@phdthesis{Harmouch2020,
  author    = {Harmouch, Hazar},
  title     = {Single-column data profiling},
  doi       = {10.25932/publishup-47455},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-474554},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 115},
  year      = {2020},
  abstract  = {The research area of data profiling consists of a large set of methods and processes to examine a given dataset and determine metadata about it. Typically, different data profiling tasks address different kinds of metadata, comprising either various statistics about individual columns (Single-column Analysis) or relationships among them (Dependency Discovery). Among the basic statistics about a column are data type, header, the number of unique values (the column's cardinality), maximum and minimum values, the number of null values, and the value distribution. Dependencies involve, for instance, functional dependencies (FDs), inclusion dependencies (INDs), and their approximate versions. Data profiling has a wide range of conventional use cases, namely data exploration, cleansing, and integration. The produced metadata is also useful for database management and schema reverse engineering. Data profiling has also more novel use cases, such as big data analytics. The generated metadata describes the structure of the data at hand, how to import it, what it is about, and how much of it there is. Thus, data profiling can be considered as an important preparatory task for many data analysis and mining scenarios to assess which data might be useful and to reveal and understand a new dataset's characteristics. In this thesis, the main focus is on the single-column analysis class of data profiling tasks. We study the impact and the extraction of three of the most important metadata about a column, namely the cardinality, the header, and the number of null values. First, we present a detailed experimental study of twelve cardinality estimation algorithms. We classify the algorithms and analyze their efficiency, scaling far beyond the original experiments and testing theoretical guarantees. Our results highlight their trade-offs and point out the possibility to create a parallel or a distributed version of these algorithms to cope with the growing size of modern datasets. Then, we present a fully automated, multi-phase system to discover human-understandable, representative, and consistent headers for a target table in cases where headers are missing, meaningless, or unrepresentative for the column values. Our evaluation on Wikipedia tables shows that 60\% of the automatically discovered schemata are exact and complete. Considering more schema candidates, top-5 for example, increases this percentage to 72\%. Finally, we formally and experimentally show the ghost and fake FDs phenomenon caused by FD discovery over datasets with missing values. We propose two efficient scores, probabilistic and likelihood-based, for estimating the genuineness of a discovered FD. Our extensive set of experiments on real-world and semi-synthetic datasets show the effectiveness and efficiency of these scores.},
  language  = {en}
}
@phdthesis{Koumarelas2020,
  author    = {Koumarelas, Ioannis},
  title     = {Data preparation and domain-agnostic duplicate detection},
  doi       = {10.25932/publishup-48913},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489131},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 97},
  year      = {2020},
  abstract  = {Successfully completing any data science project demands careful consideration across its whole process. Although the focus is often put on later phases of the process, in practice, experts spend more time in earlier phases, preparing data, to make them consistent with the systems' requirements or to improve their models' accuracies. Duplicate detection is typically applied during the data cleaning phase, which is dedicated to removing data inconsistencies and improving the overall quality and usability of data. While data cleaning involves a plethora of approaches to perform specific operations, such as schema alignment and data normalization, the task of detecting and removing duplicate records is particularly challenging. Duplicates arise when multiple records representing the same entities exist in a database. Due to numerous reasons, spanning from simple typographical errors to different schemas and formats of integrated databases. Keeping a database free of duplicates is crucial for most use-cases, as their existence causes false negatives and false positives when matching queries against it. These two data quality issues have negative implications for tasks, such as hotel booking, where users may erroneously select a wrong hotel, or parcel delivery, where a parcel can get delivered to the wrong address. Identifying the variety of possible data issues to eliminate duplicates demands sophisticated approaches. While research in duplicate detection is well-established and covers different aspects of both efficiency and effectiveness, our work in this thesis focuses on the latter. We propose novel approaches to improve data quality before duplicate detection takes place and apply the latter in datasets even when prior labeling is not available. Our experiments show that improving data quality upfront can increase duplicate classification results by up to 19\%. To this end, we propose two novel pipelines that select and apply generic as well as address-specific data preparation steps with the purpose of maximizing the success of duplicate detection. Generic data preparation, such as the removal of special characters, can be applied to any relation with alphanumeric attributes. When applied, data preparation steps are selected only for attributes where there are positive effects on pair similarities, which indirectly affect classification, or on classification directly. Our work on addresses is twofold; first, we consider more domain-specific approaches to improve the quality of values, and, second, we experiment with known and modified versions of similarity measures to select the most appropriate per address attribute, e.g., city or country. To facilitate duplicate detection in applications where gold standard annotations are not available and obtaining them is not possible or too expensive, we propose MDedup. MDedup is a novel, rule-based, and fully automatic duplicate detection approach that is based on matching dependencies. These dependencies can be used to detect duplicates and can be discovered using state-of-the-art algorithms efficiently and without any prior labeling. MDedup uses two pipelines to first train on datasets with known labels, learning to identify useful matching dependencies, and then be applied on unseen datasets, regardless of any existing gold standard. Finally, our work is accompanied by open source code to enable repeatability of our research results and application of our approaches to other datasets.},
  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{Hitz2021,
  author    = {Hitz, Michael},
  title     = {Modellierung und Generierung kombinierbarer Benutzungsschnittstellenvarianten und deren gemeinschaftliche Nutzung in Dienst-Ökosystemen},
  doi       = {10.25932/publishup-50022},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-500224},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, 313},
  year      = {2021},
  abstract  = {Digitalisierung erm{\"o}glicht es uns, mit Partnern (z.B. Unternehmen, Institutionen) in einer IT-unterst{\"u}tzten Umgebung zu interagieren und T{\"a}tigkeiten auszuf{\"u}hren, die vormals manuell erledigt wurden. Ein Ziel der Digitalisierung ist dabei, Dienstleistungen unterschiedlicher fachlicher Dom{\"a}nen zu Prozessen zu kombinieren und vielen Nutzergruppen bedarfsgerecht zug{\"a}nglich zu machen. Hierzu stellen Anbieter technische Dienste bereit, die in unterschiedliche Anwendungen integriert werden k{\"o}nnen. Die Digitalisierung stellt die Anwendungsentwicklung vor neue Herausforderungen. Ein Aspekt ist die bedarfsgerechte Anbindung von Nutzern an Dienste. Zur Interaktion menschlicher Nutzer mit den Diensten werden Benutzungsschnittstellen ben{\"o}tigt, die auf deren Bed{\"u}rfnisse zugeschnitten sind. Hierzu werden Varianten f{\"u}r spezifische Nutzergruppen (fachliche Varianten) und variierende Umgebungen (technische Varianten) ben{\"o}tigt. Zunehmend m{\"u}ssen diese mit Diensten anderer Anbieter kombiniert werden k{\"o}nnen, um dom{\"a}nen{\"u}bergreifend Prozesse zu Anwendungen mit einem erh{\"o}hten Mehrwert f{\"u}r den Endnutzer zu verkn{\"u}pfen (z.B. eine Flugbuchung mit einer optionalen Reiseversicherung). Die Vielf{\"a}ltigkeit der Varianten l{\"a}sst die Erstellung von Benutzungsschnittstellen komplex und die Ergebnisse sehr individuell erscheinen. Daher werden die Varianten in der Praxis vorwiegend manuell erstellt. Dies f{\"u}hrt zur parallelen Entwicklung einer Vielzahl sehr {\"a}hnlicher Anwendungen, die nur geringes Potential zur Wiederverwendung besitzen. Die Folge sind hohe Aufw{\"a}nde bei Erstellung und Wartung. Dadurch wird h{\"a}ufig auf die Unterst{\"u}tzung kleiner Nutzerkreise mit speziellen Anforderungen verzichtet (z.B. Menschen mit physischen Einschr{\"a}nkungen), sodass diese weiterhin von der Digitalisierung ausgeschlossen bleiben. Die Arbeit stellt eine konsistente L{\"o}sung f{\"u}r diese neuen Herausforderungen mit den Mitteln der modellgetriebenen Entwicklung vor. Sie präsentiert einen Ansatz zur Modellierung von Benutzungsschnittstellen, Varianten und Kompositionen und deren automatischer Generierung f{\"u}r digitale Dienste in einem verteilten Umfeld. Die Arbeit schafft eine L{\"o}sung zur Wiederverwendung und gemeinschaftlichen Nutzung von Benutzungsschnittstellen {\"u}ber Anbietergrenzen hinweg. Sie f{\"u}hrt zu einer Infrastruktur, in der eine Vielzahl von Anbietern ihre Expertise in gemeinschaftliche Anwendungen einbringen k{\"o}nnen. Die Beitr{\"a}ge bestehen im Einzelnen in Konzepten und Metamodellen zur Modellierung von Benutzungsschnittstellen, Varianten und Kompositionen sowie einem Verfahren zu deren vollst{\"a}ndig automatisierten Transformation in funktionale Benutzungsschnittstellen. Zur Umsetzung der gemeinschaftlichen Nutzbarkeit werden diese erg{\"a}nzt um eine universelle Repr{\"a}sentation der Modelle, einer Methodik zur Anbindung unterschiedlicher Dienst-Anbieter sowie einer Architektur zur verteilten Nutzung der Artefakte und Verfahren in einer dienstorientierten Umgebung. Der Ansatz bietet die Chance, unterschiedlichste Menschen bedarfsgerecht an der Digitalisierung teilhaben zu lassen. Damit setzt die Arbeit Impulse f{\"u}r zuk{\"u}nftige Methoden zur Anwendungserstellung in einem zunehmend vielf{\"a}ltigen Umfeld.},
  language  = {de}
}
@phdthesis{Haarmann2022,
  author    = {Haarmann, Stephan},
  title     = {WICKR: A Joint Semantics for Flexible Processes and Data},
  doi       = {10.25932/publishup-54613},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-546137},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvii, 191},
  year      = {2022},
  abstract  = {Knowledge-intensive business processes are flexible and data-driven. Therefore, traditional process modeling languages do not meet their requirements: These languages focus on highly structured processes in which data plays a minor role. As a result, process-oriented information systems fail to assist knowledge workers on executing their processes. We propose a novel case management approach that combines flexible activity-centric processes with data models, and we provide a joint semantics using colored Petri nets. The approach is suited to model, verify, and enact knowledge-intensive processes and can aid the development of information systems that support knowledge work. Knowledge-intensive processes are human-centered, multi-variant, and data-driven. Typical domains include healthcare, insurances, and law. The processes cannot be fully modeled, since the underlying knowledge is too vast and changes too quickly. Thus, models for knowledge-intensive processes are necessarily underspecified. In fact, a case emerges gradually as knowledge workers make informed decisions. Knowledge work imposes special requirements on modeling and managing respective processes. They include flexibility during design and execution, ad-hoc adaption to unforeseen situations, and the integration of behavior and data. However, the predominantly used process modeling languages (e.g., BPMN) are unsuited for this task. Therefore, novel modeling languages have been proposed. Many of them focus on activities' data requirements and declarative constraints rather than imperative control flow. Fragment-Based Case Management, for example, combines activity-centric imperative process fragments with declarative data requirements. At runtime, fragments can be combined dynamically, and new ones can be added. Yet, no integrated semantics for flexible activity-centric process models and data models exists. In this thesis, Wickr, a novel case modeling approach extending fragment-based Case Management, is presented. It supports batch processing of data, sharing data among cases, and a full-fledged data model with associations and multiplicity constraints. We develop a translational semantics for Wickr targeting (colored) Petri nets. The semantics assert that a case adheres to the constraints in both the process fragments and the data models. Among other things, multiplicity constraints must not be violated. Furthermore, the semantics are extended to multiple cases that operate on shared data. Wickr shows that the data structure may reflect process behavior and vice versa. Based on its semantics, prototypes for executing and verifying case models showcase the feasibility of Wickr. Its applicability to knowledge-intensive and to data-centric processes is evaluated using well-known requirements from related work.},
  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{FreitasdaCruz2021,
  author    = {Freitas da Cruz, Harry},
  title     = {Standardizing clinical predictive modeling},
  doi       = {10.25932/publishup-51496},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-514960},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiii, 133},
  year      = {2021},
  abstract  = {An ever-increasing number of prediction models is published every year in different medical specialties. Prognostic or diagnostic in nature, these models support medical decision making by utilizing one or more items of patient data to predict outcomes of interest, such as mortality or disease progression. While different computer tools exist that support clinical predictive modeling, I observed that the state of the art is lacking in the extent to which the needs of research clinicians are addressed. When it comes to model development, current support tools either 1) target specialist data engineers, requiring advanced coding skills, or 2) cater to a general-purpose audience, therefore not addressing the specific needs of clinical researchers. Furthermore, barriers to data access across institutional silos, cumbersome model reproducibility and extended experiment-to-result times significantly hampers validation of existing models. Similarly, without access to interpretable explanations, which allow a given model to be fully scrutinized, acceptance of machine learning approaches will remain limited. Adequate tool support, i.e., a software artifact more targeted at the needs of clinical modeling, can help mitigate the challenges identified with respect to model development, validation and interpretation. To this end, I conducted interviews with modeling practitioners in health care to better understand the modeling process itself and ascertain in what aspects adequate tool support could advance the state of the art. The functional and non-functional requirements identified served as the foundation for a software artifact that can be used for modeling outcome and risk prediction in health research. To establish the appropriateness of this approach, I implemented a use case study in the Nephrology domain for acute kidney injury, which was validated in two different hospitals. Furthermore, I conducted user evaluation to ascertain whether such an approach provides benefits compared to the state of the art and the extent to which clinical practitioners could benefit from it. Finally, when updating models for external validation, practitioners need to apply feature selection approaches to pinpoint the most relevant features, since electronic health records tend to contain several candidate predictors. Building upon interpretability methods, I developed an explanation-driven recursive feature elimination approach. This method was comprehensively evaluated against state-of-the art feature selection methods. Therefore, this thesis' main contributions are three-fold, namely, 1) designing and developing a software artifact tailored to the specific needs of the clinical modeling domain, 2) demonstrating its application in a concrete case in the Nephrology context and 3) development and evaluation of a new feature selection approach applicable in a validation context that builds upon interpretability methods. In conclusion, I argue that appropriate tooling, which relies on standardization and parametrization, can support rapid model prototyping and collaboration between clinicians and data scientists in clinical predictive modeling.},
  language  = {en}
}
@phdthesis{Shaabani2020,
  author    = {Shaabani, Nuhad},
  title     = {On discovering and incrementally updating inclusion dependencies},
  doi       = {10.25932/publishup-47186},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471862},
  school      = {Universit{\"a}t Potsdam},
  pages     = {119},
  year      = {2020},
  abstract  = {In today's world, many applications produce large amounts of data at an enormous rate. Analyzing such datasets for metadata is indispensable for effectively understanding, storing, querying, manipulating, and mining them. Metadata summarizes technical properties of a dataset which rang from basic statistics to complex structures describing data dependencies. One type of dependencies is inclusion dependency (IND), which expresses subset-relationships between attributes of datasets. Therefore, inclusion dependencies are important for many data management applications in terms of data integration, query optimization, schema redesign, or integrity checking. So, the discovery of inclusion dependencies in unknown or legacy datasets is at the core of any data profiling effort. For exhaustively detecting all INDs in large datasets, we developed S-indd++, a new algorithm that eliminates the shortcomings of existing IND-detection algorithms and significantly outperforms them. S-indd++ is based on a novel concept for the attribute clustering for efficiently deriving INDs. Inferring INDs from our attribute clustering eliminates all redundant operations caused by other algorithms. S-indd++ is also based on a novel partitioning strategy that enables discording a large number of candidates in early phases of the discovering process. Moreover, S-indd++ does not require to fit a partition into the main memory--this is a highly appreciable property in the face of ever-growing datasets. S-indd++ reduces up to 50\% of the runtime of the state-of-the-art approach. None of the approach for discovering INDs is appropriate for the application on dynamic datasets; they can not update the INDs after an update of the dataset without reprocessing it entirely. To this end, we developed the first approach for incrementally updating INDs in frequently changing datasets. We achieved that by reducing the problem of incrementally updating INDs to the incrementally updating the attribute clustering from which all INDs are efficiently derivable. We realized the update of the clusters by designing new operations to be applied to the clusters after every data update. The incremental update of INDs reduces the time of the complete rediscovery by up to 99.999\%. All existing algorithms for discovering n-ary INDs are based on the principle of candidate generation--they generate candidates and test their validity in the given data instance. The major disadvantage of this technique is the exponentially growing number of database accesses in terms of SQL queries required for validation. We devised Mind2, the first approach for discovering n-ary INDs without candidate generation. Mind2 is based on a new mathematical framework developed in this thesis for computing the maximum INDs from which all other n-ary INDs are derivable. The experiments showed that Mind2 is significantly more scalable and effective than hypergraph-based algorithms.},
  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{Baier2015,
  author    = {Baier, Thomas},
  title     = {Matching events and activities},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84548},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxii, 213},
  year      = {2015},
  abstract  = {Nowadays, business processes are increasingly supported by IT services that produce massive amounts of event data during process execution. Aiming at a better process understanding and improvement, this event data can be used to analyze processes using process mining techniques. Process models can be automatically discovered and the execution can be checked for conformance to specified behavior. Moreover, existing process models can be enhanced and annotated with valuable information, for example for performance analysis. While the maturity of process mining algorithms is increasing and more tools are entering the market, process mining projects still face the problem of different levels of abstraction when comparing events with modeled business activities. Mapping the recorded events to activities of a given process model is essential for conformance checking, annotation and understanding of process discovery results. Current approaches try to abstract from events in an automated way that does not capture the required domain knowledge to fit business activities. Such techniques can be a good way to quickly reduce complexity in process discovery. Yet, they fail to enable techniques like conformance checking or model annotation, and potentially create misleading process discovery results by not using the known business terminology. In this thesis, we develop approaches that abstract an event log to the same level that is needed by the business. Typically, this abstraction level is defined by a given process model. Thus, the goal of this thesis is to match events from an event log to activities in a given process model. To accomplish this goal, behavioral and linguistic aspects of process models and event logs as well as domain knowledge captured in existing process documentation are taken into account to build semiautomatic matching approaches. The approaches establish a pre--processing for every available process mining technique that produces or annotates a process model, thereby reducing the manual effort for process analysts. While each of the presented approaches can be used in isolation, we also introduce a general framework for the integration of different matching approaches. The approaches have been evaluated in case studies with industry and using a large industry process model collection and simulated event logs. The evaluation demonstrates the effectiveness and efficiency of the approaches and their robustness towards nonconforming execution logs.},
  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{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}
}