision model. Such an approach increases the agility of model design and execution. This provides organizations with the flexibility to adapt to the ever increasing rapid and dynamic changes in the business ecosystem. The research gap, identified by us, is that the separation of concerns, recommended by DMN, prescribes the externalization of the decision logic of process models in one or more separate decision models, but it does not specify this can be achieved. The goal of this thesis is to overcome the presented gap by developing a framework for discovering decision models in a semi-automated way from information about existing process decision making. Thus, in this thesis we develop methodologies to extract decision models from: (1) control flow and data of process models that exist in enterprises; and (2) from event logs recorded by enterprise information systems, encapsulating day-to-day operations. Furthermore, we provide an extension of the methodologies to discover decision models from event logs enriched with fuzziness, a tool dealing with partial knowledge of the process execution information. All the proposed techniques are implemented and evaluated in case studies using real-life and synthetic process models and event logs. The evaluation of these case studies shows that the proposed methodologies provide valid and accurate output decision models that can serve as blueprints for executing decisions complementary to process models. Thus, these methodologies have applicability in the real world and they can be used, for example, for compliance checks, among other uses, which could improve the organization's decision making and hence it's overall performance.},
  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{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{Che2017,
  author    = {Che, Xiaoyin},
  title     = {E-lecture material enhancement based on automatic multimedia analysis},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-408224},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xviii, 148},
  year      = {2017},
  abstract  = {In this era of high-speed informatization and globalization, online education is no longer an exquisite concept in the ivory tower, but a rapidly developing industry closely relevant to people's daily lives. Numerous lectures are recorded in form of multimedia data, uploaded to the Internet and made publicly accessible from anywhere in this world. These lectures are generally addressed as e-lectures. In recent year, a new popular form of e-lectures, the Massive Open Online Courses (MOOCs), boosts the growth of online education industry and somehow turns "learning online" into a fashion. As an e-learning provider, besides to keep improving the quality of e-lecture content, to provide better learning environment for online learners is also a highly important task. This task can be preceded in various ways, and one of them is to enhance and upgrade the learning materials provided: e-lectures could be more than videos. Moreover, this process of enhancement or upgrading should be done automatically, without giving extra burdens to the lecturers or teaching teams, and this is the aim of this thesis. The first part of this thesis is an integrated framework of multi-lingual subtitles production, which can help online learners penetrate the language barrier. The framework consists of Automatic Speech Recognition (ASR), Sentence Boundary Detection (SBD) and Machine Translation (MT), among which the proposed SBD solution is major technical contribution, building on Deep Neural Network (DNN) and Word Vector (WV) and achieving state-of-the-art performance. Besides, a quantitative evaluation with dozens of volunteers is also introduced to measure how these auto-generated subtitles could actually help in context of e-lectures. Secondly, a technical solution "TOG" (Tree-Structure Outline Generation) is proposed to extract textual content from the displaying slides recorded in video and re-organize them into a hierarchical lecture outline, which may serve in multiple functions, such like preview, navigation and retrieval. TOG runs adaptively and can be roughly divided into intra-slide and inter-slides phases. Table detection and lecture video segmentation can be implemented as sub- or post-application in these two phases respectively. Evaluation on diverse e-lectures shows that all the outlines, tables and segments achieved are trustworthily accurate. Based on the subtitles and outlines previously created, lecture videos can be further split into sentence units and slide-based segment units. A lecture highlighting process is further applied on these units, in order to capture and mark the most important parts within the corresponding lecture, just as what people do with a pen when reading paper books. Sentence-level highlighting depends on the acoustic analysis on the audio track, while segment-level highlighting focuses on exploring clues from the statistical information of related transcripts and slide content. Both objective and subjective evaluations prove that the proposed lecture highlighting solution is with decent precision and welcomed by users. All above enhanced e-lecture materials have been already implemented in actual use or made available for implementation by convenient interfaces.},
  language  = {en}
}