@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{Gruendler2018,
  author    = {Gr{\"u}ndler, Klaus},
  title     = {A Contribution to the Empirics of Economic Development - The Role of Technology, Inequality, and the State},
  edition   = {1. Auflage},
  publisher = {W{\"u}rzburg University Press},
  address   = {W{\"u}rzburg},
  isbn      = {978-3-95826-072-6 (Print)},
  doi       = {10.25972/WUP-978-3-95826-073-3},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-141520},
  school      = {W{\"u}rzburg University Press},
  pages     = {300},
  year      = {2018},
  abstract  = {This dissertation contributes to the empirical analysis of economic development. The continuing poverty in many Sub-Saharan-African countries as well as the declining trend in growth in the advanced economies that was initiated around the turn of the millennium raises a number of new questions which have received little attention in recent empirical studies. Is culture a decisive factor for economic development? Do larger financial markets trigger positive stimuli with regard to incomes, or is the recent increase in their size in advanced economies detrimental to economic growth? What causes secular stagnation, i.e. the reduction in growth rates of the advanced economies observable over the past 20 years? What is the role of inequality in the growth process, and how do governmental attempts to equalize the income distribution affect economic development? And finally: Is the process of democratization accompanied by an increase in living standards? These are the central questions of this doctoral thesis. To facilitate the empirical analysis of the determinants of economic growth, this dissertation introduces a new method to compute classifications in the field of social sciences. The approach is based on mathematical algorithms of machine learning and pattern recognition. Whereas the construction of indices typically relies on arbitrary assumptions regarding the aggregation strategy of the underlying attributes, utilization of Support Vector Machines transfers the question of how to aggregate the individual components into a non-linear optimization problem. Following a brief overview of the theoretical models of economic growth provided in the first chapter, the second chapter illustrates the importance of culture in explaining the differences in incomes across the globe. In particular, if inhabitants have a lower average degree of risk-aversion, the implementation of new technology proceeds much faster compared with countries with a lower tendency towards risk. However, this effect depends on the legal and political framework of the countries, their average level of education, and their stage of development. The initial wealth of individuals is often not sufficient to cover the cost of investments in both education and new technologies. By providing loans, a developed financial sector may help to overcome this shortage. However, the investigations in the third chapter show that this mechanism is dependent on the development levels of the economies. In poor countries, growth of the financial sector leads to better education and higher investment levels. This effect diminishes along the development process, as intermediary activity is increasingly replaced by speculative transactions. Particularly in times of low technological innovation, an increasing financial sector has a negative impact on economic development. In fact, the world economy is currently in a phase of this kind. Since the turn of the millennium, growth rates in the advanced economies have experienced a multi-national decline, leading to an intense debate about "secular stagnation" initiated at the beginning of 2015. The fourth chapter deals with this phenomenon and shows that the growth potentials of new technologies have been gradually declining since the beginning of the 2000s. If incomes are unequally distributed, some individuals can invest less in education and technological innovations, which is why the fifth chapter identifies an overall negative effect of inequality on growth. This influence, however, depends on the development level of countries. While the negative effect is strongly pronounced in poor economies with a low degree of equality of opportunity, this influence disappears during the development process. Accordingly, redistributive polices of governments exert a growth-promoting effect in developing countries, while in advanced economies, the fostering of equal opportunities is much more decisive. The sixth chapter analyzes the growth effect of the political environment and shows that the ambiguity of earlier studies is mainly due to unsophisticated measurement of the degree of democratization. To solve this problem, the chapter introduces a new method based on mathematical algorithms of machine learning and pattern recognition. While the approach can be used for various classification problems in the field of social sciences, in this dissertation it is applied for the problem of democracy measurement. Based on different country examples, the chapter shows that the resulting SVMDI is superior to other indices in modeling the level of democracy. The subsequent empirical analysis emphasizes a significantly positive growth effect of democracy measured via SVMDI.},
  subject      = {Wirtschaftsentwicklung},
  language  = {en}
}
@phdthesis{Pfitzner2019,
  author    = {Pfitzner, Christian},
  title     = {Visual Human Body Weight Estimation with Focus on Clinical Applications},
  isbn      = {978-3-945459-27-0 (online)},
  doi       = {10.25972/OPUS-17484},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-174842},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {It is the aim of this thesis to present a visual body weight estimation, which is suitable for medical applications. A typical scenario where the estimation of the body weight is essential, is the emergency treatment of stroke patients: In case of an ischemic stroke, the patient has to receive a body weight adapted drug, to solve a blood clot in a vessel. The accuracy of the estimated weight influences the outcome of the therapy directly. However, the treatment has to start as early as possible after the arrival at a trauma room, to provide sufficient treatment. Weighing a patient takes time, and the patient has to be moved. Furthermore, patients are often not able to communicate a value for their body weight due to their stroke symptoms. Therefore, it is state of the art that physicians guess the body weight. A patient receiving a too low dose has an increased risk that the blood clot does not dissolve and brain tissue is permanently damaged. Today, about one-third gets an insufficient dosage. In contrast to that, an overdose can cause bleedings and further complications. Physicians are aware of this issue, but a reliable alternative is missing. The thesis presents state-of-the-art principles and devices for the measurement and estimation of body weight in the context of medical applications. While scales are common and available at a hospital, the process of weighing takes too long and can hardly be integrated into the process of stroke treatment. Sensor systems and algorithms are presented in the section for related work and provide an overview of different approaches. The here presented system -- called Libra3D -- consists of a computer installed in a real trauma room, as well as visual sensors integrated into the ceiling. For the estimation of the body weight, the patient is on a stretcher which is placed in the field of view of the sensors. The three sensors -- two RGB-D and a thermal camera -- are calibrated intrinsically and extrinsically. Also, algorithms for sensor fusion are presented to align the data from all sensors which is the base for a reliable segmentation of the patient. A combination of state-of-the-art image and point cloud algorithms is used to localize the patient on the stretcher. The challenges in the scenario with the patient on the bed is the dynamic environment, including other people or medical devices in the field of view. After the successful segmentation, a set of hand-crafted features is extracted from the patient's point cloud. These features rely on geometric and statistical values and provide a robust input to a subsequent machine learning approach. The final estimation is done with a previously trained artificial neural network. The experiment section offers different configurations of the previously extracted feature vector. Additionally, the here presented approach is compared to state-of-the-art methods; the patient's own assessment, the physician's guess, and an anthropometric estimation. Besides the patient's own estimation, Libra3D outperforms all state-of-the-art estimation methods: 95 percent of all patients are estimated with a relative error of less than 10 percent to ground truth body weight. It takes only a minimal amount of time for the measurement, and the approach can easily be integrated into the treatment of stroke patients, while physicians are not hindered. Furthermore, the section for experiments demonstrates two additional applications: The extracted features can also be used to estimate the body weight of people standing, or even walking in front of a 3D camera. Also, it is possible to determine or classify the BMI of a subject on a stretcher. A potential application for this approach is the reduction of the radiation dose of patients being exposed to X-rays during a CT examination. During the time of this thesis, several data sets were recorded. These data sets contain the ground truth body weight, as well as the data from the sensors. They are available for the collaboration in the field of body weight estimation for medical applications.},
  subject      = {Punktwolke},
  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}
}
@phdthesis{Notz2021,
  author    = {Notz, Pascal Markus},
  title     = {Prescriptive Analytics for Data-driven Capacity Management},
  doi       = {10.25972/OPUS-24042},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-240423},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2021},
  abstract  = {Digitization and artificial intelligence are radically changing virtually all areas across business and society. These developments are mainly driven by the technology of machine learning (ML), which is enabled by the coming together of large amounts of training data, statistical learning theory, and sufficient computational power. This technology forms the basis for the development of new approaches to solve classical planning problems of Operations Research (OR): prescriptive analytics approaches integrate ML prediction and OR optimization into a single prescription step, so they learn from historical observations of demand and a set of features (co-variates) and provide a model that directly prescribes future decisions. These novel approaches provide enormous potential to improve planning decisions, as first case reports showed, and, consequently, constitute a new field of research in Operations Management (OM). First works in this new field of research have studied approaches to solving comparatively simple planning problems in the area of inventory management. However, common OM planning problems often have a more complex structure, and many of these complex planning problems are within the domain of capacity planning. Therefore, this dissertation focuses on developing new prescriptive analytics approaches for complex capacity management problems. This dissertation consists of three independent articles that develop new prescriptive approaches and use these to solve realistic capacity planning problems. The first article, "Prescriptive Analytics for Flexible Capacity Management", develops two prescriptive analytics approaches, weighted sample average approximation (wSAA) and kernelized empirical risk minimization (kERM), to solve a complex two-stage capacity planning problem that has been studied extensively in the literature: a logistics service provider sorts daily incoming mail items on three service lines that must be staffed on a weekly basis. This article is the first to develop a kERM approach to solve a complex two-stage stochastic capacity planning problem with matrix-valued observations of demand and vector-valued decisions. The article develops out-of-sample performance guarantees for kERM and various kernels, and shows the universal approximation property when using a universal kernel. The results of the numerical study suggest that prescriptive analytics approaches may lead to significant improvements in performance compared to traditional two-step approaches or SAA and that their performance is more robust to variations in the exogenous cost parameters. The second article, "Prescriptive Analytics for a Multi-Shift Staffing Problem", uses prescriptive analytics approaches to solve the (queuing-type) multi-shift staffing problem (MSSP) of an aviation maintenance provider that receives customer requests of uncertain number and at uncertain arrival times throughout each day and plans staff capacity for two shifts. This planning problem is particularly complex because the order inflow and processing are modelled as a queuing system, and the demand in each day is non-stationary. The article addresses this complexity by deriving an approximation of the MSSP that enables the planning problem to be solved using wSAA, kERM, and a novel Optimization Prediction approach. A numerical evaluation shows that wSAA leads to the best performance in this particular case. The solution method developed in this article builds a foundation for solving queuing-type planning problems using prescriptive analytics approaches, so it bridges the "worlds" of queuing theory and prescriptive analytics. The third article, "Explainable Subgradient Tree Boosting for Prescriptive Analytics in Operations Management" proposes a novel prescriptive analytics approach to solve the two capacity planning problems studied in the first and second articles that allows decision-makers to derive explanations for prescribed decisions: Subgradient Tree Boosting (STB). STB combines the machine learning method Gradient Boosting with SAA and relies on subgradients because the cost function of OR planning problems often cannot be differentiated. A comprehensive numerical analysis suggests that STB can lead to a prescription performance that is comparable to that of wSAA and kERM. The explainability of STB prescriptions is demonstrated by breaking exemplary decisions down into the impacts of individual features. The novel STB approach is an attractive choice not only because of its prescription performance, but also because of the explainability that helps decision-makers understand the causality behind the prescriptions. The results presented in these three articles demonstrate that using prescriptive analytics approaches, such as wSAA, kERM, and STB, to solve complex planning problems can lead to significantly better decisions compared to traditional approaches that neglect feature data or rely on a parametric distribution estimation.},
  subject      = {Maschinelles Lernen},
  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{Kobs2024,
  author    = {Kobs, Konstantin},
  title     = {Think outside the Black Box: Model-Agnostic Deep Learning with Domain Knowledge},
  doi       = {10.25972/OPUS-34968},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349689},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2024},
  abstract  = {Deep Learning (DL) models are trained on a downstream task by feeding (potentially preprocessed) input data through a trainable Neural Network (NN) and updating its parameters to minimize the loss function between the predicted and the desired output. While this general framework has mainly remained unchanged over the years, the architectures of the trainable models have greatly evolved. Even though it is undoubtedly important to choose the right architecture, we argue that it is also beneficial to develop methods that address other components of the training process. We hypothesize that utilizing domain knowledge can be helpful to improve DL models in terms of performance and/or efficiency. Such model-agnostic methods can be applied to any existing or future architecture. Furthermore, the black box nature of DL models motivates the development of techniques to understand their inner workings. Considering the rapid advancement of DL architectures, it is again crucial to develop model-agnostic methods. In this thesis, we explore six principles that incorporate domain knowledge to understand or improve models. They are applied either on the input or output side of the trainable model. Each principle is applied to at least two DL tasks, leading to task-specific implementations. To understand DL models, we propose to use Generated Input Data coming from a controllable generation process requiring knowledge about the data properties. This way, we can understand the model's behavior by analyzing how it changes when one specific high-level input feature changes in the generated data. On the output side, Gradient-Based Attribution methods create a gradient at the end of the NN and then propagate it back to the input, indicating which low-level input features have a large influence on the model's prediction. The resulting input features can be interpreted by humans using domain knowledge. To improve the trainable model in terms of downstream performance, data and compute efficiency, or robustness to unwanted features, we explore principles that each address one of the training components besides the trainable model. Input Masking and Augmentation directly modifies the training input data, integrating knowledge about the data and its impact on the model's output. We also explore the use of Feature Extraction using Pretrained Multimodal Models which can be seen as a beneficial preprocessing step to extract useful features. When no training data is available for the downstream task, using such features and domain knowledge expressed in other modalities can result in a Zero-Shot Learning (ZSL) setting, completely eliminating the trainable model. The Weak Label Generation principle produces new desired outputs using knowledge about the labels, giving either a good pretraining or even exclusive training dataset to solve the downstream task. Finally, improving and choosing the right Loss Function is another principle we explore in this thesis. Here, we enrich existing loss functions with knowledge about label interactions or utilize and combine multiple task-specific loss functions in a multitask setting. We apply the principles to classification, regression, and representation tasks as well as to image and text modalities. We propose, apply, and evaluate existing and novel methods to understand and improve the model. Overall, this thesis introduces and evaluates methods that complement the development and choice of DL model architectures.},
  subject      = {Deep learning},
  language  = {en}
}
@phdthesis{Allgaier2024,
  author    = {Allgaier, Johannes},
  title     = {Machine Learning Explainability on Multi-Modal Data using Ecological Momentary Assessments in the Medical Domain},
  doi       = {10.25972/OPUS-35118},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-351189},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2024},
  abstract  = {Introduction. Mobile health (mHealth) integrates mobile devices into healthcare, enabling remote monitoring, data collection, and personalized interventions. Machine Learning (ML), a subfield of Artificial Intelligence (AI), can use mHealth data to confirm or extend domain knowledge by finding associations within the data, i.e., with the goal of improving healthcare decisions. In this work, two data collection techniques were used for mHealth data fed into ML systems: Mobile Crowdsensing (MCS), which is a collaborative data gathering approach, and Ecological Momentary Assessments (EMA), which capture real-time individual experiences within the individual's common environments using questionnaires and sensors. We collected EMA and MCS data on tinnitus and COVID-19. About 15 \% of the world's population suffers from tinnitus. Materials \& Methods. This thesis investigates the challenges of ML systems when using MCS and EMA data. It asks: How can ML confirm or broad domain knowledge? Domain knowledge refers to expertise and understanding in a specific field, gained through experience and education. Are ML systems always superior to simple heuristics and if yes, how can one reach explainable AI (XAI) in the presence of mHealth data? An XAI method enables a human to understand why a model makes certain predictions. Finally, which guidelines can be beneficial for the use of ML within the mHealth domain? In tinnitus research, ML discerns gender, temperature, and season-related variations among patients. In the realm of COVID-19, we collaboratively designed a COVID-19 check app for public education, incorporating EMA data to offer informative feedback on COVID-19-related matters. This thesis uses seven EMA datasets with more than 250,000 assessments. Our analyses revealed a set of challenges: App user over-representation, time gaps, identity ambiguity, and operating system specific rounding errors, among others. Our systematic review of 450 medical studies assessed prior utilization of XAI methods. Results. ML models predict gender and tinnitus perception, validating gender-linked tinnitus disparities. Using season and temperature to predict tinnitus shows the association of these variables with tinnitus. Multiple assessments of one app user can constitute a group. Neglecting these groups in data sets leads to model overfitting. In select instances, heuristics outperform ML models, highlighting the need for domain expert consultation to unveil hidden groups or find simple heuristics. Conclusion. This thesis suggests guidelines for mHealth related data analyses and improves estimates for ML performance. Close communication with medical domain experts to identify latent user subsets and incremental benefits of ML is essential.},
  subject      = {Maschinelles Lernen},
  language  = {en}
}