@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{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} } @phdthesis{Wolz2003, author = {Wolz, Frank}, title = {Ein generisches Konzept zur Modellierung und Bewertung feldprogrammierbarer Architekturen}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-7944}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2003}, abstract = {Gegenstand der Arbeit stellt eine erstmalig unternommene, architektur{\"u}bergreifende Studie {\"u}ber feldprogrammierbare Logikbausteine zur Implementierung synchroner Schaltkreise dar. Zun{\"a}chst wird ein Modell f{\"u}r allgemeine feldprogrammiebare Architekturen basierend auf periodischen Graphen definiert. Schließlich werden Bewertungsmaße f{\"u}r Architekturen und Schaltkreislayouts angegeben zur Charakterisierung struktureller Eigenschaften hinsichtlich des Verhaltens in Chipfl{\"a}chenverbrauch und Signalverz{\"o}gerung. Ferner wird ein generisches Layout-Werkzeug entwickelt, das f{\"u}r beliebige Architekturen und Schaltkreise Implementierungen berechnen und bewerten kann. Abschließend werden neun ressourcenminimalistische Architekturen mit Maschen- und mit Inselstruktur einander gegen{\"u}bergestellt.}, subject = {Gay-Array-Bauelement}, language = {de} } @phdthesis{Menth2004, author = {Menth, Michael}, title = {Efficient admission control and routing for resilient communication networks}, doi = {10.25972/OPUS-846}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-9949}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2004}, abstract = {This work is subdivided into two main areas: resilient admission control and resilient routing. The work gives an overview of the state of the art of quality of service mechanisms in communication networks and proposes a categorization of admission control (AC) methods. These approaches are investigated regarding performance, more precisely, regarding the potential resource utilization by dimensioning the capacity for a network with a given topology, traffic matrix, and a required flow blocking probability. In case of a failure, the affected traffic is rerouted over backup paths which increases the traffic rate on the respective links. To guarantee the effectiveness of admission control also in failure scenarios, the increased traffic rate must be taken into account for capacity dimensioning and leads to resilient AC. Capacity dimensioning is not feasible for existing networks with already given link capacities. For the application of resilient NAC in this case, the size of distributed AC budgets must be adapted according to the traffic matrix in such a way that the maximum blocking probability for all flows is minimized and that the capacity of all links is not exceeded by the admissible traffic rate in any failure scenario. Several algorithms for the solution of that problem are presented and compared regarding their efficiency and fairness. A prototype for resilient AC was implemented in the laboratories of Siemens AG in Munich within the scope of the project KING. Resilience requires additional capacity on the backup paths for failure scenarios. The amount of this backup capacity depends on the routing and can be minimized by routing optimization. New protection switching mechanisms are presented that deviate the traffic quickly around outage locations. They are simple and can be implemented, e.g, by MPLS technology. The Self-Protecting Multi-Path (SPM) is a multi-path consisting of disjoint partial paths. The traffic is distributed over all faultless partial paths according to an optimized load balancing function both in the working case and in failure scenarios. Performance studies show that the network topology and the traffic matrix also influence the amount of required backup capacity significantly. The example of the COST-239 network illustrates that conventional shortest path routing may need 50\% more capacity than the optimized SPM if all single link and node failures are protected.}, subject = {Kommunikation}, language = {en} } @article{MadeiraGromerLatoschiketal.2021, author = {Madeira, Octavia and Gromer, Daniel and Latoschik, Marc Erich and Pauli, Paul}, title = {Effects of Acrophobic Fear and Trait Anxiety on Human Behavior in a Virtual Elevated Plus-Maze}, series = {Frontiers in Virtual Reality}, volume = {2}, journal = {Frontiers in Virtual Reality}, doi = {10.3389/frvir.2021.635048}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-258709}, year = {2021}, abstract = {The Elevated Plus-Maze (EPM) is a well-established apparatus to measure anxiety in rodents, i.e., animals exhibiting an increased relative time spent in the closed vs. the open arms are considered anxious. To examine whether such anxiety-modulated behaviors are conserved in humans, we re-translated this paradigm to a human setting using virtual reality in a Cave Automatic Virtual Environment (CAVE) system. In two studies, we examined whether the EPM exploration behavior of humans is modulated by their trait anxiety and also assessed the individuals' levels of acrophobia (fear of height), claustrophobia (fear of confined spaces), sensation seeking, and the reported anxiety when on the maze. First, we constructed an exact virtual copy of the animal EPM adjusted to human proportions. In analogy to animal EPM studies, participants (N = 30) freely explored the EPM for 5 min. In the second study (N = 61), we redesigned the EPM to make it more human-adapted and to differentiate influences of trait anxiety and acrophobia by introducing various floor textures and lower walls of closed arms to the height of standard handrails. In the first experiment, hierarchical regression analyses of exploration behavior revealed the expected association between open arm avoidance and Trait Anxiety, an even stronger association with acrophobic fear. In the second study, results revealed that acrophobia was associated with avoidance of open arms with mesh-floor texture, whereas for trait anxiety, claustrophobia, and sensation seeking, no effect was detected. Also, subjects' fear rating was moderated by all psychometrics but trait anxiety. In sum, both studies consistently indicate that humans show no general open arm avoidance analogous to rodents and that human EPM behavior is modulated strongest by acrophobic fear, whereas trait anxiety plays a subordinate role. Thus, we conclude that the criteria for cross-species validity are met insufficiently in this case. Despite the exploratory nature, our studies provide in-depth insights into human exploration behavior on the virtual EPM.}, language = {en} } @techreport{OdhahGrassKraemer2022, type = {Working Paper}, author = {Odhah, Najib and Grass, Eckhard and Kraemer, Rolf}, title = {Effective Rate of URLLC with Short Block-Length Information Theory}, 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-28085}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-280859}, pages = {4}, year = {2022}, abstract = {Shannon channel capacity estimation, based on large packet length is used in traditional Radio Resource Management (RRM) optimization. This is good for the normal transmission of data in a wired or wireless system. For industrial automation and control, rather short packages are used due to the short-latency requirements. Using Shannon's formula leads in this case to inaccurate RRM solutions, thus another formula should be used to optimize radio resources in short block-length packet transmission, which is the basic of Ultra-Reliable Low-Latency Communications (URLLCs). The stringent requirement of delay Quality of Service (QoS) for URLLCs requires a link-level channel model rather than a physical level channel model. After finding the basic and accurate formula of the achievable rate of short block-length packet transmission, the RRM optimization problem can be accurately formulated and solved under the new constraints of URLLCs. In this short paper, the current mathematical models, which are used in formulating the effective transmission rate of URLLCs, will be briefly explained. Then, using this rate in RRM for URLLC will be discussed.}, subject = {Datennetz}, language = {en} } @phdthesis{Kaussner2003, author = {Kaußner, Armin}, title = {Dynamische Szenerien in der Fahrsimulation}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-8286}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2003}, abstract = {In der Arbeit wird ein neues Konzept f{\"u}r Fahrsimulator-Datenbasen vorgestellt. Der Anwender entwirft eine auf seine Fragestellung zugeschnittene Datenbasis mithilfe einer einfachen Skriptsprache. Das Straßennetzwerk wird auf einer topologischen Ebene rep{\"a}sentiert. In jedem Simulationsschritt wird hieraus im Sichtbarkeitsbereich des Fahrers die geometrische Rep{\"a}sentation berechnet. Die f{\"u}r den Fahrer unsichtbaren Teile des Straßenetzwerks k{\"o}nnen w{\"a}hrend der Simulation ver{\"a}ndert werden. Diese Ver{\"a}nderungen k{\"o}nnen von der Route des Fahrers oder von den in der Simulation erhobenen Messerten abh{\"a}ngen. Zudem kann der Anwender das Straßennetzwerk interaktiv ver{\"a}ndern. Das vorgestellte Konzept bietet zahlreiche M{\"o}glichkeiten zur Erzeugung reproduzierbarer Szenarien f{\"u}r Experimente in Fahrsimulatoren.}, subject = {Straßenverkehr}, language = {de} } @article{DumicBjeloperaNuechter2021, author = {Dumic, Emil and Bjelopera, Anamaria and N{\"u}chter, Andreas}, title = {Dynamic point cloud compression based on projections, surface reconstruction and video compression}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {1}, issn = {1424-8220}, doi = {10.3390/s22010197}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-252231}, year = {2021}, abstract = {In this paper we will present a new dynamic point cloud compression based on different projection types and bit depth, combined with the surface reconstruction algorithm and video compression for obtained geometry and texture maps. Texture maps have been compressed after creating Voronoi diagrams. Used video compression is specific for geometry (FFV1) and texture (H.265/HEVC). Decompressed point clouds are reconstructed using a Poisson surface reconstruction algorithm. Comparison with the original point clouds was performed using point-to-point and point-to-plane measures. Comprehensive experiments show better performance for some projection maps: cylindrical, Miller and Mercator projections.}, language = {en} } @article{BuchinBuchinByrkaetal.2012, author = {Buchin, Kevin and Buchin, Maike and Byrka, Jaroslaw and N{\"o}llenburg, Martin and Okamoto, Yoshio and Silveira, Rodrigo I. and Wolff, Alexander}, title = {Drawing (Complete) Binary Tanglegrams}, series = {Algorithmica}, volume = {62}, journal = {Algorithmica}, doi = {10.1007/s00453-010-9456-3}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-124622}, pages = {309-332}, year = {2012}, abstract = {A binary tanglegram is a drawing of a pair of rooted binary trees whose leaf sets are in one-to-one correspondence; matching leaves are connected by inter-tree edges. For applications, for example, in phylogenetics, it is essential that both trees are drawn without edge crossings and that the inter-tree edges have as few crossings as possible. It is known that finding a tanglegram with the minimum number of crossings is NP-hard and that the problem is fixed-parameter tractable with respect to that number. We prove that under the Unique Games Conjecture there is no constant-factor approximation for binary trees. We show that the problem is NP-hard even if both trees are complete binary trees. For this case we give an O(n 3)-time 2-approximation and a new, simple fixed-parameter algorithm. We show that the maximization version of the dual problem for binary trees can be reduced to a version of MaxCut for which the algorithm of Goemans and Williamson yields a 0.878-approximation.}, language = {en} } @phdthesis{Houshiar2017, author = {Houshiar, Hamidreza}, title = {Documentation and mapping with 3D point cloud processing}, isbn = {978-3-945459-14-0}, doi = {10.25972/OPUS-14449}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-144493}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2017}, abstract = {3D point clouds are a de facto standard for 3D documentation and modelling. The advances in laser scanning technology broadens the usability and access to 3D measurement systems. 3D point clouds are used in many disciplines such as robotics, 3D modelling, archeology and surveying. Scanners are able to acquire up to a million of points per second to represent the environment with a dense point cloud. This represents the captured environment with a very high degree of detail. The combination of laser scanning technology with photography adds color information to the point clouds. Thus the environment is represented more realistically. Full 3D models of environments, without any occlusion, require multiple scans. Merging point clouds is a challenging process. This thesis presents methods for point cloud registration based on the panorama images generated from the scans. Image representation of point clouds introduces 2D image processing methods to 3D point clouds. Several projection methods for the generation of panorama maps of point clouds are presented in this thesis. Additionally, methods for point cloud reduction and compression based on the panorama maps are proposed. Due to the large amounts of data generated from the 3D measurement systems these methods are necessary to improve the point cloud processing, transmission and archiving. This thesis introduces point cloud processing methods as a novel framework for the digitisation of archeological excavations. The framework replaces the conventional documentation methods for excavation sites. It employs point clouds for the generation of the digital documentation of an excavation with the help of an archeologist on-site. The 3D point cloud is used not only for data representation but also for analysis and knowledge generation. Finally, this thesis presents an autonomous indoor mobile mapping system. The mapping system focuses on the sensor placement planning method. Capturing a complete environment requires several scans. The sensor placement planning method solves for the minimum required scans to digitise large environments. Combining this method with a navigation system on a mobile robot platform enables it to acquire data fully autonomously. This thesis introduces a novel hole detection method for point clouds to detect obscured parts of a captured environment. The sensor placement planning method selects the next scan position with the most coverage of the obscured environment. This reduces the required number of scans. The navigation system on the robot platform consist of path planning, path following and obstacle avoidance. This guarantees the safe navigation of the mobile robot platform between the scan positions. The sensor placement planning method is designed as a stand alone process that could be used with a mobile robot platform for autonomous mapping of an environment or as an assistant tool for the surveyor on scanning projects.}, subject = {3D Punktwolke}, language = {en} } @phdthesis{Binder2006, author = {Binder, Andreas}, title = {Die stochastische Wissenschaft und zwei Teilsysteme eines Web-basierten Informations- und Anwendungssystems zu ihrer Etablierung}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-26146}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2006}, abstract = {Das stochastische Denken, die Bernoullische Stochastik und dessen informationstechnologische Umsetzung, namens Stochastikon stellen die Grundlage f{\"u}r das Verst{\"a}ndnis und die erfolgreiche Nutzung einer stochastischen Wissenschaft dar. Im Rahmen dieser Arbeit erfolgt eine Kl{\"a}rung des Begriffs des stochastischen Denkens, eine anschauliche Darstellung der von Elart von Collani entwickelten Bernoullischen Stochastik und eine Beschreibung von Stochastikon. Dabei werden sowohl das Gesamtkonzept von Stochastikon, sowie die Ziele, Aufgaben und die Realisierung der beiden Teilsysteme namens Mentor und Encyclopedia vorgestellt. Das stochastische Denken erlaubt eine realit{\"a}tsnahe Sichtweise der Dinge, d.h. eine Sichtweise, die mit den menschlichen Beobachtungen und Erfahrungen im Einklang steht und somit die Unsicherheit {\"u}ber zuk{\"u}nftige Entwicklungen ber{\"u}cksichtigt. Der in diesem Kontext verwendete Begriff der Unsicherheit bezieht sich ausschließlich auf zuk{\"u}nftige Entwicklungen und {\"a}ußert sich in Variabilit{\"a}t. Quellen der Unsicherheit sind einerseits die menschliche Ignoranz und andererseits der Zufall. Unter Ignoranz wird hierbei die Unwissenheit des Menschen {\"u}ber die unbekannten, aber feststehenden Fakten verstanden, die die Anfangsbedingungen der zuk{\"u}nftigen Entwicklung repr{\"a}sentieren. Die Bernoullische Stochastik liefert ein Regelwerk und erm{\"o}glicht die Entwicklung eines quantitativen Modells zur Beschreibung der Unsicherheit und expliziter Einbeziehung der beiden Quellen Ignoranz und Zufall. Das Modell tr{\"a}gt den Namen Bernoulli-Raum und bildet die Grundlage f{\"u}r die Herleitung quantitativer Verfahren, um zuverl{\"a}ssige und genaue Aussagen sowohl {\"u}ber die nicht-existente zuf{\"a}llige Zukunft (Vorhersageverfahren), als auch {\"u}ber die unbekannte feststehende Vergangenheit (Messverfahren). Das Softwaresystem Stochastikon implementiert die Bernoullische Stochastik in Form einer Reihe autarker, miteinander kommunizierender Teilsysteme. Ziel des Teilsystems Encyclopedia ist die Bereitstellung und Bewertung stochastischen Wissens. Das Teilsystem Mentor dient der Unterst{\"u}tzung des Anwenders bei der Probleml{\"o}sungsfindung durch Identifikation eines richtigen Modells bzw. eines korrekten Bernoulli-Raums. Der L{\"o}sungsfindungsprozess selber enth{\"a}lt keinerlei Unsicherheit. Die ganze Unsicherheit steckt in der L{\"o}sung, d.h. im Bernoulli-Raum, der explizit die vorhandene Unwissenheit (Ignoranz) und den vorliegenden Zufall abdeckend enth{\"a}lt.}, subject = {Stochastik}, language = {de} } @misc{Kaempgen2009, type = {Master Thesis}, author = {Kaempgen, Benedikt}, title = {Deskriptives Data-Mining f{\"u}r Entscheidungstr{\"a}ger: Eine Mehrfachfallstudie}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-46343}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2009}, abstract = {Das Potenzial der Wissensentdeckung in Daten wird h{\"a}ufig nicht ausgenutzt, was haupts{\"a}chlich auf Barrieren zwischen dem Entwicklerteam und dem Endnutzer des Data-Mining zur{\"u}ckzuf{\"u}hren ist. In dieser Arbeit wird ein transparenter Ansatz zum Beschreiben und Erkl{\"a}ren von Daten f{\"u}r Entscheidungstr{\"a}ger vorgestellt. In Entscheidungstr{\"a}ger-zentrierten Aufgaben werden die Projektanforderungen definiert und die Ergebnisse zu einer Geschichte zusammengestellt. Eine Anforderung besteht dabei aus einem tabellarischen Bericht und ggf. Mustern in seinem Inhalt, jeweils verst{\"a}ndlich f{\"u}r einen Entscheidungstr{\"a}ger. Die technischen Aufgaben bestehen aus einer Datenpr{\"u}fung, der Integration der Daten in einem Data-Warehouse sowie dem Generieren von Berichten und dem Entdecken von Mustern wie in den Anforderungen beschrieben. Mehrere Data-Mining-Projekte k{\"o}nnen durch Wissensmanagement sowie eine geeignete Infrastruktur voneinander profitieren. Der Ansatz wurde in zwei Projekten unter Verwendung von ausschließlich Open-Source-Software angewendet.}, subject = {Data Mining}, language = {de} } @phdthesis{Klein2014, author = {Klein, Dominik Werner}, title = {Design and Evaluation of Components for Future Internet Architectures}, issn = {1432-8801}, doi = {10.25972/OPUS-9313}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-93134}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2014}, abstract = {Die derzeitige Internetarchitektur wurde nicht in einem geplanten Prozess konzipiert und entwickelt, sondern hat vielmehr eine evolutionsartige Entwicklung hinter sich. Ausl{\"o}ser f{\"u}r die jeweiligen Evolutionsschritte waren dabei meist aufstrebende Anwendungen, welche neue Anforderungen an die zugrundeliegende Netzarchitektur gestellt haben. Um diese Anforderungen zu erf{\"u}llen, wurden h{\"a}ufig neuartige Dienste oder Protokolle spezifiziert und in die bestehende Architektur integriert. Dieser Prozess ist jedoch meist mit hohem Aufwand verbunden und daher sehr tr{\"a}ge, was die Entwicklung und Verbreitung innovativer Dienste beeintr{\"a}chtigt. Derzeitig diskutierte Konzepte wie Software-Defined Networking (SDN) oder Netzvirtualisierung (NV) werden als eine M{\"o}glichkeit angesehen, die Altlasten der bestehenden Internetarchitektur zu l{\"o}sen. Beiden Konzepten gemein ist die Idee, logische Netze {\"u}ber dem physikalischen Substrat zu betreiben. Diese logischen Netze sind hochdynamisch und k{\"o}nnen so flexibel an die Anforderungen der jeweiligen Anwendungen angepasst werden. Insbesondere erlaubt das Konzept der Virtualisierung intelligentere Netzknoten, was innovative neue Anwendungsf{\"a}lle erm{\"o}glicht. Ein h{\"a}ufig in diesem Zusammenhang diskutierter Anwendungsfall ist die Mobilit{\"a}t sowohl von Endger{\"a}ten als auch von Diensten an sich. Die Mobilit{\"a}t der Dienste wird hierbei ausgenutzt, um die Zugriffsverz{\"o}gerung oder die belegten Ressourcen im Netz zu reduzieren, indem die Dienste zum Beispiel in f{\"u}r den Nutzer geographisch nahe Datenzentren migriert werden. Neben den reinen Mechanismen bez{\"u}glich Dienst- und Endger{\"a}temobilit{\"a}t sind in diesem Zusammenhang auch geeignete {\"U}berwachungsl{\"o}sungen relevant, welche die vom Nutzer wahrgenommene Dienstg{\"u}te bewerten k{\"o}nnen. Diese L{\"o}sungen liefern wichtige Entscheidungshilfen f{\"u}r die Migration oder {\"u}berwachen m{\"o}gliche Effekte der Migration auf die erfahrene Dienstg{\"u}te beim Nutzer. Im Falle von Video Streaming erm{\"o}glicht ein solcher Anwendungsfall die flexible Anpassung der Streaming Topologie f{\"u}r mobile Nutzer, um so die Videoqualit{\"a}t unabh{\"a}ngig vom Zugangsnetz aufrechterhalten zu k{\"o}nnen. Im Rahmen dieser Doktorarbeit wird der beschriebene Anwendungsfall am Beispiel einer Video Streaming Anwendung n{\"a}her analysiert und auftretende Herausforderungen werden diskutiert. Des Weiteren werden L{\"o}sungsans{\"a}tze vorgestellt und bez{\"u}glich ihrer Effizienz ausgewertet. Im Detail besch{\"a}ftigt sich die Arbeit mit der Leistungsanalyse von Mechanismen f{\"u}r die Dienstmobilit{\"a}t und entwickelt eine Architektur zur Optimierung der Dienstmobilit{\"a}t. Im Bereich Endger{\"a}temobilit{\"a}t werden Verbesserungen entwickelt, welche die Latenz zwischen Endger{\"a}t und Dienst reduzieren oder die Konnektivit{\"a}t unabh{\"a}ngig vom Zugangsnetz gew{\"a}hrleisten. Im letzten Teilbereich wird eine L{\"o}sung zur {\"U}berwachung der Videoqualit{\"a}t im Netz entwickelt und bez{\"u}glich ihrer Genauigkeit analysiert.}, subject = {Leistungsbewertung}, language = {en} } @article{SteiningerKobsDavidsonetal.2021, author = {Steininger, Michael and Kobs, Konstantin and Davidson, Padraig and Krause, Anna and Hotho, Andreas}, title = {Density-based weighting for imbalanced regression}, series = {Machine Learning}, volume = {110}, journal = {Machine Learning}, number = {8}, issn = {1573-0565}, doi = {10.1007/s10994-021-06023-5}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-269177}, pages = {2187-2211}, year = {2021}, abstract = {In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point's influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.}, language = {en} }