@phdthesis{Peindl2024,
  author    = {Peindl, Matthias},
  title     = {Refinement of 3D lung cancer models for automation and patient stratification with mode-of-action studies},
  doi       = {10.25972/OPUS-31069},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310693},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2024},
  abstract  = {Lung cancer is the main cause of cancer-related deaths worldwide. Despite the availability of several targeted therapies and immunotherapies in the clinics, the prognosis for lung cancer remains poor. A major problem for the low benefit of these therapies is intrinsic and acquired resistance, asking for pre-clinical models for closer investigation of predictive biomarkers for refined personalized medicine and testing of possible combination therapies as well as novel therapeutic approaches to break resistances. One third of all lung adenocarcinoma harbor mutations in the KRAS gene, of which 39 \% are transitions from glycine to cysteine in codon 12 (KRASG12C). Being considered "undruggable" in previous decades, KRASG12C-inhibitors now paved the way into the standard-of-care for lung adenocarcinoma treatment in the clinics. Still, the overall response rates as well as overall survival of patients treated with KRASG12C-inhibitors are sobering. Therefore, 3D KRASG12C-biomarker in vitro models were developed based on a decellularized porcine jejunum (SISmuc) using commercial and PDX-derived cell lines and characterized in regards of epithelial-mesenchymal-transition (EMT), stemness, proliferation, invasion and c-MYC expression as well as the sensitivity towards KRASG12C-inhibiton. The phenotype of lung tumors harboring KRAS mutations together with a c-MYC overexpression described in the literature regarding invasion and proliferation for in vivo models was well represented in the SISmuc models. A higher resistance towards targeted therapies was validated in the 3D models compared to 2D cultures, while reduced viability after treatment with combination therapies were exclusively observed in the 3D models. In the test system neither EMT, stemness nor the c-MYC expression were directly predictive for drug sensitivity. Testing of a panel of combination therapies, a sensitizing effect of the aurora kinase A (AURKA) inhibitor alisertib for the KRASG12C-inhibitor ARS-1620 directly correlating with the level of c-MYC expression in the corresponding 3D models was observed. Thereby, the capability of SISmuc tumor models as an in vitro test system for patient stratification was demonstrated, holding the possibility to reduce animal experiments. Besides targeted therapies the treatment of NSCLC with oncolytic viruses (OVs) is a promising approach. However, a lack of in vitro models to test novel OVs limits the transfer from bench to bedside. In this study, 3D NSCLC models based on the SISmuc were evaluated for their capability to perform efficacy and risk assessment of oncolytic viruses (OVs) in a pre-clinical setting. Hereby, the infection of cocultures of tumor cells and fibroblasts on the SISmuc with provided viruses demonstrated that in contrast to a wildtype herpes simplex virus 1 (HSV-1) based OV, the attenuated version of the OV exhibited specificity for NSCLC cells with a more advanced and highly proliferative phenotype, while fibroblasts were no longer permissive for infection. This approach introduced SISmuc tumor models as novel test system for in vitro validation of OVs. Finally, a workflow for validating the efficacy of anti-cancer therapies in 3D tumor spheroids was established for the transfer to an automated platform based on a two-arm-robot system. In a proof-of-concept process, H358 spheroids were characterized and treated with the KRASG12C-inhibitor ARS-1620. A time- and dose-dependent reduction of the spheroid area after treatment was defined together with a live/dead-staining as easy-to-perform and cost-effective assays for automated drug testing that can be readily performed in situ in an automated system.},
  subject      = {Krebs <Medizin>},
  language  = {en}
}
@phdthesis{Wandtner2018,
  author    = {Wandtner, Bernhard},
  title     = {Non-driving related tasks in highly automated driving - Effects of task characteristics and drivers' self-regulation on take-over performance},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-173956},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2018},
  abstract  = {The rise of automated driving will fundamentally change our mobility in the near future. This thesis specifically considers the stage of so called highly automated driving (Level 3, SAE International, 2014). At this level, a system carries out vehicle guidance in specific application areas, e.g. on highway roads. The driver can temporarily suspend from monitoring the driving task and might use the time by engaging in so called non-driving related tasks (NDR-tasks). However, the driver is still in charge to resume vehicle control when prompted by the system. This new role of the driver has to be critically examined from a human factors perspective. The main aim of this thesis was to systematically investigate the impact of different NDR-tasks on driver behavior and take-over performance. Wickens' (2008) architecture of multiple resource theory was chosen as theoretical framework, with the building blocks of multiplicity (task interference due to resource overlap), mental workload (task demands), and aspects of executive control or self-regulation. Specific adaptations and extensions of the theory were discussed to account for the context of NDR-task interactions in highly automated driving. Overall four driving simulator studies were carried out to investigate the role of these theoretical components. Study 1 showed that drivers focused NDR-task engagement on sections of highly automated compared to manual driving. In addition, drivers avoided task engagement prior to predictable take-over situations. These results indicate that self-regulatory behavior, as reported for manual driving, also takes place in the context of highly automated driving. Study 2 specifically addressed the impact of NDR-tasks' stimulus and response modalities on take-over performance. Results showed that particularly visual-manual tasks with high motoric load (including the need to get rid of a handheld object) had detrimental effects. However, drivers seemed to be aware of task specific distraction in take-over situations and strictly canceled visual-manual tasks compared to a low impairing auditory-vocal task. Study 3 revealed that also the mental demand of NDR-tasks should be considered for drivers' take-over performance. Finally, different human-machine-interfaces were developed and evaluated in Simulator Study 4. Concepts including an explicit pre-alert ("notification") clearly supported drivers' self-regulation and achieved high usability and acceptance ratings. Overall, this thesis indicates that the architecture of multiple resource theory provides a useful framework for research in this field. Practical implications arise regarding the potential legal regulation of NDR-tasks as well as the design of elaborated human-machine-interfaces.},
  subject      = {Autonomes Fahrzeug},
  language  = {en}
}
@phdthesis{Zuefle2022,
  author    = {Z{\"u}fle, Marwin Otto},
  title     = {Proactive Critical Event Prediction based on Monitoring Data with Focus on Technical Systems},
  doi       = {10.25972/OPUS-25575},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-255757},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {The importance of proactive and timely prediction of critical events is steadily increasing, whether in the manufacturing industry or in private life. In the past, machines in the manufacturing industry were often maintained based on a regular schedule or threshold violations, which is no longer competitive as it causes unnecessary costs and downtime. In contrast, the predictions of critical events in everyday life are often much more concealed and hardly noticeable to the private individual, unless the critical event occurs. For instance, our electricity provider has to ensure that we, as end users, are always supplied with sufficient electricity, or our favorite streaming service has to guarantee that we can watch our favorite series without interruptions. For this purpose, they have to constantly analyze what the current situation is, how it will develop in the near future, and how they have to react in order to cope with future conditions without causing power outages or video stalling. In order to analyze the performance of a system, monitoring mechanisms are often integrated to observe characteristics that describe the workload and the state of the system and its environment. Reactive systems typically employ thresholds, utility functions, or models to determine the current state of the system. However, such reactive systems cannot proactively estimate future events, but only as they occur. In the case of critical events, reactive determination of the current system state is futile, whereas a proactive system could have predicted this event in advance and enabled timely countermeasures. To achieve proactivity, the system requires estimates of future system states. Given the gap between design time and runtime, it is typically not possible to use expert knowledge to a priori model all situations a system might encounter at runtime. Therefore, prediction methods must be integrated into the system. Depending on the available monitoring data and the complexity of the prediction task, either time series forecasting in combination with thresholding or more sophisticated machine and deep learning models have to be trained. Although numerous forecasting methods have been proposed in the literature, these methods have their advantages and disadvantages depending on the characteristics of the time series under consideration. Therefore, expert knowledge is required to decide which forecasting method to choose. However, since the time series observed at runtime cannot be known at design time, such expert knowledge cannot be implemented in the system. In addition to selecting an appropriate forecasting method, several time series preprocessing steps are required to achieve satisfactory forecasting accuracy. In the literature, this preprocessing is often done manually, which is not practical for autonomous computing systems, such as Self-Aware Computing Systems. Several approaches have also been presented in the literature for predicting critical events based on multivariate monitoring data using machine and deep learning. However, these approaches are typically highly domain-specific, such as financial failures, bearing failures, or product failures. Therefore, they require in-depth expert knowledge. For this reason, these approaches cannot be fully automated and are not transferable to other use cases. Thus, the literature lacks generalizable end-to-end workflows for modeling, detecting, and predicting failures that require only little expert knowledge. To overcome these shortcomings, this thesis presents a system model for meta-self-aware prediction of critical events based on the LRA-M loop of Self-Aware Computing Systems. Building upon this system model, this thesis provides six further contributions to critical event prediction. While the first two contributions address critical event prediction based on univariate data via time series forecasting, the three subsequent contributions address critical event prediction for multivariate monitoring data using machine and deep learning algorithms. Finally, the last contribution addresses the update procedure of the system model. Specifically, the seven main contributions of this thesis can be summarized as follows: First, we present a system model for meta self-aware prediction of critical events. To handle both univariate and multivariate monitoring data, it offers univariate time series forecasting for use cases where a single observed variable is representative of the state of the system, and machine learning algorithms combined with various preprocessing techniques for use cases where a large number of variables are observed to characterize the system's state. However, the two different modeling alternatives are not disjoint, as univariate time series forecasts can also be included to estimate future monitoring data as additional input to the machine learning models. Finally, a feedback loop is incorporated to monitor the achieved prediction quality and trigger model updates. We propose a novel hybrid time series forecasting method for univariate, seasonal time series, called Telescope. To this end, Telescope automatically preprocesses the time series, performs a kind of divide-and-conquer technique to split the time series into multiple components, and derives additional categorical information. It then forecasts the components and categorical information separately using a specific state-of-the-art method for each component. Finally, Telescope recombines the individual predictions. As Telescope performs both preprocessing and forecasting automatically, it represents a complete end-to-end approach to univariate seasonal time series forecasting. Experimental results show that Telescope achieves enhanced forecast accuracy, more reliable forecasts, and a substantial speedup. Furthermore, we apply Telescope to the scenario of predicting critical events for virtual machine auto-scaling. Here, results show that Telescope considerably reduces the average response time and significantly reduces the number of service level objective violations. For the automatic selection of a suitable forecasting method, we introduce two frameworks for recommending forecasting methods. The first framework extracts various time series characteristics to learn the relationship between them and forecast accuracy. In contrast, the other framework divides the historical observations into internal training and validation parts to estimate the most appropriate forecasting method. Moreover, this framework also includes time series preprocessing steps. Comparisons between the proposed forecasting method recommendation frameworks and the individual state-of-the-art forecasting methods and the state-of-the-art forecasting method recommendation approach show that the proposed frameworks considerably improve the forecast accuracy. With regard to multivariate monitoring data, we first present an end-to-end workflow to detect critical events in technical systems in the form of anomalous machine states. The end-to-end design includes raw data processing, phase segmentation, data resampling, feature extraction, and machine tool anomaly detection. In addition, the workflow does not rely on profound domain knowledge or specific monitoring variables, but merely assumes standard machine monitoring data. We evaluate the end-to-end workflow using data from a real CNC machine. The results indicate that conventional frequency analysis does not detect the critical machine conditions well, while our workflow detects the critical events very well with an F1-score of almost 91\%. To predict critical events rather than merely detecting them, we compare different modeling alternatives for critical event prediction in the use case of time-to-failure prediction of hard disk drives. Given that failure records are typically significantly less frequent than instances representing the normal state, we employ different oversampling strategies. Next, we compare the prediction quality of binary class modeling with downscaled multi-class modeling. Furthermore, we integrate univariate time series forecasting into the feature generation process to estimate future monitoring data. Finally, we model the time-to-failure using not only classification models but also regression models. The results suggest that multi-class modeling provides the overall best prediction quality with respect to practical requirements. In addition, we prove that forecasting the features of the prediction model significantly improves the critical event prediction quality. We propose an end-to-end workflow for predicting critical events of industrial machines. Again, this approach does not rely on expert knowledge except for the definition of monitoring data, and therefore represents a generalizable workflow for predicting critical events of industrial machines. The workflow includes feature extraction, feature handling, target class mapping, and model learning with integrated hyperparameter tuning via a grid-search technique. Drawing on the result of the previous contribution, the workflow models the time-to-failure prediction in terms of multiple classes, where we compare different labeling strategies for multi-class classification. The evaluation using real-world production data of an industrial press demonstrates that the workflow is capable of predicting six different time-to-failure windows with a macro F1-score of 90\%. When scaling the time-to-failure classes down to a binary prediction of critical events, the F1-score increases to above 98\%. Finally, we present four update triggers to assess when critical event prediction models should be re-trained during on-line application. Such re-training is required, for instance, due to concept drift. The update triggers introduced in this thesis take into account the elapsed time since the last update, the prediction quality achieved on the current test data, and the prediction quality achieved on the preceding test data. We compare the different update strategies with each other and with the static baseline model. The results demonstrate the necessity of model updates during on-line application and suggest that the update triggers that consider both the prediction quality of the current and preceding test data achieve the best trade-off between prediction quality and number of updates required. We are convinced that the contributions of this thesis constitute significant impulses for the academic research community as well as for practitioners. First of all, to the best of our knowledge, we are the first to propose a fully automated, end-to-end, hybrid, component-based forecasting method for seasonal time series that also includes time series preprocessing. Due to the combination of reliably high forecast accuracy and reliably low time-to-result, it offers many new opportunities in applications requiring accurate forecasts within a fixed time period in order to take timely countermeasures. In addition, the promising results of the forecasting method recommendation systems provide new opportunities to enhance forecasting performance for all types of time series, not just seasonal ones. Furthermore, we are the first to expose the deficiencies of the prior state-of-the-art forecasting method recommendation system. Concerning the contributions to critical event prediction based on multivariate monitoring data, we have already collaborated closely with industrial partners, which supports the practical relevance of the contributions of this thesis. The automated end-to-end design of the proposed workflows that do not demand profound domain or expert knowledge represents a milestone in bridging the gap between academic theory and industrial application. Finally, the workflow for predicting critical events in industrial machines is currently being operationalized in a real production system, underscoring the practical impact of this thesis.},
  subject      = {Prognose},
  language  = {en}
}