@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}
}
@phdthesis{Gold2023,
  author    = {Gold, Lukas},
  title     = {Methods for the state estimation of lithium-ion batteries},
  doi       = {10.25972/OPUS-30618},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-306180},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {This work introduced the reader to all relevant fields to tap into an ultrasound-based state of charge estimation and provides a blueprint for the procedure to achieve and test the fundamentals of such an approach. It spanned from an in-depth electrochemical characterization of the studied battery cells over establishing the measurement technique, digital processing of ultrasonic transmission signals, and characterization of the SoC dependent property changes of those signals to a proof of concept of an ultrasound-based state of charge estimation. The State of the art \& theoretical background chapter focused on the battery section on the mechanical property changes of lithium-ion batteries during operation. The components and the processes involved to manufacture a battery cell were described to establish the fundamentals for later interrogation. A comprehensive summary of methods for state estimation was given and an emphasis was laid on mechanical methods, including a critical review of the most recent research on ultrasound-based state estimation. Afterward, the fundamentals of ultrasonic non-destructive evaluation were introduced, starting with the sound propagation modes in isotropic boundary-free media, followed by the introduction of boundaries and non-isotropic structure to finally approach the class of fluid-saturated porous media, which batteries can be counted to. As the processing of the ultrasonic signals transmitted through lithium-ion battery cells with the aim of feature extraction was one of the main goals of this work, the fundamentals of digital signal processing and methods for the time of flight estimation were reviewed and compared in a separate section. All available information on the interrogated battery cell and the instrumentation was collected in the Experimental methods \& instrumentation chapter, including a detailed step-by-step manual of the process developed in this work to create and attach a sensor stack for ultrasonic interrogation based on low-cost off-the-shelf piezo elements. The Results \& discussion chapter opened with an in-depth electrochemical and post-mortem interrogation to reverse engineer the battery cell design and its internal structure. The combination of inductively coupled plasma-optical emission spectrometry and incremental capacity analysis applied to three-electrode lab cells, constructed from the studied battery cell's materials, allowed to identify the SoC ranges in which phase transitions and staging occur and thereby directly links changes in the ultrasonic signal properties with the state of the active materials, which makes this work stand out among other studies on ultrasound-based state estimation. Additional dilatometer experiments were able to prove that the measured effect in ultrasonic time of flight cannot originate from the thickness increase of the battery cells alone, as this thickness increase is smaller and in opposite direction to the change in time of flight. Therefore, changes in elastic modulus and density have to be responsible for the observed effect. The construction of the sensor stack from off-the-shelf piezo elements, its electromagnetic shielding, and attachment to both sides of the battery cells was treated in a subsequent section. Experiments verified the necessity of shielding and its negligible influence on the ultrasonic signals. A hypothesis describing the metal layer in the pouch foil to be the transport medium of an electrical coupling/distortion between sending and receiving sensor was formulated and tested. Impedance spectroscopy was shown to be a useful tool to characterize the resonant behavior of piezo elements and ensure the mechanical coupling of such to the surface of the battery cells. The excitation of the piezo elements by a raised cosine (RCn) waveform with varied center frequency in the range of 50 kHz to 250 kHz was studied in the frequency domain and the influence of the resonant behavior, as identified prior by impedance spectroscopy, on waveform and frequency content was evaluated to be uncritical. Therefore, the forced oscillation produced by this excitation was assumed to be mechanically coupled as ultrasonic waves into the battery cells. The ultrasonic waves transmitted through the battery cell were recorded by piezo elements on the opposing side. A first inspection of the raw, unprocessed signals identified the transmission of two main wave packages and allowed the identification of two major trends: the time of flight of ultrasonic wave packages decreases with the center frequency of the RCn waveform, and with state of charge. These trends were to be assessed further in the subsequent sections. Therefore, methods for the extraction of features (properties) from the ultrasonic signals were established, compared, and tested in a dedicated section. Several simple and advanced thresholding methods were compared with envelope-based and cross-correlation methods to estimate the time of flight (ToF). It was demonstrated that the envelope-based method yields the most robust estimate for the first and second wave package. This finding is in accordance with the literature stating that an envelope-based method is best suited for dispersive, absorptive media [204], to which lithium-ion batteries are counted. Respective trends were already suggested by the heatmap plots of the raw signals vs. RCn frequency and SoC. To enable such a robust estimate, an FIR filter had to be designed to preprocess the transmitted signals and thereby attenuate frequency components that verifiably lead to a distorted shape of the envelope. With a robust ToF estimation method selected, the characterization of the signal properties ToF and transmitted energy content (EC) was performed in-depth. A study of cycle-to-cycle variations unveiled that the signal properties are affected by a long rest period and the associated relaxation of the multi-particle system "battery cell" to equilibrium. In detail, during cycling, the signal properties don't reach the same value at a given SoC in two subsequent cycles if the first of the two cycles follows a long rest period. In accordance with the literature, a break-in period, making up for more than ten cycles post-formation, was observed. During this break-in period, the mechanical properties of the system are said to change until a steady state is reached [25]. Experiments at different C-rate showed that ultrasonic signal properties can sense the non-equilibrium state of a battery cell, characterized by an increasing area between charge and discharge curve of the respective signal property vs. SoC plot. This non-equilibrium state relaxes in the rest period following the discharge after the cut-off voltage is reached. The relaxation in the rest period following the charge is much smaller and shows little C-rate dependency as the state is prepared by constant voltage charging at the end of charge voltage. For a purely statistical SoC estimation approach, as employed in this work, where only instantaneous measurements are taken into account and the historic course of the measurement is not utilized as a source of information, the presence of hysteresis and relaxation leads to a reduced estimation accuracy. Future research should address this issue or even utilize the relaxation to improve the estimation accuracy, by incorporating historic information, e.g., by using the derivative of a signal property as an additional feature. The signal properties were then tested for their correlation with SoC as a function of RCn frequency. This allowed identifying trends in the behavior of the signal properties as a function of RCn frequency and C-rate in a condensed fashion and thereby enabled to predict the frequency range, about 50 kHz to 125 kHz, in which the course of the signal properties is best suited for SoC estimation. The final section provided a proof of concept of the ultrasound-based SoC estimation, by applying a support vector regression (SVR) to before thoroughly studied ultrasonic signal properties, as well as current and battery cell voltage. The included case study was split into different parts that assessed the ability of an SVR to estimate the SoC in a variety of scenarios. Seven battery cells, prepared with sensor stacks attached to both faces, were used to generate 14 datasets. First, a comparison of self-tests, where a portion of a dataset is used for training and another for testing, and cross-tests, which use the dataset of one cell for training and the dataset of another for testing, was performed. A root mean square error (RMSE) of 3.9\% to 4.8\% SoC and 3.6\% to 10.0\% SoC was achieved, respectively. In general, it was observed that the SVR is prone to overestimation at low SoCs and underestimation at high SoCs, which was attributed to the pronounced hysteresis and relaxation of the ultrasonic signal properties in this SoC ranges. The fact that higher accuracy is achieved, if the exact cell is known to the model, indicates that a variation between cells exists. This variation between cells can originate from differences in mechanical properties as a result of production variations or from differences in manual sensor placement, mechanical coupling, or resonant behavior of the ultrasonic sensors. To mitigate the effect of the cell-to-cell variations, a test was performed, where the datasets of six out of the seven cells were combined as training data, and the dataset of the seventh cell was used for testing. This reduced the spread of the RMSE from (3.6 - 10.0)\% SoC to (5.9 - 8.5)\% SoC, respectively, once again stating that a databased approach for state estimation becomes more reliable with a large data basis. Utilizing self-tests on seven datasets, the effect of additional features on the state estimation result was tested. The involvement of an additional feature did not necessarily improve the estimation accuracy, but it was shown that a combination of ultrasonic and electrical features is superior to the training with these features alone. To test the ability of the model to estimate the SoC in unknown cycling conditions, a test was performed where the C-rate of the test dataset was not included in the training data. The result suggests that for practical applications it might be sufficient to perform training with the boundary of the use cases in a controlled laboratory environment to handle the estimation in a broad spectrum of use cases. In comparison with literature, this study stands out by utilizing and modifying off-the-shelf piezo elements to equip state-of-the-art lithium-ion battery cells with ultrasonic sensors, employing a range of center frequencies for the waveform, transmitted through the battery cell, instead of a fixed frequency and by allowing the SVR to choose the frequency that yields the best result. The characterization of the ultrasonic signal properties as a function of RCn frequency and SoC and the assignment of characteristic changes in the signal properties to electrochemical processes, such as phase transitions and staging, makes this work unique. By studying a range of use cases, it was demonstrated that an improved SoC estimation accuracy can be achieved with the aid of ultrasonic measurements - thanks to the correlation of the mechanical properties of the battery cells with the SoC.},
  subject      = {Lithium-Ionen-Akkumulator},
  language  = {en}
}
@phdthesis{Grohmann2022,
  author    = {Grohmann, Johannes Sebastian},
  title     = {Model Learning for Performance Prediction of Cloud-native Microservice Applications},
  doi       = {10.25972/OPUS-26160},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-261608},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {One consequence of the recent coronavirus pandemic is increased demand and use of online services around the globe. At the same time, performance requirements for modern technologies are becoming more stringent as users become accustomed to higher standards. These increased performance and availability requirements, coupled with the unpredictable usage growth, are driving an increasing proportion of applications to run on public cloud platforms as they promise better scalability and reliability. With data centers already responsible for about one percent of the world's power consumption, optimizing resource usage is of paramount importance. Simultaneously, meeting the increasing and changing resource and performance requirements is only possible by optimizing resource management without introducing additional overhead. This requires the research and development of new modeling approaches to understand the behavior of running applications with minimal information. However, the emergence of modern software paradigms makes it increasingly difficult to derive such models and renders previous performance modeling techniques infeasible. Modern cloud applications are often deployed as a collection of fine-grained and interconnected components called microservices. Microservice architectures offer massive benefits but also have broad implications for the performance characteristics of the respective systems. In addition, the microservices paradigm is typically paired with a DevOps culture, resulting in frequent application and deployment changes. Such applications are often referred to as cloud-native applications. In summary, the increasing use of ever-changing cloud-hosted microservice applications introduces a number of unique challenges for modeling the performance of modern applications. These include the amount, type, and structure of monitoring data, frequent behavioral changes, or infrastructure variabilities. This violates common assumptions of the state of the art and opens a research gap for our work. In this thesis, we present five techniques for automated learning of performance models for cloud-native software systems. We achieve this by combining machine learning with traditional performance modeling techniques. Unlike previous work, our focus is on cloud-hosted and continuously evolving microservice architectures, so-called cloud-native applications. Therefore, our contributions aim to solve the above challenges to deliver automated performance models with minimal computational overhead and no manual intervention. Depending on the cloud computing model, privacy agreements, or monitoring capabilities of each platform, we identify different scenarios where performance modeling, prediction, and optimization techniques can provide great benefits. Specifically, the contributions of this thesis are as follows: Monitorless: Application-agnostic prediction of performance degradations. To manage application performance with only platform-level monitoring, we propose Monitorless, the first truly application-independent approach to detecting performance degradation. We use machine learning to bridge the gap between platform-level monitoring and application-specific measurements, eliminating the need for application-level monitoring. Monitorless creates a single and holistic resource saturation model that can be used for heterogeneous and untrained applications. Results show that Monitorless infers resource-based performance degradation with 97\% accuracy. Moreover, it can achieve similar performance to typical autoscaling solutions, despite using less monitoring information. SuanMing: Predicting performance degradation using tracing. We introduce SuanMing to mitigate performance issues before they impact the user experience. This contribution is applied in scenarios where tracing tools enable application-level monitoring. SuanMing predicts explainable causes of expected performance degradations and prevents performance degradations before they occur. Evaluation results show that SuanMing can predict and pinpoint future performance degradations with an accuracy of over 90\%. SARDE: Continuous and autonomous estimation of resource demands. We present SARDE to learn application models for highly variable application deployments. This contribution focuses on the continuous estimation of application resource demands, a key parameter of performance models. SARDE represents an autonomous ensemble estimation technique. It dynamically and continuously optimizes, selects, and executes an ensemble of approaches to estimate resource demands in response to changes in the application or its environment. Through continuous online adaptation, SARDE efficiently achieves an average resource demand estimation error of 15.96\% in our evaluation. DepIC: Learning parametric dependencies from monitoring data. DepIC utilizes feature selection techniques in combination with an ensemble regression approach to automatically identify and characterize parametric dependencies. Although parametric dependencies can massively improve the accuracy of performance models, DepIC is the first approach to automatically learn such parametric dependencies from passive monitoring data streams. Our evaluation shows that DepIC achieves 91.7\% precision in identifying dependencies and reduces the characterization prediction error by 30\% compared to the best individual approach. Baloo: Modeling the configuration space of databases. To study the impact of different configurations within distributed DBMSs, we introduce Baloo. Our last contribution models the configuration space of databases considering measurement variabilities in the cloud. More specifically, Baloo dynamically estimates the required benchmarking measurements and automatically builds a configuration space model of a given DBMS. Our evaluation of Baloo on a dataset consisting of 900 configuration points shows that the framework achieves a prediction error of less than 11\% while saving up to 80\% of the measurement effort. Although the contributions themselves are orthogonally aligned, taken together they provide a holistic approach to performance management of modern cloud-native microservice applications. Our contributions are a significant step forward as they specifically target novel and cloud-native software development and operation paradigms, surpassing the capabilities and limitations of previous approaches. In addition, the research presented in this paper also has a significant impact on the industry, as the contributions were developed in collaboration with research teams from Nokia Bell Labs, Huawei, and Google. Overall, our solutions open up new possibilities for managing and optimizing cloud applications and improve cost and energy efficiency.},
  subject      = {Cloud Computing},
  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{Hauser2020,
  author    = {Hauser, Matthias},
  title     = {Smart Store Applications in Fashion Retail},
  doi       = {10.25972/OPUS-19301},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193017},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {Traditional fashion retailers are increasingly hard-pressed to keep up with their digital competitors. In this context, the re-invention of brick-and-mortar stores as smart retail environments is being touted as a crucial step towards regaining a competitive edge. This thesis describes a design-oriented research project that deals with automated product tracking on the sales floor and presents three smart fashion store applications that are tied to such localization information: (i) an electronic article surveillance (EAS) system that distinguishes between theft and non-theft events, (ii) an automated checkout system that detects customers' purchases when they are leaving the store and associates them with individual shopping baskets to automatically initiate payment processes, and (iii) a smart fitting room that detects the items customers bring into individual cabins and identifies the items they are currently most interested in to offer additional customer services (e.g., product recommendations or omnichannel services). The implementation of such cyberphysical systems in established retail environments is challenging, as architectural constraints, well-established customer processes, and customer expectations regarding privacy and convenience pose challenges to system design. To overcome these challenges, this thesis leverages Radio Frequency Identification (RFID) technology and machine learning techniques to address the different detection tasks. To optimally configure the systems and draw robust conclusions regarding their economic value contribution, beyond technological performance criteria, this thesis furthermore introduces a service operations model that allows mapping the systems' technical detection characteristics to business relevant metrics such as service quality and profitability. This analytical model reveals that the same system component for the detection of object transitions is well suited for the EAS application but does not have the necessary high detection accuracy to be used as a component of an automated checkout system.},
  subject      = {Laden},
  language  = {en}
}
@phdthesis{Hein2014,
  author    = {Hein, Michael},
  title     = {Entwicklung computergest{\"u}tzter Methoden zur Bewertung von Docking-L{\"o}sungen und Entwurf niedermolekularer MIP-Inhibitoren},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-101585},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2014},
  abstract  = {Dockingbasierte Ans{\"a}tze z{\"a}hlen zu den wichtigsten Komponenten im virtuellen Screening. Sie dienen der Vorhersage der Ligandposition und -konformation in der Bindetasche sowie der Absch{\"a}tzung der Bindungsaffinit{\"a}t zum Protein. Bis heute stellt die korrekte Identifizierung proteingebundener Ligandkonformationen ein noch nicht vollst{\"a}ndig gel{\"o}stes Problem f{\"u}r Scoringfunktionen dar. Der erste Teil der vorliegenden Arbeit ist daher der Entwicklung computergest{\"u}tzter Methoden zur Bewertung von Docking-L{\"o}sungen gewidmet. Der Fokus eines ersten Teilprojektes lag auf der Ber{\"u}cksichtigung der Abs{\"a}ttigung vergrabener Wasserstoffbr{\"u}ckenakzeptoren (HBA) und -donoren (HBD) bei der Bewertung von Docking-L{\"o}sungen. Nicht-abges{\"a}ttigte vergrabene HBA und HBD stellen einen der Bindungsaffinit{\"a}t abtr{\"a}glichen Beitrag dar, der bis dato aufgrund fehlender Struktur- bzw. Affinit{\"a}tsdaten in Scoringfunktionen vernachl{\"a}ssigt wird. Im Rahmen der vorliegenden Arbeit wurde auf der Basis einer detaillierten Untersuchung zur H{\"a}ufigkeit vergrabener nicht-abges{\"a}ttigter HBA und HBD in hochaufgel{\"o}sten Protein-Ligand-Komplexen des Hartshorn-Datensatzes eine empirische Filterfunktion („vnaHB"-Filterfunktion) entwickelt, die unerw{\"u}nschte Ligandbindeposen erkennt und von der Bewertung mittels Scoringfunktionen ausschließt. Der praktische Nutzen der empirischen Filterfunktion wurde f{\"u}r die Scoringfunktionen SFCscore und DSX anhand vorgenerierter Docking-L{\"o}sungen des Cheng-Datensatzes untersucht. Die H{\"a}ufigkeitsuntersuchung zeigt, dass eine Abs{\"a}ttigung vergrabener polarer Gruppen in Protein-Ligand-Komplexen f{\"u}r eine hochaffine Protein-Ligand-Bindung notwendig ist, da vergrabene nicht-abges{\"a}ttigte HBA und HBD nur selten auftreten. Eine vollst{\"a}ndige Abs{\"a}ttigung durch entsprechende Proteinpartner wird f{\"u}r ca. 48 \% der untersuchten Komplexe beobachtet, ca. 92 \% weisen weniger als drei haupts{\"a}chlich schwache, nicht-abges{\"a}ttigte HBA bzw. HBD (z. B. Etherfunktionen) auf. Unter Einbeziehung von Wassermolek{\"u}len in die H{\"a}ufigkeitsanalyse sind sogar f{\"u}r ca. 61 \% aller Komplexe alle wasserstoffbr{\"u}ckenbindenden Gruppen abges{\"a}ttigt. Im Gegensatz zu DSX werden f{\"u}r SFCscore nach Anwendung der empirischen Filterfunktion erh{\"o}hte Erfolgsraten f{\"u}r das Auffinden einer kristallnahen Pose (≤ 2.0 {\AA} Abweichung) unter den am besten bewerteten Docking-Posen erzielt. F{\"u}r die beste SFCscore-Funktion (SFCscore::229m) werden Steigerungen dieses als „Docking Power" bezeichneten Kriteriums f{\"u}r die Top-3-Posen (Erfolgsrate f{\"u}r die Identifizierung einer kristallnahen 2.0 {\AA} Pose unter den besten drei Docking-L{\"o}sungen) von 63.1 \% auf 64.2 \% beobachtet. In einem weiteren Teilprojekt wurden repulsive Protein-Ligand-Kontakte infolge sterischer {\"U}berlappungen der Bindungspartner bei der Bewertung von Docking-L{\"o}sungen ber{\"u}cksichtigt. Die ad{\"a}quate Einbeziehung solcher repulsiver Kontakte im Scoring ist f{\"u}r die Identifizierung proteingebundener Ligandkonformationen entscheidend, jedoch aufgrund fehlender Affinit{\"a}ts- bzw. Strukturdaten problematisch. Im Rahmen der vorliegenden Arbeit wurde auf der Basis des Lennard-Jones-Potentiales des AMBER-Kraftfeldes zun{\"a}chst ein neuer Deskriptor zur Beschreibung repulsiver Kontakte („Clash"-Deskriptor) entwickelt und zur Untersuchung der H{\"a}ufigkeit ung{\"u}nstiger Protein-Ligand-Kontakte in hochaufgel{\"o}sten Protein-Ligand-Komplexen des Hartshorn-Datensatzes herangezogen. Eine aus der H{\"a}ufigkeitsverteilung abgeleitete empirische Filterfunktion („Clash"-Filterfunktion) wurde anschließend der Bewertung von Docking-L{\"o}sungen des Cheng-Datensatzes mittels der Scoringfunktionen SFCscore und DSX vorgeschaltet, um unerw{\"u}nschte Ligandbindeposen auszuschließen. Die H{\"a}ufigkeitsuntersuchung zeigt, dass vorwiegend schwache repulsive Kontakte in Protein-Ligand-Komplexen auftreten. So werden in 75 \% der Komplexe des Hartshorn-Datensatzes abstoßende Potentiale unter 0.462 kcal/mol beobachtet. Zwar betragen die ung{\"u}nstigen Beitr{\"a}ge pro Komplex f{\"u}r 50 \% aller Strukturen ca. 0.8 kcal/mol bis 2.5 kcal/mol, jedoch k{\"o}nnen diese auf Ungenauigkeiten der Kristallstrukturen zur{\"u}ckzuf{\"u}hren sein bzw. durch g{\"u}nstige Protein-Ligand-Wechselwirkungen kompensiert werden. Die Anwendung der „Clash"-Filterfunktion zeigt signifikante Verbesserungen der Docking Power f{\"u}r SFCscore. F{\"u}r die beste SFCscore-Funktion (SFCscore::frag) werden Steigerungen der Erfolgsraten f{\"u}r das Auffinden einer kristallnahen Pose unter den drei am besten bewerteten Docking-L{\"o}sungen von 61.4 \% auf 86.9 \% erzielt, was an die Docking Power der bis dato besten Scoringfunktionen aus der Literatur (z. B. DSX, GlideScore::SP) heranreicht (Docking Power (DSX): 92.6 \%; Docking Power (GlideScore::SP): 86.9 \%). Die „Clash"-Filterfunktion allein ist auch der Kombination der „Clash"- und der „vnaHB"-Filterfunktion {\"u}berlegen. Ein weiterer Schwerpunkt der vorliegenden Arbeit wurde auf die Einbeziehung von Decoy-Daten (Struktur- und Affinit{\"a}tsdaten schwach affiner und inaktiver Liganden) im Zuge der Entwicklung computergest{\"u}tzter Methoden zur Bewertung von Docking-L{\"o}sungen gelegt. Dadurch soll eine ad{\"a}quate Ber{\"u}cksichtigung ung{\"u}nstiger Beitr{\"a}ge zur Bindungsaffinit{\"a}t erm{\"o}glicht werden, die f{\"u}r die Richtigkeit und Zuverl{\"a}ssigkeit ermittelter Vorhersagen essentiell ist. In der vorliegenden Arbeit wurden bin{\"a}re Klassifizierungsmodelle zur Bewertung von Docking-L{\"o}sungen entwickelt, die die Einbeziehung von Decoy-Daten ohne die Verf{\"u}gbarkeit von Affinit{\"a}tsdaten erlauben. Der Random-Forest-Algorithmus (RF), SFCscore-Deskriptoren, der neu entwickelte „Clash"-Deskriptor, und die Decoy-Datens{\"a}tze von Cheng und Huang (Trainingsdaten) bilden die Grundlage des leistungsf{\"a}higsten Klassifizierungsmodells. Der praktische Nutzen des „besten" RF-Modells wurde nach Kombination mit der Scoringfunktion DSX anhand der Docking Power f{\"u}r das Auffinden einer kristallnahen Pose auf Rang 1 am unabh{\"a}ngigen Cheng-/Huang- (Komplexe, die nicht in den Trainingsdaten enthalten sind) und CSAR-2012-Testdatensatz untersucht. Gegen{\"u}ber einer alleinigen Anwendung von DSX werden an beiden Testdatens{\"a}tzen weitere Verbesserungen der Docking Power erzielt (Cheng-/Huang-Testdatensatz: DSX 84.24 \%, RF 87.27 \%; CSAR-2012-Testdatensatz: DSX 87.93 \%, RF 91.38 \%). Das „beste" Modell zeichnet sich durch die zuverl{\"a}ssige Vorhersage richtig-positiver Docking-L{\"o}sungen f{\"u}r einige wenige Komplexe aus, f{\"u}r die DSX keine kristallnahe Ligandkonformation identifizieren kann. Ein visueller Vergleich der jeweils am besten bewerteten RF- und DSX-Pose f{\"u}r diese Komplexe zeigt Vorteile des RF-Modells hinsichtlich der Erkennung f{\"u}r die Protein-Ligand-Bindung essentieller Wechselwirkungen. Die Untersuchung der Bedeutung einzelner SFCscore-Deskriptoren f{\"u}r die Klassifizierung von Docking-L{\"o}sungen sowie die Analyse der Misserfolge nach Anwendung des Modells geben wertvolle Hinweise zur weiteren Optimierung der bestehenden Methode. Hinsichtlich der zu bewertenden Eigenschaften ausgeglichenere Trainingsdaten, Weiterentwicklungen bestehender SFCscore-Deskriptoren sowie die Implementierung neuer Deskriptoren zur Beschreibung bis dato nicht-ber{\"u}cksichtigter Beitr{\"a}ge zur Bindungsaffinit{\"a}t stellen Ansatzpunkte zur Verbesserung dar. Der zweite Teil der vorliegenden Arbeit umfasst die Anwendung dockingbasierter Methoden im Rahmen der Entwicklung neuer Inhibitoren des „Macrophage Infectivity Potentiator"-(MIP)-Proteins von Legionella pneumophila und Burkholderia pseudomallei. Das MIP-Protein von Legionella pneumophila stellt einen wichtigen Virulenzfaktor und daher ein attraktives Zielprotein f{\"u}r die Therapie der Legionellose dar. Im Rahmen der vorliegenden Arbeit erfolgten systematische Optimierungen des Pipecolins{\"a}ure-Sulfonamides 1, des bis dato besten niedermolekularen MIP-Inhibitors (IC50 (1): 9 ± 0.7 µM). Nach Hot-Spot-Analysen der Bindetasche wurden Docking-Studien zur Auswahl aussichtsreicher Kandidaten f{\"u}r die Synthese und Testung auf MIP-Inhibition durchgef{\"u}hrt. Die Ergebnisse der Hot-Spot-Analysen zeigen g{\"u}nstige Wechselwirkungsbereiche f{\"u}r Donorgruppen und hydrophobe Substituenten in meta-Position sowie Akzeptorgruppen in para-Position des Benzylringes von 1 auf. Die Einf{\"u}hrung einer Nitrofunktion in para-Position des Benzylringes von 1 (2h) resultiert in einer erh{\"o}hten MIP-Inhibition (IC50 (2h): 5 ± 1.5 µM), was wahrscheinlich auf die Ausbildung einer zus{\"a}tzlichen Wasserstoffbr{\"u}cke zu Gly116 zur{\"u}ckzuf{\"u}hren ist. Selektivit{\"a}tsverbesserungen gegen{\"u}ber dem strukturverwandten humanen FKBP12-Protein werden insbesondere f{\"u}r das para-Aminoderivat von 1 (2n) erzielt (Selektivit{\"a}tsindex (1): 45, Selektivit{\"a}tsindex (2n): 4.2; mit Selektivit{\"a}tsindex = IC50 (MIP)/IC50 (FKBP12)). Der Ersatz des hydrophoben Trimethoxyphenylrestes von 1 durch einen Pyridinring (2s) f{\"u}hrt zu einer verbesserten L{\"o}slichkeit bei vergleichbarer MIP-Inhibition. Das MIP-Protein von Burkholderia pseudomallei spielt eine wichtige Rolle in der Pathogenese der Melioidose und stellt daher ein attraktives Zielprotein f{\"u}r die Entwicklung neuer Arzneistoffe dar. In der vorliegenden Arbeit erfolgten Optimierungen des bis dato besten niedermolekularen MIP-Inhibitors 1. Ausgehend von einem Strukturvergleich von Burkholderia pseudomallei MIP mit Legionella pneumophila MIP und einer Hot-Spot-Analyse der Burkholderia pseudomallei MIP-Bindetasche wurden Docking-Studien zur Auswahl aussichtsreicher Kandidaten f{\"u}r die Synthese und Testung auf MIP-Inhibition durchgef{\"u}hrt. Der Strukturvergleich zeigt eine hohe Homologie beider Bindetaschen. Gr{\"o}ßere konformelle {\"A}nderungen werden lediglich f{\"u}r den von Ala94, Gly95, Val97 und Ile98 geformten Bindetaschenbereich beobachtet, was unterschiedliche Optimierungsstrategien f{\"u}r 1 erforderlich macht. G{\"u}nstige Wechselwirkungsbereiche der Burkholderia pseudomallei MIP-Bindetasche finden sich einerseits f{\"u}r Donorgruppen oder hydrophobe Substituenten in para-Position des Benzylringes (Region A) von 1, andererseits f{\"u}r Akzeptor- bzw. Donorgruppen in para- bzw. meta-/para-Position des Trimethoxyphenylringes (Region B). Anhand von Docking-Studien konnten sowohl f{\"u}r Variationen in Region A als auch in Region B aussichtsreiche Kandidaten identifiziert werden. Initiale MIP-Inhibitionsmessungen der bis dato synthetisierten Derivate deuten auf erh{\"o}hte Hemmungen im Vergleich zu 1 hin. Der Ersatz des hydrophoben Trimethoxyphenylrestes von 1 durch einen Pyridinring f{\"u}hrt auch hier zu vergleichbarer MIP-Inhibition bei verbesserter L{\"o}slichkeit. Derzeit sind weitere Synthesen und Testungen aussichtsreicher Liganden durch die Kooperationspartner geplant. Die Ergebnisse der Inhibitionsmessungen sollen deren Nutzen als MIP-Inhibitoren aufzeigen und wertvolle Informationen f{\"u}r weitere Zyklen des strukturbasierten Wirkstoffdesigns liefern.},
  subject      = {Arzneimitteldesign},
  language  = {de}
}
@article{HermJanieschFuchs2022,
  author    = {Herm, Lukas-Valentin and Janiesch, Christian and Fuchs, Patrick},
  title     = {Der Einfluss von menschlichen Denkmustern auf k{\"u}nstliche Intelligenz - eine strukturierte Untersuchung von kognitiven Verzerrungen},
  series = {HMD Praxis der Wirtschaftsinformatik},
  volume    = {59},
  journal   = {HMD Praxis der Wirtschaftsinformatik},
  number    = {2},
  issn      = {1436-3011},
  doi       = {10.1365/s40702-022-00844-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-323787},
  pages     = {556-571},
  year      = {2022},
  abstract  = {K{\"u}nstliche Intelligenz (KI) dringt vermehrt in sensible Bereiche des allt{\"a}glichen menschlichen Lebens ein. Es werden nicht mehr nur noch einfache Entscheidungen durch intelligente Systeme getroffen, sondern zunehmend auch komplexe Entscheidungen. So entscheiden z. B. intelligente Systeme, ob Bewerber in ein Unternehmen eingestellt werden sollen oder nicht. Oftmals kann die zugrundeliegende Entscheidungsfindung nur schwer nachvollzogen werden und ungerechtfertigte Entscheidungen k{\"o}nnen dadurch unerkannt bleiben, weshalb die Implementierung einer solchen KI auch h{\"a}ufig als sogenannte Blackbox bezeichnet wird. Folglich steigt die Bedrohung, durch unfaire und diskriminierende Entscheidungen einer KI benachteiligt behandelt zu werden. Resultieren diese Verzerrungen aus menschlichen Handlungen und Denkmustern spricht man von einer kognitiven Verzerrung oder einem kognitiven Bias. Aufgrund der Neuigkeit dieser Thematik ist jedoch bisher nicht ersichtlich, welche verschiedenen kognitiven Bias innerhalb eines KI-Projektes auftreten k{\"o}nnen. Ziel dieses Beitrages ist es, anhand einer strukturierten Literaturanalyse, eine gesamtheitliche Darstellung zu erm{\"o}glichen. Die gewonnenen Erkenntnisse werden anhand des in der Praxis weit verbreiten Cross-Industry Standard Process for Data Mining (CRISP-DM) Modell aufgearbeitet und klassifiziert. Diese Betrachtung zeigt, dass der menschliche Einfluss auf eine KI in jeder Entwicklungsphase des Modells gegeben ist und es daher wichtig ist „mensch-{\"a}hnlichen" Bias in einer KI explizit zu untersuchen.},
  language  = {de}
}
@phdthesis{Kleineisel2024,
  author    = {Kleineisel, Jonas},
  title     = {Variational networks in magnetic resonance imaging - Application to spiral cardiac MRI and investigations on image quality},
  doi       = {10.25972/OPUS-34737},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-347370},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2024},
  abstract  = {Acceleration is a central aim of clinical and technical research in magnetic resonance imaging (MRI) today, with the potential to increase robustness, accessibility and patient comfort, reduce cost, and enable entirely new kinds of examinations. A key component in this endeavor is image reconstruction, as most modern approaches build on advanced signal and image processing. Here, deep learning (DL)-based methods have recently shown considerable potential, with numerous publications demonstrating benefits for MRI reconstruction. However, these methods often come at the cost of an increased risk for subtle yet critical errors. Therefore, the aim of this thesis is to advance DL-based MRI reconstruction, while ensuring high quality and fidelity with measured data. A network architecture specifically suited for this purpose is the variational network (VN). To investigate the benefits these can bring to non-Cartesian cardiac imaging, the first part presents an application of VNs, which were specifically adapted to the reconstruction of accelerated spiral acquisitions. The proposed method is compared to a segmented exam, a U-Net and a compressed sensing (CS) model using qualitative and quantitative measures. While the U-Net performed poorly, the VN as well as the CS reconstruction showed good output quality. In functional cardiac imaging, the proposed real-time method with VN reconstruction substantially accelerates examinations over the gold-standard, from over 10 to just 1 minute. Clinical parameters agreed on average. Generally in MRI reconstruction, the assessment of image quality is complex, in particular for modern non-linear methods. Therefore, advanced techniques for precise evaluation of quality were subsequently demonstrated. With two distinct methods, resolution and amplification or suppression of noise are quantified locally in each pixel of a reconstruction. Using these, local maps of resolution and noise in parallel imaging (GRAPPA), CS, U-Net and VN reconstructions were determined for MR images of the brain. In the tested images, GRAPPA delivers uniform and ideal resolution, but amplifies noise noticeably. The other methods adapt their behavior to image structure, where different levels of local blurring were observed at edges compared to homogeneous areas, and noise was suppressed except at edges. Overall, VNs were found to combine a number of advantageous properties, including a good trade-off between resolution and noise, fast reconstruction times, and high overall image quality and fidelity of the produced output. Therefore, this network architecture seems highly promising for MRI reconstruction.},
  subject      = {Kernspintomografie},
  language  = {en}
}
@phdthesis{Kluegl2015,
  author    = {Kl{\"u}gl, Peter},
  title     = {Context-specific Consistencies in Information Extraction: Rule-based and Probabilistic Approaches},
  publisher = {W{\"u}rzburg University Press},
  address   = {W{\"u}rzburg},
  isbn      = {978-3-95826-018-4 (print)},
  doi       = {10.25972/WUP-978-3-95826-019-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-108352},
  school      = {W{\"u}rzburg University Press},
  year      = {2015},
  abstract  = {Large amounts of communication, documentation as well as knowledge and information are stored in textual documents. Most often, these texts like webpages, books, tweets or reports are only available in an unstructured representation since they are created and interpreted by humans. In order to take advantage of this huge amount of concealed information and to include it in analytic processes, it needs to be transformed into a structured representation. Information extraction considers exactly this task. It tries to identify well-defined entities and relations in unstructured data and especially in textual documents. Interesting entities are often consistently structured within a certain context, especially in semi-structured texts. However, their actual composition varies and is possibly inconsistent among different contexts. Information extraction models stay behind their potential and return inferior results if they do not consider these consistencies during processing. This work presents a selection of practical and novel approaches for exploiting these context-specific consistencies in information extraction tasks. The approaches direct their attention not only to one technique, but are based on handcrafted rules as well as probabilistic models. A new rule-based system called UIMA Ruta has been developed in order to provide optimal conditions for rule engineers. This system consists of a compact rule language with a high expressiveness and strong development support. Both elements facilitate rapid development of information extraction applications and improve the general engineering experience, which reduces the necessary efforts and costs when specifying rules. The advantages and applicability of UIMA Ruta for exploiting context-specific consistencies are illustrated in three case studies. They utilize different engineering approaches for including the consistencies in the information extraction task. Either the recall is increased by finding additional entities with similar composition, or the precision is improved by filtering inconsistent entities. Furthermore, another case study highlights how transformation-based approaches are able to correct preliminary entities using the knowledge about the occurring consistencies. The approaches of this work based on machine learning rely on Conditional Random Fields, popular probabilistic graphical models for sequence labeling. They take advantage of a consistency model, which is automatically induced during processing the document. The approach based on stacked graphical models utilizes the learnt descriptions as feature functions that have a static meaning for the model, but change their actual function for each document. The other two models extend the graph structure with additional factors dependent on the learnt model of consistency. They include feature functions for consistent and inconsistent entities as well as for additional positions that fulfill the consistencies. The presented approaches are evaluated in three real-world domains: segmentation of scientific references, template extraction in curricula vitae, and identification and categorization of sections in clinical discharge letters. They are able to achieve remarkable results and provide an error reduction of up to 30\% compared to usually applied techniques.},
  subject      = {Information Extraction},
  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}
}