@phdthesis{Niebler2019, author = {Niebler, Thomas}, title = {Extracting and Learning Semantics from Social Web Data}, doi = {10.25972/OPUS-17866}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-178666}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2019}, abstract = {Making machines understand natural language is a dream of mankind that existed since a very long time. Early attempts at programming machines to converse with humans in a supposedly intelligent way with humans relied on phrase lists and simple keyword matching. However, such approaches cannot provide semantically adequate answers, as they do not consider the specific meaning of the conversation. Thus, if we want to enable machines to actually understand language, we need to be able to access semantically relevant background knowledge. For this, it is possible to query so-called ontologies, which are large networks containing knowledge about real-world entities and their semantic relations. However, creating such ontologies is a tedious task, as often extensive expert knowledge is required. Thus, we need to find ways to automatically construct and update ontologies that fit human intuition of semantics and semantic relations. More specifically, we need to determine semantic entities and find relations between them. While this is usually done on large corpora of unstructured text, previous work has shown that we can at least facilitate the first issue of extracting entities by considering special data such as tagging data or human navigational paths. Here, we do not need to detect the actual semantic entities, as they are already provided because of the way those data are collected. Thus we can mainly focus on the problem of assessing the degree of semantic relatedness between tags or web pages. However, there exist several issues which need to be overcome, if we want to approximate human intuition of semantic relatedness. For this, it is necessary to represent words and concepts in a way that allows easy and highly precise semantic characterization. This also largely depends on the quality of data from which these representations are constructed. In this thesis, we extract semantic information from both tagging data created by users of social tagging systems and human navigation data in different semantic-driven social web systems. Our main goal is to construct high quality and robust vector representations of words which can the be used to measure the relatedness of semantic concepts. First, we show that navigation in the social media systems Wikipedia and BibSonomy is driven by a semantic component. After this, we discuss and extend methods to model the semantic information in tagging data as low-dimensional vectors. Furthermore, we show that tagging pragmatics influences different facets of tagging semantics. We then investigate the usefulness of human navigational paths in several different settings on Wikipedia and BibSonomy for measuring semantic relatedness. Finally, we propose a metric-learning based algorithm in adapt pre-trained word embeddings to datasets containing human judgment of semantic relatedness. This work contributes to the field of studying semantic relatedness between words by proposing methods to extract semantic relatedness from web navigation, learn highquality and low-dimensional word representations from tagging data, and to learn semantic relatedness from any kind of vector representation by exploiting human feedback. Applications first and foremest lie in ontology learning for the Semantic Web, but also semantic search or query expansion.}, subject = {Semantik}, language = {en} } @article{WienrichLatoschik2021, author = {Wienrich, Carolin and Latoschik, Marc Erich}, title = {eXtended Artificial Intelligence: New Prospects of Human-AI Interaction Research}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.686783}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260296}, year = {2021}, abstract = {Artificial Intelligence (AI) covers a broad spectrum of computational problems and use cases. Many of those implicate profound and sometimes intricate questions of how humans interact or should interact with AIs. Moreover, many users or future users do have abstract ideas of what AI is, significantly depending on the specific embodiment of AI applications. Human-centered-design approaches would suggest evaluating the impact of different embodiments on human perception of and interaction with AI. An approach that is difficult to realize due to the sheer complexity of application fields and embodiments in reality. However, here XR opens new possibilities to research human-AI interactions. The article's contribution is twofold: First, it provides a theoretical treatment and model of human-AI interaction based on an XR-AI continuum as a framework for and a perspective of different approaches of XR-AI combinations. It motivates XR-AI combinations as a method to learn about the effects of prospective human-AI interfaces and shows why the combination of XR and AI fruitfully contributes to a valid and systematic investigation of human-AI interactions and interfaces. Second, the article provides two exemplary experiments investigating the aforementioned approach for two distinct AI-systems. The first experiment reveals an interesting gender effect in human-robot interaction, while the second experiment reveals an Eliza effect of a recommender system. Here the article introduces two paradigmatic implementations of the proposed XR testbed for human-AI interactions and interfaces and shows how a valid and systematic investigation can be conducted. In sum, the article opens new perspectives on how XR benefits human-centered AI design and development.}, language = {en} } @article{LodaKrebsDanhofetal.2019, author = {Loda, Sophia and Krebs, Jonathan and Danhof, Sophia and Schreder, Martin and Solimando, Antonio G. and Strifler, Susanne and Rasche, Leo and Kort{\"u}m, Martin and Kerscher, Alexander and Knop, Stefan and Puppe, Frank and Einsele, Hermann and Bittrich, Max}, title = {Exploration of artificial intelligence use with ARIES in multiple myeloma research}, series = {Journal of Clinical Medicine}, volume = {8}, journal = {Journal of Clinical Medicine}, number = {7}, issn = {2077-0383}, doi = {10.3390/jcm8070999}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197231}, pages = {999}, year = {2019}, abstract = {Background: Natural language processing (NLP) is a powerful tool supporting the generation of Real-World Evidence (RWE). There is no NLP system that enables the extensive querying of parameters specific to multiple myeloma (MM) out of unstructured medical reports. We therefore created a MM-specific ontology to accelerate the information extraction (IE) out of unstructured text. Methods: Our MM ontology consists of extensive MM-specific and hierarchically structured attributes and values. We implemented "A Rule-based Information Extraction System" (ARIES) that uses this ontology. We evaluated ARIES on 200 randomly selected medical reports of patients diagnosed with MM. Results: Our system achieved a high F1-Score of 0.92 on the evaluation dataset with a precision of 0.87 and recall of 0.98. Conclusions: Our rule-based IE system enables the comprehensive querying of medical reports. The IE accelerates the extraction of data and enables clinicians to faster generate RWE on hematological issues. RWE helps clinicians to make decisions in an evidence-based manner. Our tool easily accelerates the integration of research evidence into everyday clinical practice.}, language = {en} } @article{AliMontenegro2016, author = {Ali, Qasim and Montenegro, Sergio}, title = {Explicit Model Following Distributed Control Scheme for Formation Flying of Mini UAVs}, series = {IEEE Access}, volume = {4}, journal = {IEEE Access}, number = {397-406}, doi = {10.1109/ACCESS.2016.2517203}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-146061}, year = {2016}, abstract = {A centralized heterogeneous formation flight position control scheme has been formulated using an explicit model following design, based on a Linear Quadratic Regulator Proportional Integral (LQR PI) controller. The leader quadcopter is a stable reference model with desired dynamics whose output is perfectly tracked by the two wingmen quadcopters. The leader itself is controlled through the pole placement control method with desired stability characteristics, while the two followers are controlled through a robust and adaptive LQR PI control method. Selected 3-D formation geometry and static stability are maintained under a number of possible perturbations. With this control scheme, formation geometry may also be switched to any arbitrary shape during flight, provided a suitable collision avoidance mechanism is incorporated. In case of communication loss between the leader and any of the followers, the other follower provides the data, received from the leader, to the affected follower. The stability of the closed-loop system has been analyzed using singular values. The proposed approach for the tightly coupled formation flight of mini unmanned aerial vehicles has been validated with the help of extensive simulations using MATLAB/Simulink, which provided promising results.}, language = {en} } @techreport{SertbasBuelbuelErgencFischer2022, type = {Working Paper}, author = {Sertbas B{\"u}lb{\"u}l, Nurefsan and Ergenc, Doganalp and Fischer, Mathias}, title = {Evaluating Dynamic Path Reconfiguration for Time Sensitive Networks}, series = {W{\"u}rzburg Workshop on Next-Generation Communication Networks (WueWoWas'22)}, journal = {W{\"u}rzburg Workshop on Next-Generation Communication Networks (WueWoWas'22)}, doi = {10.25972/OPUS-28074}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-280743}, pages = {5}, year = {2022}, abstract = {In time-sensitive networks (TSN) based on 802.1Qbv, i.e., the time-aware Shaper (TAS) protocol, precise transmission schedules and, paths are used to ensure end-to-end deterministic communication. Such resource reservations for data flows are usually established at the startup time of an application and remain untouched until the flow ends. There is no way to migrate existing flows easily to alternative paths without inducing additional delay or wasting resources. Therefore, some of the new flows cannot be embedded due to capacity limitations on certain links which leads to sub-optimal flow assignment. As future networks will need to support a large number of lowlatency flows, accommodating new flows at runtime and adapting existing flows accordingly becomes a challenging problem. In this extended abstract we summarize a previously published paper of us [1]. We combine software-defined networking (SDN), which provides better control of network flows, with TSN to be able to seamlessly migrate time-sensitive flows. For that, we formulate an optimization problem and propose different dynamic path configuration strategies under deterministic communication requirements. Our simulation results indicate that regularly reconfiguring the flow assignments can improve the latency of time-sensitive flows and can increase the number of flows embedded in the network around 4\% in worst-case scenarios while still satisfying individual flow deadlines.}, subject = {Datennetz}, language = {en} } @article{GehrkeBalbachRauchetal.2019, author = {Gehrke, Alexander and Balbach, Nico and Rauch, Yong-Mi and Degkwitz, Andreas and Puppe, Frank}, title = {Erkennung von handschriftlichen Unterstreichungen in Alten Drucken}, series = {Bibliothek Forschung und Praxis}, volume = {43}, journal = {Bibliothek Forschung und Praxis}, number = {3}, issn = {1865-7648}, doi = {10.1515/bfp-2019-2083}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193377}, pages = {447 -- 452}, year = {2019}, abstract = {Die Erkennung handschriftlicher Artefakte wie Unterstreichungen in Buchdrucken erm{\"o}glicht R{\"u}ckschl{\"u}sse auf das Rezeptionsverhalten und die Provenienzgeschichte und wird auch f{\"u}r eine OCR ben{\"o}tigt. Dabei soll zwischen handschriftlichen Unterstreichungen und waagerechten Linien im Druck (z. B. Trennlinien usw.) unterschieden werden, da letztere nicht ausgezeichnet werden sollen. Im Beitrag wird ein Ansatz basierend auf einem auf Unterstreichungen trainierten Neuronalen Netz gem{\"a}ß der U-Net Architektur vorgestellt, dessen Ergebnisse in einem zweiten Schritt mit heuristischen Regeln nachbearbeitet werden. Die Evaluationen zeigen, dass Unterstreichungen sehr gut erkannt werden, wenn bei der Binarisierung der Scans nicht zu viele Pixel der Unterstreichung wegen geringem Kontrast verloren gehen. Zuk{\"u}nftig sollen die Worte oberhalb der Unterstreichung mit OCR transkribiert werden und auch andere Artefakte wie handschriftliche Notizen in alten Drucken erkannt werden.}, language = {de} } @article{RodriguesWeissHewigetal.2021, author = {Rodrigues, Johannes and Weiß, Martin and Hewig, Johannes and Allen, John J. B.}, title = {EPOS: EEG Processing Open-Source Scripts}, series = {Frontiers in Neuroscience}, volume = {15}, journal = {Frontiers in Neuroscience}, issn = {1662-453X}, doi = {10.3389/fnins.2021.660449}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-240221}, year = {2021}, abstract = {Background: Since the replication crisis, standardization has become even more important in psychological science and neuroscience. As a result, many methods are being reconsidered, and researchers' degrees of freedom in these methods are being discussed as a potential source of inconsistencies across studies. New Method: With the aim of addressing these subjectivity issues, we have been working on a tutorial-like EEG (pre-)processing pipeline to achieve an automated method based on the semi-automated analysis proposed by Delorme and Makeig. Results: Two scripts are presented and explained step-by-step to perform basic, informed ERP and frequency-domain analyses, including data export to statistical programs and visual representations of the data. The open-source software EEGlab in MATLAB is used as the data handling platform, but scripts based on code provided by Mike Cohen (2014) are also included. Comparison with existing methods: This accompanying tutorial-like article explains and shows how the processing of our automated pipeline affects the data and addresses, especially beginners in EEG-analysis, as other (pre)-processing chains are mostly targeting rather informed users in specialized areas or only parts of a complete procedure. In this context, we compared our pipeline with a selection of existing approaches. Conclusion: The need for standardization and replication is evident, yet it is equally important to control the plausibility of the suggested solution by data exploration. Here, we provide the community with a tool to enhance the understanding and capability of EEG-analysis. We aim to contribute to comprehensive and reliable analyses for neuro-scientific research.}, language = {en} } @article{OberdoerferHeidrichBirnstieletal.2021, author = {Oberd{\"o}rfer, Sebastian and Heidrich, David and Birnstiel, Sandra and Latoschik, Marc Erich}, title = {Enchanted by Your Surrounding? Measuring the Effects of Immersion and Design of Virtual Environments on Decision-Making}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.679277}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-260101}, pages = {679277}, year = {2021}, abstract = {Impaired decision-making leads to the inability to distinguish between advantageous and disadvantageous choices. The impairment of a person's decision-making is a common goal of gambling games. Given the recent trend of gambling using immersive Virtual Reality it is crucial to investigate the effects of both immersion and the virtual environment (VE) on decision-making. In a novel user study, we measured decision-making using three virtual versions of the Iowa Gambling Task (IGT). The versions differed with regard to the degree of immersion and design of the virtual environment. While emotions affect decision-making, we further measured the positive and negative affect of participants. A higher visual angle on a stimulus leads to an increased emotional response. Thus, we kept the visual angle on the Iowa Gambling Task the same between our conditions. Our results revealed no significant impact of immersion or the VE on the IGT. We further found no significant difference between the conditions with regard to positive and negative affect. This suggests that neither the medium used nor the design of the VE causes an impairment of decision-making. However, in combination with a recent study, we provide first evidence that a higher visual angle on the IGT leads to an effect of impairment.}, language = {en} } @techreport{GrossmannHomeyer2023, type = {Working Paper}, author = {Großmann, Marcel and Homeyer, Tobias}, title = {Emulation of Multipath Transmissions in P4 Networks with Kathar{\´a}}, series = {KuVS Fachgespr{\"a}ch - W{\"u}rzburg Workshop on Modeling, Analysis and Simulation of Next-Generation Communication Networks 2023 (WueWoWAS'23)}, journal = {KuVS Fachgespr{\"a}ch - W{\"u}rzburg Workshop on Modeling, Analysis and Simulation of Next-Generation Communication Networks 2023 (WueWoWAS'23)}, doi = {10.25972/OPUS-32209}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-322095}, pages = {4}, year = {2023}, abstract = {Packets sent over a network can either get lost or reach their destination. Protocols like TCP try to solve this problem by resending the lost packets. However, retransmissions consume a lot of time and are cumbersome for the transmission of critical data. Multipath solutions are quite common to address this reliability issue and are available on almost every layer of the ISO/OSI model. We propose a solution based on a P4 network to duplicate packets in order to send them to their destination via multiple routes. The last network hop ensures that only a single copy of the traffic is further forwarded to its destination by adopting a concept similar to Bloom filters. Besides, if fast delivery is requested we provide a P4 prototype, which randomly forwards the packets over different transmission paths. For reproducibility, we implement our approach in a container-based network emulation system called Kathar{\´a}.}, language = {en} } @unpublished{Nassourou2010, author = {Nassourou, Mohamadou}, title = {Empirical Study on Screen Scraping Web Service Creation: Case of Rhein-Main-Verkehrsverbund (RMV)}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-49396}, year = {2010}, abstract = {Internet is the biggest database that science and technology have ever produced. The world wide web is a large repository of information that cannot be used for automation by many applications due to its limited target audience. One of the solutions to the automation problem is to develop wrappers. Wrapping is a process whereby unstructured extracted information is transformed into a more structured one such as XML, which could be provided as webservice to other applications. A web service is a web page whose content is well structured so that a computer program can consume it automatically. This paper describes steps involved in constructing wrappers manually in order to automatically generate web services.}, subject = {HTML}, language = {en} }