@article{AaRebmannLeopold2021, author = {Aa, Han van der and Rebmann, Adrian and Leopold, Henrik}, title = {Natural language-based detection of semantic execution anomalies in event logs}, series = {Information systems : IS ; an international journal ; data bases}, volume = {102}, journal = {Information systems : IS ; an international journal ; data bases}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0306-4379}, doi = {10.1016/j.is.2021.101824}, pages = {13}, year = {2021}, abstract = {Anomaly detection in process mining aims to recognize outlying or unexpected behavior in event logs for purposes such as the removal of noise and identification of conformance violations. Existing techniques for this task are primarily frequency-based, arguing that behavior is anomalous because it is uncommon. However, such techniques ignore the semantics of recorded events and, therefore, do not take the meaning of potential anomalies into consideration. In this work, we overcome this caveat and focus on the detection of anomalies from a semantic perspective, arguing that anomalies can be recognized when process behavior does not make sense. To achieve this, we propose an approach that exploits the natural language associated with events. Our key idea is to detect anomalous process behavior by identifying semantically inconsistent execution patterns. To detect such patterns, we first automatically extract business objects and actions from the textual labels of events. We then compare these against a process-independent knowledge base. By populating this knowledge base with patterns from various kinds of resources, our approach can be used in a range of contexts and domains. We demonstrate the capability of our approach to successfully detect semantic execution anomalies through an evaluation based on a set of real-world and synthetic event logs and show the complementary nature of semantics-based anomaly detection to existing frequency-based techniques.}, language = {en} } @book{AdrianoBleifussChengetal.2019, author = {Adriano, Christian and Bleifuß, Tobias and Cheng, Lung-Pan and Diba, Kiarash and Fricke, Andreas and Grapentin, Andreas and Jiang, Lan and Kovacs, Robert and Krejca, Martin Stefan and Mandal, Sankalita and Marwecki, Sebastian and Matthies, Christoph and Mattis, Toni and Niephaus, Fabio and Pirl, Lukas and Quinzan, Francesco and Ramson, Stefan and Rezaei, Mina and Risch, Julian and Rothenberger, Ralf and Roumen, Thijs and Stojanovic, Vladeta and Wolf, Johannes}, title = {Technical report}, number = {129}, editor = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick and Friedrich, Tobias and B{\"o}ttinger, Erwin and Lippert, Christoph}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-465-4}, issn = {1613-5652}, doi = {10.25932/publishup-42753}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427535}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 267}, year = {2019}, abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the research school, this technical report covers a wide range of topics. These include but are not limited to: Human Computer Interaction and Computer Vision as Service; Service-oriented Geovisualization Systems; Algorithm Engineering for Service-oriented Systems; Modeling and Verification of Self-adaptive Service-oriented Systems; Tools and Methods for Software Engineering in Service-oriented Systems; Security Engineering of Service-based IT Systems; Service-oriented Information Systems; Evolutionary Transition of Enterprise Applications to Service Orientation; Operating System Abstractions for Service-oriented Computing; and Services Specification, Composition, and Enactment.}, language = {en} } @phdthesis{Afifi2023, author = {Afifi, Haitham}, title = {Wireless In-Network Processing for Multimedia Applications}, doi = {10.25932/publishup-60437}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604371}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 233}, year = {2023}, abstract = {With the recent growth of sensors, cloud computing handles the data processing of many applications. Processing some of this data on the cloud raises, however, many concerns regarding, e.g., privacy, latency, or single points of failure. Alternatively, thanks to the development of embedded systems, smart wireless devices can share their computation capacity, creating a local wireless cloud for in-network processing. In this context, the processing of an application is divided into smaller jobs so that a device can run one or more jobs. The contribution of this thesis to this scenario is divided into three parts. In part one, I focus on wireless aspects, such as power control and interference management, for deciding which jobs to run on which node and how to route data between nodes. Hence, I formulate optimization problems and develop heuristic and meta-heuristic algorithms to allocate wireless and computation resources. Additionally, to deal with multiple applications competing for these resources, I develop a reinforcement learning (RL) admission controller to decide which application should be admitted. Next, I look into acoustic applications to improve wireless throughput by using microphone clock synchronization to synchronize wireless transmissions. In the second part, I jointly work with colleagues from the acoustic processing field to optimize both network and application (i.e., acoustic) qualities. My contribution focuses on the network part, where I study the relation between acoustic and network qualities when selecting a subset of microphones for collecting audio data or selecting a subset of optional jobs for processing these data; too many microphones or too many jobs can lessen quality by unnecessary delays. Hence, I develop RL solutions to select the subset of microphones under network constraints when the speaker is moving while still providing good acoustic quality. Furthermore, I show that autonomous vehicles carrying microphones improve the acoustic qualities of different applications. Accordingly, I develop RL solutions (single and multi-agent ones) for controlling these vehicles. In the third part, I close the gap between theory and practice. I describe the features of my open-source framework used as a proof of concept for wireless in-network processing. Next, I demonstrate how to run some algorithms developed by colleagues from acoustic processing using my framework. I also use the framework for studying in-network delays (wireless and processing) using different distributions of jobs and network topologies.}, language = {en} } @article{AlarioHoyosDelgadoKloosKiendletal.2023, author = {Alario Hoyos, Carlos and Delgado Kloos, Carlos and Kiendl, Doris and Terzieva, Liliya}, title = {Innovat MOOC}, series = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, journal = {EMOOCs 2023 : Post-Covid Prospects for Massive Open Online Courses - Boost or Backlash?}, editor = {Meinel, Christoph and Schweiger, Stefanie and Staubitz, Thomas and Conrad, Robert and Alario Hoyos, Carlos and Ebner, Martin and Sancassani, Susanna and Żur, Agnieszka and Friedl, Christian and Halawa, Sherif and Gamage, Dilrukshi and Scott, Jeffrey and Kristine Jonson Carlon, May and Deville, Yves and Gaebel, Michael and Delgado Kloos, Carlos and von Schmieden, Karen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-62456}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624560}, pages = {229 -- 237}, year = {2023}, abstract = {The COVID-19 pandemic has revealed the importance for university teachers to have adequate pedagogical and technological competences to cope with the various possible educational scenarios (face-to-face, online, hybrid, etc.), making use of appropriate active learning methodologies and supporting technologies to foster a more effective learning environment. In this context, the InnovaT project has been an important initiative to support the development of pedagogical and technological competences of university teachers in Latin America through several trainings aiming to promote teacher innovation. These trainings combined synchronous online training through webinars and workshops with asynchronous online training through the MOOC "Innovative Teaching in Higher Education." This MOOC was released twice. The first run took place right during the lockdown of 2020, when Latin American teachers needed urgent training to move to emergency remote teaching overnight. The second run took place in 2022 with the return to face-to-face teaching and the implementation of hybrid educational models. This article shares the results of the design of the MOOC considering the constraints derived from the lockdowns applied in each country, the lessons learned from the delivery of such a MOOC to Latin American university teachers, and the results of the two runs of the MOOC.}, language = {en} } @misc{AlbertOwolabiGebeletal.2020, author = {Albert, Justin Amadeus and Owolabi, Victor and Gebel, Arnd and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, title = {Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {3}, doi = {10.25932/publishup-48413}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-484130}, pages = {24}, year = {2020}, abstract = {Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.}, language = {en} } @article{AlbertOwolabiGebeletal.2020, author = {Albert, Justin Amadeus and Owolabi, Victor and Gebel, Arnd and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, title = {Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard}, series = {Sensors}, volume = {20}, journal = {Sensors}, number = {18}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s20185104}, pages = {22}, year = {2020}, abstract = {Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.}, language = {en} } @phdthesis{AlhosseiniAlmodarresiYasin2024, author = {Alhosseini Almodarresi Yasin, Seyed Ali}, title = {Classification, prediction and evaluation of graph neural networks on online social media platforms}, doi = {10.25932/publishup-62642}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-626421}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 78}, year = {2024}, abstract = {The vast amount of data generated on social media platforms have made them a valuable source of information for businesses, governments and researchers. Social media data can provide insights into user behavior, preferences, and opinions. In this work, we address two important challenges in social media analytics. Predicting user engagement with online content has become a critical task for content creators to increase user engagement and reach larger audiences. Traditional user engagement prediction approaches rely solely on features derived from the user and content. However, a new class of deep learning methods based on graphs captures not only the content features but also the graph structure of social media networks. This thesis proposes a novel Graph Neural Network (GNN) approach to predict user interaction with tweets. The proposed approach combines the features of users, tweets and their engagement graphs. The tweet text features are extracted using pre-trained embeddings from language models, and a GNN layer is used to embed the user in a vector space. The GNN model then combines the features and graph structure to predict user engagement. The proposed approach achieves an accuracy value of 94.22\% in classifying user interactions, including likes, retweets, replies, and quotes. Another major challenge in social media analysis is detecting and classifying social bot accounts. Social bots are automated accounts used to manipulate public opinion by spreading misinformation or generating fake interactions. Detecting social bots is critical to prevent their negative impact on public opinion and trust in social media. In this thesis, we classify social bots on Twitter by applying Graph Neural Networks. The proposed approach uses a combination of both the features of a node and an aggregation of the features of a node's neighborhood to classify social bot accounts. Our final results indicate a 6\% improvement in the area under the curve score in the final predictions through the utilization of GNN. Overall, our work highlights the importance of social media data and the potential of new methods such as GNNs to predict user engagement and detect social bots. These methods have important implications for improving the quality and reliability of information on social media platforms and mitigating the negative impact of social bots on public opinion and discourse.}, language = {en} } @misc{AlvianoRomeroDavilaSchaub2018, author = {Alviano, Mario and Romero Davila, Javier and Schaub, Torsten H.}, title = {Preference Relations by Approximation}, series = {Sixteenth International Conference on Principles of Knowledge Representation and Reasoning}, journal = {Sixteenth International Conference on Principles of Knowledge Representation and Reasoning}, publisher = {AAAI Conference on Artificial Intelligence}, address = {Palo Alto}, pages = {2 -- 11}, year = {2018}, abstract = {Declarative languages for knowledge representation and reasoning provide constructs to define preference relations over the set of possible interpretations, so that preferred models represent optimal solutions of the encoded problem. We introduce the notion of approximation for replacing preference relations with stronger preference relations, that is, relations comparing more pairs of interpretations. Our aim is to accelerate the computation of a non-empty subset of the optimal solutions by means of highly specialized algorithms. We implement our approach in Answer Set Programming (ASP), where problems involving quantitative and qualitative preference relations can be addressed by ASPRIN, implementing a generic optimization algorithm. Unlike this, chains of approximations allow us to reduce several preference relations to the preference relations associated with ASP's native weak constraints and heuristic directives. In this way, ASPRIN can now take advantage of several highly optimized algorithms implemented by ASP solvers for computing optimal solutions}, language = {en} } @article{AmbassaKayemWolthusenetal.2018, author = {Ambassa, Pacome L. and Kayem, Anne Voluntas dei Massah and Wolthusen, Stephen D. and Meinel, Christoph}, title = {Inferring private user behaviour based on information leakage}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_7}, pages = {145 -- 159}, year = {2018}, abstract = {In rural/remote areas, resource constrained smart micro-grid (RCSMG) architectures can provide a cost-effective power supply alternative in cases when connectivity to the national power grid is impeded by factors such as load shedding. RCSMG architectures can be designed to handle communications over a distributed lossy network in order to minimise operation costs. However, due to the unreliable nature of lossy networks communication data can be distorted by noise additions that alter the veracity of the data. In this chapter, we consider cases in which an adversary who is internal to the RCSMG, deliberately distorts communicated data to gain an unfair advantage over the RCSMG's users. The adversary's goal is to mask malicious data manipulations as distortions due to additive noise due to communication channel unreliability. Distinguishing malicious data distortions from benign distortions is important in ensuring trustworthiness of the RCSMG. Perturbation data anonymisation algorithms can be used to alter transmitted data to ensure that adversarial manipulation of the data reveals no information that the adversary can take advantage of. However, because existing data perturbation anonymisation algorithms operate by using additive noise to anonymise data, using these algorithms in the RCSMG context is challenging. This is due to the fact that distinguishing benign noise additions from malicious noise additions is a difficult problem. In this chapter, we present a brief survey of cases of privacy violations due to inferences drawn from observed power consumption patterns in RCSMGs centred on inference, and propose a method of mitigating these risks. The lesson here is that while RCSMGs give users more control over power management and distribution, good anonymisation is essential to protecting personal information on RCSMGs.}, language = {en} } @phdthesis{Amirkhanyan2019, author = {Amirkhanyan, Aragats}, title = {Methods and frameworks for GeoSpatioTemporal data analytics}, doi = {10.25932/publishup-44168}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-441685}, school = {Universit{\"a}t Potsdam}, pages = {xxiv, 133}, year = {2019}, abstract = {In the era of social networks, internet of things and location-based services, many online services produce a huge amount of data that have valuable objective information, such as geographic coordinates and date time. These characteristics (parameters) in the combination with a textual parameter bring the challenge for the discovery of geospatiotemporal knowledge. This challenge requires efficient methods for clustering and pattern mining in spatial, temporal and textual spaces. In this thesis, we address the challenge of providing methods and frameworks for geospatiotemporal data analytics. As an initial step, we address the challenges of geospatial data processing: data gathering, normalization, geolocation, and storage. That initial step is the basement to tackle the next challenge -- geospatial clustering challenge. The first step of this challenge is to design the method for online clustering of georeferenced data. This algorithm can be used as a server-side clustering algorithm for online maps that visualize massive georeferenced data. As the second step, we develop the extension of this method that considers, additionally, the temporal aspect of data. For that, we propose the density and intensity-based geospatiotemporal clustering algorithm with fixed distance and time radius. Each version of the clustering algorithm has its own use case that we show in the thesis. In the next chapter of the thesis, we look at the spatiotemporal analytics from the perspective of the sequential rule mining challenge. We design and implement the framework that transfers data into textual geospatiotemporal data - data that contain geographic coordinates, time and textual parameters. By this way, we address the challenge of applying pattern/rule mining algorithms in geospatiotemporal space. As the applicable use case study, we propose spatiotemporal crime analytics -- discovery spatiotemporal patterns of crimes in publicly available crime data. The second part of the thesis, we dedicate to the application part and use case studies. We design and implement the application that uses the proposed clustering algorithms to discover knowledge in data. Jointly with the application, we propose the use case studies for analysis of georeferenced data in terms of situational and public safety awareness.}, language = {en} } @misc{AndjelkovicBabicLietal.2019, author = {Andjelkovic, Marko and Babic, Milan and Li, Yuanqing and Schrape, Oliver and Krstić, Miloš and Kraemer, Rolf}, title = {Use of decoupling cells for mitigation of SET effects in CMOS combinational gates}, series = {2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS)}, journal = {2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-9562-3}, doi = {10.1109/ICECS.2018.8617996}, pages = {361 -- 364}, year = {2019}, abstract = {This paper investigates the applicability of CMOS decoupling cells for mitigating the Single Event Transient (SET) effects in standard combinational gates. The concept is based on the insertion of two decoupling cells between the gate's output and the power/ground terminals. To verify the proposed hardening approach, extensive SPICE simulations have been performed with standard combinational cells designed in IHP's 130 nm bulk CMOS technology. Obtained simulation results have shown that the insertion of decoupling cells results in the increase of the gate's critical charge, thus reducing the gate's soft error rate (SER). Moreover, the decoupling cells facilitate the suppression of SET pulses propagating through the gate. It has been shown that the decoupling cells may be a competitive alternative to gate upsizing and gate duplication for hardening the gates with lower critical charge and multiple (3 or 4) inputs, as well as for filtering the short SET pulses induced by low-LET particles.}, language = {en} } @misc{ArandaSchoelzelMendezetal.2018, author = {Aranda, Juan and Sch{\"o}lzel, Mario and Mendez, Diego and Carrillo, Henry}, title = {An energy consumption model for multiModal wireless sensor networks based on wake-up radio receivers}, series = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, journal = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6820-7}, doi = {10.1109/ColComCon.2018.8466728}, pages = {6}, year = {2018}, abstract = {Energy consumption is a major concern in Wireless Sensor Networks. A significant waste of energy occurs due to the idle listening and overhearing problems, which are typically avoided by turning off the radio, while no transmission is ongoing. The classical approach for allowing the reception of messages in such situations is to use a low-duty-cycle protocol, and to turn on the radio periodically, which reduces the idle listening problem, but requires timers and usually unnecessary wakeups. A better solution is to turn on the radio only on demand by using a Wake-up Radio Receiver (WuRx). In this paper, an energy model is presented to estimate the energy saving in various multi-hop network topologies under several use cases, when a WuRx is used instead of a classical low-duty-cycling protocol. The presented model also allows for estimating the benefit of various WuRx properties like using addressing or not.}, language = {en} } @book{BaltzerHradilakPfennigschmidtetal.2021, author = {Baltzer, Wanda and Hradilak, Theresa and Pfennigschmidt, Lara and Prestin, Luc Maurice and Spranger, Moritz and Stadlinger, Simon and Wendt, Leo and Lincke, Jens and Rein, Patrick and Church, Luke and Hirschfeld, Robert}, title = {An individual-centered approach to visualize people's opinions and demographic information}, number = {136}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-504-0}, issn = {1613-5652}, doi = {10.25932/publishup-49145}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-491457}, publisher = {Universit{\"a}t Potsdam}, pages = {326}, year = {2021}, abstract = {The noble way to substantiate decisions that affect many people is to ask these people for their opinions. For governments that run whole countries, this means asking all citizens for their views to consider their situations and needs. Organizations such as Africa's Voices Foundation, who want to facilitate communication between decision-makers and citizens of a country, have difficulty mediating between these groups. To enable understanding, statements need to be summarized and visualized. Accomplishing these goals in a way that does justice to the citizens' voices and situations proves challenging. Standard charts do not help this cause as they fail to create empathy for the people behind their graphical abstractions. Furthermore, these charts do not create trust in the data they are representing as there is no way to see or navigate back to the underlying code and the original data. To fulfill these functions, visualizations would highly benefit from interactions to explore the displayed data, which standard charts often only limitedly provide. To help improve the understanding of people's voices, we developed and categorized 80 ideas for new visualizations, new interactions, and better connections between different charts, which we present in this report. From those ideas, we implemented 10 prototypes and two systems that integrate different visualizations. We show that this integration allows consistent appearance and behavior of visualizations. The visualizations all share the same main concept: representing each individual with a single dot. To realize this idea, we discuss technologies that efficiently allow the rendering of a large number of these dots. With these visualizations, direct interactions with representations of individuals are achievable by clicking on them or by dragging a selection around them. This direct interaction is only possible with a bidirectional connection from the visualization to the data it displays. We discuss different strategies for bidirectional mappings and the trade-offs involved. Having unified behavior across visualizations enhances exploration. For our prototypes, that includes grouping, filtering, highlighting, and coloring of dots. Our prototyping work was enabled by the development environment Lively4. We explain which parts of Lively4 facilitated our prototyping process. Finally, we evaluate our approach to domain problems and our developed visualization concepts. Our work provides inspiration and a starting point for visualization development in this domain. Our visualizations can improve communication between citizens and their government and motivate empathetic decisions. Our approach, combining low-level entities to create visualizations, provides value to an explorative and empathetic workflow. We show that the design space for visualizing this kind of data has a lot of potential and that it is possible to combine qualitative and quantitative approaches to data analysis.}, language = {en} } @phdthesis{Bano2023, author = {Bano, Dorina}, title = {Discovering data models from event logs}, doi = {10.25932/publishup-58542}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585427}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 137}, year = {2023}, abstract = {In the last two decades, process mining has developed from a niche discipline to a significant research area with considerable impact on academia and industry. Process mining enables organisations to identify the running business processes from historical execution data. The first requirement of any process mining technique is an event log, an artifact that represents concrete business process executions in the form of sequence of events. These logs can be extracted from the organization's information systems and are used by process experts to retrieve deep insights from the organization's running processes. Considering the events pertaining to such logs, the process models can be automatically discovered and enhanced or annotated with performance-related information. Besides behavioral information, event logs contain domain specific data, albeit implicitly. However, such data are usually overlooked and, thus, not utilized to their full potential. Within the process mining area, we address in this thesis the research gap of discovering, from event logs, the contextual information that cannot be captured by applying existing process mining techniques. Within this research gap, we identify four key problems and tackle them by looking at an event log from different angles. First, we address the problem of deriving an event log in the absence of a proper database access and domain knowledge. The second problem is related to the under-utilization of the implicit domain knowledge present in an event log that can increase the understandability of the discovered process model. Next, there is a lack of a holistic representation of the historical data manipulation at the process model level of abstraction. Last but not least, each process model presumes to be independent of other process models when discovered from an event log, thus, ignoring possible data dependencies between processes within an organization. For each of the problems mentioned above, this thesis proposes a dedicated method. The first method provides a solution to extract an event log only from the transactions performed on the database that are stored in the form of redo logs. The second method deals with discovering the underlying data model that is implicitly embedded in the event log, thus, complementing the discovered process model with important domain knowledge information. The third method captures, on the process model level, how the data affects the running process instances. Lastly, the fourth method is about the discovery of the relations between business processes (i.e., how they exchange data) from a set of event logs and explicitly representing such complex interdependencies in a business process architecture. All the methods introduced in this thesis are implemented as a prototype and their feasibility is proven by being applied on real-life event logs.}, language = {en} } @book{BarkowskyGiese2023, author = {Barkowsky, Matthias and Giese, Holger}, title = {Modular and incremental global model management with extended generalized discrimination networks}, number = {154}, isbn = {978-3-86956-555-2}, issn = {1613-5652}, doi = {10.25932/publishup-57396}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-573965}, publisher = {Universit{\"a}t Potsdam}, pages = {63 -- 63}, year = {2023}, abstract = {Complex projects developed under the model-driven engineering paradigm nowadays often involve several interrelated models, which are automatically processed via a multitude of model operations. Modular and incremental construction and execution of such networks of models and model operations are required to accommodate efficient development with potentially large-scale models. The underlying problem is also called Global Model Management. In this report, we propose an approach to modular and incremental Global Model Management via an extension to the existing technique of Generalized Discrimination Networks (GDNs). In addition to further generalizing the notion of query operations employed in GDNs, we adapt the previously query-only mechanism to operations with side effects to integrate model transformation and model synchronization. We provide incremental algorithms for the execution of the resulting extended Generalized Discrimination Networks (eGDNs), as well as a prototypical implementation for a number of example eGDN operations. Based on this prototypical implementation, we experiment with an application scenario from the software development domain to empirically evaluate our approach with respect to scalability and conceptually demonstrate its applicability in a typical scenario. Initial results confirm that the presented approach can indeed be employed to realize efficient Global Model Management in the considered scenario.}, language = {en} } @book{BarkowskyGiese2023, author = {Barkowsky, Matthias and Giese, Holger}, title = {Triple graph grammars for multi-version models}, number = {155}, isbn = {978-3-86956-556-9}, issn = {1613-5652}, doi = {10.25932/publishup-57399}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-573994}, publisher = {Universit{\"a}t Potsdam}, pages = {28 -- 28}, year = {2023}, abstract = {Like conventional software projects, projects in model-driven software engineering require adequate management of multiple versions of development artifacts, importantly allowing living with temporary inconsistencies. In the case of model-driven software engineering, employed versioning approaches also have to handle situations where different artifacts, that is, different models, are linked via automatic model transformations. In this report, we propose a technique for jointly handling the transformation of multiple versions of a source model into corresponding versions of a target model, which enables the use of a more compact representation that may afford improved execution time of both the transformation and further analysis operations. Our approach is based on the well-known formalism of triple graph grammars and a previously introduced encoding of model version histories called multi-version models. In addition to showing the correctness of our approach with respect to the standard semantics of triple graph grammars, we conduct an empirical evaluation that demonstrates the potential benefit regarding execution time performance.}, language = {en} } @phdthesis{Bartz2022, author = {Bartz, Christian}, title = {Reducing the annotation burden: deep learning for optical character recognition using less manual annotations}, doi = {10.25932/publishup-55540}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-555407}, school = {Universit{\"a}t Potsdam}, pages = {xxiv, 183}, year = {2022}, abstract = {Text is a ubiquitous entity in our world and daily life. We encounter it nearly everywhere in shops, on the street, or in our flats. Nowadays, more and more text is contained in digital images. These images are either taken using cameras, e.g., smartphone cameras, or taken using scanning devices such as document scanners. The sheer amount of available data, e.g., millions of images taken by Google Streetview, prohibits manual analysis and metadata extraction. Although much progress was made in the area of optical character recognition (OCR) for printed text in documents, broad areas of OCR are still not fully explored and hold many research challenges. With the mainstream usage of machine learning and especially deep learning, one of the most pressing problems is the availability and acquisition of annotated ground truth for the training of machine learning models because obtaining annotated training data using manual annotation mechanisms is time-consuming and costly. In this thesis, we address of how we can reduce the costs of acquiring ground truth annotations for the application of state-of-the-art machine learning methods to optical character recognition pipelines. To this end, we investigate how we can reduce the annotation cost by using only a fraction of the typically required ground truth annotations, e.g., for scene text recognition systems. We also investigate how we can use synthetic data to reduce the need of manual annotation work, e.g., in the area of document analysis for archival material. In the area of scene text recognition, we have developed a novel end-to-end scene text recognition system that can be trained using inexact supervision and shows competitive/state-of-the-art performance on standard benchmark datasets for scene text recognition. Our method consists of two independent neural networks, combined using spatial transformer networks. Both networks learn together to perform text localization and text recognition at the same time while only using annotations for the recognition task. We apply our model to end-to-end scene text recognition (meaning localization and recognition of words) and pure scene text recognition without any changes in the network architecture. In the second part of this thesis, we introduce novel approaches for using and generating synthetic data to analyze handwriting in archival data. First, we propose a novel preprocessing method to determine whether a given document page contains any handwriting. We propose a novel data synthesis strategy to train a classification model and show that our data synthesis strategy is viable by evaluating the trained model on real images from an archive. Second, we introduce the new analysis task of handwriting classification. Handwriting classification entails classifying a given handwritten word image into classes such as date, word, or number. Such an analysis step allows us to select the best fitting recognition model for subsequent text recognition; it also allows us to reason about the semantic content of a given document page without the need for fine-grained text recognition and further analysis steps, such as Named Entity Recognition. We show that our proposed approaches work well when trained on synthetic data. Further, we propose a flexible metric learning approach to allow zero-shot classification of classes unseen during the network's training. Last, we propose a novel data synthesis algorithm to train off-the-shelf pixel-wise semantic segmentation networks for documents. Our data synthesis pipeline is based on the famous Style-GAN architecture and can synthesize realistic document images with their corresponding segmentation annotation without the need for any annotated data!}, language = {en} } @book{BartzKrestel2021, author = {Bartz, Christian and Krestel, Ralf}, title = {Deep learning for computer vision in the art domain}, number = {139}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-514-9}, issn = {1613-5652}, doi = {10.25932/publishup-51290}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-512906}, publisher = {Universit{\"a}t Potsdam}, pages = {vii, 79}, year = {2021}, abstract = {In recent years, computer vision algorithms based on machine learning have seen rapid development. In the past, research mostly focused on solving computer vision problems such as image classification or object detection on images displaying natural scenes. Nowadays other fields such as the field of cultural heritage, where an abundance of data is available, also get into the focus of research. In the line of current research endeavours, we collaborated with the Getty Research Institute which provided us with a challenging dataset, containing images of paintings and drawings. In this technical report, we present the results of the seminar "Deep Learning for Computer Vision". In this seminar, students of the Hasso Plattner Institute evaluated state-of-the-art approaches for image classification, object detection and image recognition on the dataset of the Getty Research Institute. The main challenge when applying modern computer vision methods to the available data is the availability of annotated training data, as the dataset provided by the Getty Research Institute does not contain a sufficient amount of annotated samples for the training of deep neural networks. However, throughout the report we show that it is possible to achieve satisfying to very good results, when using further publicly available datasets, such as the WikiArt dataset, for the training of machine learning models.}, language = {en} } @misc{BartzYangMeinel2018, author = {Bartz, Christian and Yang, Haojin and Meinel, Christoph}, title = {SEE: Towards semi-supervised end-to-end scene text recognition}, series = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, Thirtieth Innovative Applications of Artificial Intelligence Conference, Eight Symposium on Educational Advances in Artificial Intelligence}, volume = {10}, journal = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, Thirtieth Innovative Applications of Artificial Intelligence Conference, Eight Symposium on Educational Advances in Artificial Intelligence}, publisher = {ASSOC Association for the Advancement of Artificial Intelligence}, address = {Palo Alto}, isbn = {978-1-57735-800-8}, pages = {6674 -- 6681}, year = {2018}, abstract = {Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps. In contrast to this, we propose to use a single deep neural network, that learns to detect and recognize text from natural images, in a semi-supervised way. SEE is a network that integrates and jointly learns a spatial transformer network, which can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We introduce the idea behind our novel approach and show its feasibility, by performing a range of experiments on standard benchmark datasets, where we achieve competitive results.}, language = {en} } @phdthesis{Batoulis2019, author = {Batoulis, Kimon}, title = {Sound integration of process and decision models}, doi = {10.25932/publishup-43738}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-437386}, school = {Universit{\"a}t Potsdam}, pages = {xviii, 155}, year = {2019}, abstract = {Business process management is an established technique for business organizations to manage and support their processes. Those processes are typically represented by graphical models designed with modeling languages, such as the Business Process Model and Notation (BPMN). Since process models do not only serve the purpose of documentation but are also a basis for implementation and automation of the processes, they have to satisfy certain correctness requirements. In this regard, the notion of soundness of workflow nets was developed, that can be applied to BPMN process models in order to verify their correctness. Because the original soundness criteria are very restrictive regarding the behavior of the model, different variants of the soundness notion have been developed for situations in which certain violations are not even harmful. All of those notions do only consider the control-flow structure of a process model, however. This poses a problem, taking into account the fact that with the recent release and the ongoing development of the Decision Model and Notation (DMN) standard, an increasing number of process models are complemented by respective decision models. DMN is a dedicated modeling language for decision logic and separates the concerns of process and decision logic into two different models, process and decision models respectively. Hence, this thesis is concerned with the development of decisionaware soundness notions, i.e., notions of soundness that build upon the original soundness ideas for process models, but additionally take into account complementary decision models. Similar to the various notions of workflow net soundness, this thesis investigates different notions of decision soundness that can be applied depending on the desired degree of restrictiveness. Since decision tables are a standardized means of DMN to represent decision logic, this thesis also puts special focus on decision tables, discussing how they can be translated into an unambiguous format and how their possible output values can be efficiently determined. Moreover, a prototypical implementation is described that supports checking a basic version of decision soundness. The decision soundness notions were also empirically evaluated on models from participants of an online course on process and decision modeling as well as from a process management project of a large insurance company. The evaluation demonstrates that violations of decision soundness indeed occur and can be detected with our approach.}, language = {en} }