TY - JOUR A1 - Lausser, Ludwig A1 - Schäfer, Lisa M. A1 - Schirra, Lyn-Rouven A1 - Szekely, Robin A1 - Schmid, Florian A1 - Kestler, Hans A. T1 - Assessing phenotype order in molecular data JF - Scientific Reports N2 - Biological entities are key elements of biomedical research. Their definition and their relationships are important in areas such as phylogenetic reconstruction, developmental processes or tumor evolution. Hypotheses about relationships like phenotype order are often postulated based on prior knowledge or belief. Evidence on a molecular level is typically unknown and whether total orders are reflected in the molecular measurements is unclear or not assessed. In this work we propose a method that allows a fast and exhaustive screening for total orders in large datasets. We utilise ordinal classifier cascades to identify discriminable molecular representations of the phenotypes. These classifiers are constrained by an order hypothesis and are highly sensitive to incorrect assumptions. Two new error bounds, which are introduced and theoretically proven, lead to a substantial speed-up and allow the application to large collections of many phenotypes. In our experiments we show that by exhaustively evaluating all possible candidate orders, we are able to identify phenotype orders that best coincide with the high-dimensional molecular profiles. UR - https://doi.org/10.1038/s41598-019-48150-z KW - machine learning KW - systems biology Y1 - 2019 UR - https://doi.org/10.1038/s41598-019-48150-z UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27353 SN - 2045-2322 VL - 9 PB - Springer Nature CY - London ER - TY - JOUR A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Klimmek, Attila A1 - Schmid, Florian A1 - Kestler, Hans A. T1 - Constraining classifiers in molecular analysis BT - invariance and robustness JF - Journal of the Royal Society Interface N2 - Analysing molecular profiles requires the selection of classification models that can cope with the high dimensionality and variability of these data. Also, improper reference point choice and scaling pose additional challenges. Often model selection is somewhat guided by ad hoc simulations rather than by sophisticated considerations on the properties of a categorization model. Here, we derive and report four linked linear concept classes/models with distinct invariance properties for high-dimensional molecular classification. We can further show that these concept classes also form a half-order of complexity classes in terms of Vapnik–Chervonenkis dimensions, which also implies increased generalization abilities. We implemented support vector machines with these properties. Surprisingly, we were able to attain comparable or even superior generalization abilities to the standard linear one on the 27 investigated RNA-Seq and microarray datasets. Our results indicate that a priori chosen invariant models can replace ad hoc robustness analysis by interpretable and theoretically guaranteed properties in molecular categorization. UR - https://doi.org/10.1098/rsif.2019.0612 KW - computational learning theory KW - classification KW - invariances KW - molecular profiles Y1 - 2020 UR - https://doi.org/10.1098/rsif.2019.0612 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27361 SN - 1742-5662 VL - 17 (2020) IS - 163 PB - The Royal Society CY - London ER - TY - JOUR A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Schmid, Florian A1 - Maucher, Markus A1 - Kestler, Hans A. T1 - Efficient cross-validation traversals in feature subset selection JF - Scientific Reports N2 - Sparse and robust classification models have the potential for revealing common predictive patterns that not only allow for categorizing objects into classes but also for generating mechanistic hypotheses. Identifying a small and informative subset of features is their main ingredient. However, the exponential search space of feature subsets and the heuristic nature of selection algorithms limit the coverage of these analyses, even for low-dimensional datasets. We present methods for reducing the computational complexity of feature selection criteria allowing for higher efficiency and coverage of screenings. We achieve this by reducing the preparation costs of high-dimensional subsets O(nm2) to those of one-dimensional ones O(m2). Our methods are based on a tight interaction between a parallelizable cross-validation traversal strategy and distance-based classification algorithms and can be used with any product distance or kernel. We evaluate the traversal strategy exemplarily in exhaustive feature subset selection experiments (perfect coverage). Its runtime, fitness landscape, and predictive performance are analyzed on publicly available datasets. Even in low-dimensional settings, we achieve approximately a 15-fold increase in exhaustively generating distance matrices for feature combinations bringing a new level of evaluations into reach. UR - https://doi.org/10.1038/s41598-022-25942-4 Y1 - 2022 UR - https://doi.org/10.1038/s41598-022-25942-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30299 SN - 2045-2322 VL - 12 PB - Springer Nature CY - London ER - TY - JOUR A1 - Schwertner, Stefan A1 - Buchberger, Tobias A1 - Diehl, Simon A1 - Ferg, Rebekka A1 - Hanzl, Christian A1 - Hartmann, Christoph A1 - Hölzle, Markus A1 - Kleiner, Jan A1 - Komsiyska, Lidiya A1 - Lewerenz, Meinert A1 - Liebhart, Bernhard A1 - Schmid, Michael A1 - Schneider, Dominik A1 - Scholz, Florian A1 - Speer, Sascha A1 - Stöttner, Julia A1 - Terbrack, Christoph A1 - Hinterberger, Michael A1 - Endisch, Christian T1 - Design and Implementation of an Intelligent Reconfigurable High-Voltage Battery System for Next-Generation Electric Vehicles JF - Batteries N2 - Battery system engineers face the challenge of balancing competing requirements regarding performance, maintainability, sustainability, safety, and cost—especially in the automotive industry. IBS potentially offer a solution with fewer trade-offs. They feature a battery management system with advanced sensing and data analysis capabilities that facilitate improved battery monitoring and operation. Reconfigurable energy storage units enable sophisticated operating strategies, including complete cell state control, full energy content utilization, and a measured response to faults. This article presents the design, development, and operation of a full-scale intelligent battery system prototype comprising 324 automotive lithium-ion cells with a nominal voltage of 400V. The system exhibits a modular single cell architecture and an advanced centralized battery management system. We detail the system architecture, hardware and software component design, and system integration. Initial tests demonstrate the battery’s operability, extended functionality, and enhanced safety. Our analysis shows that the additional losses introduced by reconfigurability are more than offset by the benefits of full energy utilization—even for new cells, with increasing advantage as aging progresses. The results underscore the potential of intelligent battery systems and motivate further research and development toward economic assessment and industrial adoption. UR - https://doi.org/10.3390/batteries11110424 Y1 - 2025 UR - https://doi.org/10.3390/batteries11110424 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-64086 SN - 2313-0105 VL - 11 IS - 11 PB - MDPI CY - Basel ER -