@unpublished{Nassourou2011,
  author    = {Nassourou, Mohamadou},
  title     = {Using Machine Learning Algorithms for Categorizing Quranic Chaptersby Major Phases of Prophet Mohammad's Messengership},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-66862},
  year      = {2011},
  abstract  = {This paper discusses the categorization of Quranic chapters by major phases of Prophet Mohammad's messengership using machine learning algorithms. First, the chapters were categorized by places of revelation using Support Vector Machine and na{\"i}ve Bayesian classifiers separately, and their results were compared to each other, as well as to the existing traditional Islamic and western orientalists classifications. The chapters were categorized into Meccan (revealed in Mecca) and Medinan (revealed in Medina). After that, chapters of each category were clustered using a kind of fuzzy-single linkage clustering approach, in order to correspond to the major phases of Prophet Mohammad's life. The major phases of the Prophet's life were manually derived from the Quranic text, as well as from the secondary Islamic literature e.g hadiths, exegesis. Previous studies on computing the places of revelation of Quranic chapters relied heavily on features extracted from existing background knowledge of the chapters. For instance, it is known that Meccan chapters contain mostly verses about faith and related problems, while Medinan ones encompass verses dealing with social issues, battles…etc. These features are by themselves insufficient as a basis for assigning the chapters to their respective places of revelation. In fact, there are exceptions, since some chapters do contain both Meccan and Medinan features. In this study, features of each category were automatically created from very few chapters, whose places of revelation have been determined through identification of historical facts and events such as battles, migration to Medina…etc. Chapters having unanimously agreed places of revelation were used as the initial training set, while the remaining chapters formed the testing set. The classification process was made recursive by regularly augmenting the training set with correctly classified chapters, in order to classify the whole testing set. Each chapter was preprocessed by removing unimportant words, stemming, and representation with vector space model. The result of this study shows that, the two classifiers have produced useable results, with an outperformance of the support vector machine classifier. This study indicates that, the proposed methodology yields encouraging results for arranging Quranic chapters by phases of Prophet Mohammad's messengership.},
  subject      = {Koran},
  language  = {en}
}
@phdthesis{Winkler2015,
  author    = {Winkler, Marco},
  title     = {On the Role of Triadic Substructures in Complex Networks},
  publisher = {epubli GmbH},
  address   = {Berlin},
  isbn      = {978-3-7375-5654-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-116022},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2015},
  abstract  = {In the course of the growth of the Internet and due to increasing availability of data, over the last two decades, the field of network science has established itself as an own area of research. With quantitative scientists from computer science, mathematics, and physics working on datasets from biology, economics, sociology, political sciences, and many others, network science serves as a paradigm for interdisciplinary research. One of the major goals in network science is to unravel the relationship between topological graph structure and a network's function. As evidence suggests, systems from the same fields, i.e. with similar function, tend to exhibit similar structure. However, it is still vague whether a similar graph structure automatically implies likewise function. This dissertation aims at helping to bridge this gap, while particularly focusing on the role of triadic structures. After a general introduction to the main concepts of network science, existing work devoted to the relevance of triadic substructures is reviewed. A major challenge in modeling triadic structure is the fact that not all three-node subgraphs can be specified independently of each other, as pairs of nodes may participate in multiple of those triadic subgraphs. In order to overcome this obstacle, we suggest a novel class of generative network models based on so called Steiner triple systems. The latter are partitions of a graph's vertices into pair-disjoint triples (Steiner triples). Thus, the configurations on Steiner triples can be specified independently of each other without overdetermining the network's link structure. Subsequently, we investigate the most basic realization of this new class of models. We call it the triadic random graph model (TRGM). The TRGM is parametrized by a probability distribution over all possible triadic subgraph patterns. In order to generate a network instantiation of the model, for all Steiner triples in the system, a pattern is drawn from the distribution and adjusted randomly on the Steiner triple. We calculate the degree distribution of the TRGM analytically and find it to be similar to a Poissonian distribution. Furthermore, it is shown that TRGMs possess non-trivial triadic structure. We discover inevitable correlations in the abundance of certain triadic subgraph patterns which should be taken into account when attributing functional relevance to particular motifs - patterns which occur significantly more frequently than expected at random. Beyond, the strong impact of the probability distributions on the Steiner triples on the occurrence of triadic subgraphs over the whole network is demonstrated. This interdependence allows us to design ensembles of networks with predefined triadic substructure. Hence, TRGMs help to overcome the lack of generative models needed for assessing the relevance of triadic structure. We further investigate whether motifs occur homogeneously or heterogeneously distributed over a graph. Therefore, we study triadic subgraph structures in each node's neighborhood individually. In order to quantitatively measure structure from an individual node's perspective, we introduce an algorithm for node-specific pattern mining for both directed unsigned, and undirected signed networks. Analyzing real-world datasets, we find that there are networks in which motifs are distributed highly heterogeneously, bound to the proximity of only very few nodes. Moreover, we observe indication for the potential sensitivity of biological systems to a targeted removal of these critical vertices. In addition, we study whole graphs with respect to the homogeneity and homophily of their node-specific triadic structure. The former describes the similarity of subgraph distributions in the neighborhoods of individual vertices. The latter quantifies whether connected vertices are structurally more similar than non-connected ones. We discover these features to be characteristic for the networks' origins. Moreover, clustering the vertices of graphs regarding their triadic structure, we investigate structural groups in the neural network of C. elegans, the international airport-connection network, and the global network of diplomatic sentiments between countries. For the latter we find evidence for the instability of triangles considered socially unbalanced according to sociological theories. Finally, we utilize our TRGM to explore ensembles of networks with similar triadic substructure in terms of the evolution of dynamical processes acting on their nodes. Focusing on oscillators, coupled along the graphs' edges, we observe that certain triad motifs impose a clear signature on the systems' dynamics, even when embedded in a larger network structure.},
  subject      = {Netzwerk},
  language  = {en}
}
@phdthesis{Krenzer2023,
  author    = {Krenzer, Adrian},
  title     = {Machine learning to support physicians in endoscopic examinations with a focus on automatic polyp detection in images and videos},
  doi       = {10.25972/OPUS-31911},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-319119},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {Deep learning enables enormous progress in many computer vision-related tasks. Artificial Intel- ligence (AI) steadily yields new state-of-the-art results in the field of detection and classification. Thereby AI performance equals or exceeds human performance. Those achievements impacted many domains, including medical applications. One particular field of medical applications is gastroenterology. In gastroenterology, machine learning algorithms are used to assist examiners during interventions. One of the most critical concerns for gastroenterologists is the development of Colorectal Cancer (CRC), which is one of the leading causes of cancer-related deaths worldwide. Detecting polyps in screening colonoscopies is the essential procedure to prevent CRC. Thereby, the gastroenterologist uses an endoscope to screen the whole colon to find polyps during a colonoscopy. Polyps are mucosal growths that can vary in severity. This thesis supports gastroenterologists in their examinations with automated detection and clas- sification systems for polyps. The main contribution is a real-time polyp detection system. This system is ready to be installed in any gastroenterology practice worldwide using open-source soft- ware. The system achieves state-of-the-art detection results and is currently evaluated in a clinical trial in four different centers in Germany. The thesis presents two additional key contributions: One is a polyp detection system with ex- tended vision tested in an animal trial. Polyps often hide behind folds or in uninvestigated areas. Therefore, the polyp detection system with extended vision uses an endoscope assisted by two additional cameras to see behind those folds. If a polyp is detected, the endoscopist receives a vi- sual signal. While the detection system handles the additional two camera inputs, the endoscopist focuses on the main camera as usual. The second one are two polyp classification models, one for the classification based on shape (Paris) and the other on surface and texture (NBI International Colorectal Endoscopic (NICE) classification). Both classifications help the endoscopist with the treatment of and the decisions about the detected polyp. The key algorithms of the thesis achieve state-of-the-art performance. Outstandingly, the polyp detection system tested on a highly demanding video data set shows an F1 score of 90.25 \% while working in real-time. The results exceed all real-time systems in the literature. Furthermore, the first preliminary results of the clinical trial of the polyp detection system suggest a high Adenoma Detection Rate (ADR). In the preliminary study, all polyps were detected by the polyp detection system, and the system achieved a high usability score of 96.3 (max 100). The Paris classification model achieved an F1 score of 89.35 \% which is state-of-the-art. The NICE classification model achieved an F1 score of 81.13 \%. Furthermore, a large data set for polyp detection and classification was created during this thesis. Therefore a fast and robust annotation system called Fast Colonoscopy Annotation Tool (FastCAT) was developed. The system simplifies the annotation process for gastroenterologists. Thereby the i gastroenterologists only annotate key parts of the endoscopic video. Afterward, those video parts are pre-labeled by a polyp detection AI to speed up the process. After the AI has pre-labeled the frames, non-experts correct and finish the annotation. This annotation process is fast and ensures high quality. FastCAT reduces the overall workload of the gastroenterologist on average by a factor of 20 compared to an open-source state-of-art annotation tool.},
  subject      = {Deep Learning},
  language  = {en}
}
@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}
}
@unpublished{Nassourou2011,
  author    = {Nassourou, Mohamadou},
  title     = {A Knowledge-based Hybrid Statistical Classifier for Reconstructing the Chronology of the Quran},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-54712},
  year      = {2011},
  abstract  = {Computationally categorizing Quran's chapters has been mainly confined to the determination of chapters' revelation places. However this broad classification is not sufficient to effectively and thoroughly understand and interpret the Quran. The chronology of revelation would not only improve comprehending the philosophy of Islam, but also the easiness of implementing and memorizing its laws and recommendations. This paper attempts estimating possible chapters' dates of revelation through their lexical frequency profiles. A hybrid statistical classifier consisting of stemming and clustering algorithms for comparing lexical frequency profiles of chapters, and deriving dates of revelation has been developed. The classifier is trained using some chapters with known dates of revelation. Then it classifies chapters with uncertain dates of revelation by computing their proximity to the training ones. The results reported here indicate that the proposed methodology yields usable results in estimating dates of revelation of the Quran's chapters based on their lexical contents.},
  subject      = {Text Mining},
  language  = {en}
}