@unpublished{30790, abstract = {{Iterative distributed optimization algorithms involve multiple agents that communicate with each other, over time, in order to minimize/maximize a global objective. In the presence of unreliable communication networks, the Age-of-Information (AoI), which measures the freshness of data received, may be large and hence hinder algorithmic convergence. In this paper, we study the convergence of general distributed gradient-based optimization algorithms in the presence of communication that neither happens periodically nor at stochastically independent points in time. We show that convergence is guaranteed provided the random variables associated with the AoI processes are stochastically dominated by a random variable with finite first moment. This improves on previous requirements of boundedness of more than the first moment. We then introduce stochastically strongly connected (SSC) networks, a new stochastic form of strong connectedness for time-varying networks. We show: If for any $p \ge0$ the processes that describe the success of communication between agents in a SSC network are $\alpha$-mixing with $n^{p-1}\alpha(n)$ summable, then the associated AoI processes are stochastically dominated by a random variable with finite $p$-th moment. In combination with our first contribution, this implies that distributed stochastic gradient descend converges in the presence of AoI, if $\alpha(n)$ is summable.}}, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, booktitle = {{arXiv:2201.11343}}, title = {{{Distributed gradient-based optimization in the presence of dependent aperiodic communication}}}, year = {{2022}}, } @inproceedings{31806, abstract = {{The creation of an RDF knowledge graph for a particular application commonly involves a pipeline of tools that transform a set ofinput data sources into an RDF knowledge graph in a process called dataset augmentation. The components of such augmentation pipelines often require extensive configuration to lead to satisfactory results. Thus, non-experts are often unable to use them. Wepresent an efficient supervised algorithm based on genetic programming for learning knowledge graph augmentation pipelines of arbitrary length. Our approach uses multi-expression learning to learn augmentation pipelines able to achieve a high F-measure on the training data. Our evaluation suggests that our approach can efficiently learn a larger class of RDF dataset augmentation tasks than the state of the art while using only a single training example. Even on the most complex augmentation problem we posed, our approach consistently achieves an average F1-measure of 99% in under 500 iterations with an average runtime of 16 seconds}}, author = {{Dreßler, Kevin and Sherif, Mohamed and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Proceedings of the 33rd ACM Conference on Hypertext and Hypermedia}}, keywords = {{2022 RAKI SFB901 deer dice kevin knowgraphs limes ngonga sherif simba}}, location = {{Barcelona (Spain)}}, title = {{{ADAGIO - Automated Data Augmentation of Knowledge Graphs Using Multi-expression Learning}}}, doi = {{10.1145/3511095.3531287}}, year = {{2022}}, } @article{32854, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, journal = {{IFAC-PapersOnLine}}, number = {{13}}, pages = {{133–138}}, publisher = {{Elsevier}}, title = {{{Practical Network Conditions for the Convergence of Distributed Optimization}}}, volume = {{55}}, year = {{2022}}, } @inproceedings{33253, author = {{Hansmeier, Tim and Brede, Mathis and Platzner, Marco}}, booktitle = {{GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion}}, location = {{Boston, MA, USA}}, pages = {{2071--2079}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{XCS on Embedded Systems: An Analysis of Execution Profiles and Accelerated Classifier Deletion}}}, doi = {{10.1145/3520304.3533977}}, year = {{2022}}, } @inproceedings{34152, author = {{Otroshi, Mortaza and Meschut, Gerson}}, location = {{Rostock}}, publisher = {{Europäische Forschungsgesellschaft für Blechverarbeitung e.V. }}, title = {{{Methodenentwicklung zur Verbesserung der Schädigungsmodellierung in der numerischen 3D-Belastungssimulation mechanischer Fügeverfahren unter Berücksichtigung der fügeinduzierten Vorbeanspruchung}}}, year = {{2022}}, } @article{34417, abstract = {{Given strict emission targets and legal requirements, especially in the automotive industry, environmentally friendly and simultaneously versatile applicable production technologies are gaining importance. In this regard, the use of mechanical joining processes, such as clinching, enable assembly sheet metals to achieve strength properties similar to those of established thermal joining technologies. However, to guarantee a high reliability of the generated joint connection, the selection of a best-fitting joining technology as well as the meaningful description of individual joint properties is essential. In the context of clinching, few contributions have to date investigated the metamodel-based estimation and optimization of joint characteristics, such as neck or interlock thickness, by applying machine learning and genetic algorithms. Therefore, several regression models have been trained on varying databases and amounts of input parameters. However, if product engineers can only provide limited data for a new joining task, such as incomplete information on applied joining tool dimensions, previously trained metamodels often reach their limits. This often results in a significant loss of prediction quality and leads to increasing uncertainties and inaccuracies within the metamodel-based design of a clinch joint connection. Motivated by this, the presented contribution investigates different machine learning algorithms regarding their ability to achieve a satisfying estimation accuracy on limited input data applying a statistically based feature selection method. Through this, it is possible to identify which regression models are suitable to predict clinch joint characteristics considering only a minimum set of required input features. Thus, in addition to the opportunity to decrease the training effort as well as the model complexity, the subsequent formulation of design equations can pave the way to a more versatile application and reuse of pretrained metamodels on varying tool configurations for a given clinch joining task.}}, author = {{Zirngibl, Christoph and Schleich, Benjamin and Wartzack, Sandro}}, issn = {{2673-2688}}, journal = {{AI}}, keywords = {{Industrial and Manufacturing Engineering}}, number = {{4}}, pages = {{990--1006}}, publisher = {{MDPI AG}}, title = {{{Estimation of Clinch Joint Characteristics Based on Limited Input Data Using Pre-Trained Metamodels}}}, doi = {{10.3390/ai3040059}}, volume = {{3}}, year = {{2022}}, } @unpublished{34618, abstract = {{In this article, we show how second-order derivative information can be incorporated into gradient sampling methods for nonsmooth optimization. The second-order information we consider is essentially the set of coefficients of all second-order Taylor expansions of the objective in a closed ball around a given point. Based on this concept, we define a model of the objective as the maximum of these Taylor expansions. Iteratively minimizing this model (constrained to the closed ball) results in a simple descent method, for which we prove convergence to minimal points in case the objective is convex. To obtain an implementable method, we construct an approximation scheme for the second-order information based on sampling objective values, gradients and Hessian matrices at finitely many points. Using a set of test problems, we compare the resulting method to five other available solvers. Considering the number of function evaluations, the results suggest that the method we propose is superior to the standard gradient sampling method, and competitive compared to other methods.}}, author = {{Gebken, Bennet}}, booktitle = {{arXiv:2210.04579}}, title = {{{Using second-order information in gradient sampling methods for nonsmooth optimization}}}, year = {{2022}}, } @inproceedings{29342, author = {{Sander, Sascha and Teutenberg, Dominik and Meschut, Gerson and Kötz, Fabian and Matzenmiller, Anton and Kasper, Yann and Ummenhofer, Thomas}}, booktitle = {{22. Kolloquium Gemeinsame Forschung in der Klebtechnik}}, location = {{Online Konferenz}}, title = {{{Methodenentwicklung zur rechnerischen Auslegung geklebter Stahlverbindungen unter Alterungsbeanspruchung im Stahl- und Anlagenbau }}}, year = {{2022}}, } @inproceedings{29302, abstract = {{This paper introduces the project Scale4Edge. The project is focused on enabling an effective RISC-V ecosystem for optimization of edge applications. We describe the basic components of this ecosystem and introduce the envisioned demonstrators, which will be used in their evaluation.}}, author = {{Ecker, Wolfgang and Adelt, Peer and Müller, Wolfgang and Heckmann, Reinhold and Krstic, Milos and Herdt, Vladimir and Drechsler, Rolf and Angst, Gerhard and Wimmer, Ralf and Mauderer, Andreas and Stahl, Rafael and Emrich, Karsten and Mueller-Gritschneder, Daniel and Becker, Bernd and Scholl, Philipp and Jentzsch, Eyck and Schlamelcher, Jan and Grüttner, Kim and Bernardo, Paul Palomero and Brinkmann, Oliver and Damian, Mihaela and Oppermann, Julian and Koch, Andreas and Bormann, Jörg and Partzsch, Johannes and Mayr, Christian and Kunz, Wolfgang}}, booktitle = {{In Proceedings of the Design Automation and Test Conference and Exhibition (DATE 2022)}}, title = {{{The Scale4Edge RISC-V Ecosystem}}}, year = {{2022}}, } @unpublished{31545, abstract = {{Knowledge graph embedding research has mainly focused on learning continuous representations of entities and relations tailored towards the link prediction problem. Recent results indicate an ever increasing predictive ability of current approaches on benchmark datasets. However, this effectiveness often comes with the cost of over-parameterization and increased computationally complexity. The former induces extensive hyperparameter optimization to mitigate malicious overfitting. The latter magnifies the importance of winning the hardware lottery. Here, we investigate a remedy for the first problem. We propose a technique based on Kronecker decomposition to reduce the number of parameters in a knowledge graph embedding model, while retaining its expressiveness. Through Kronecker decomposition, large embedding matrices are split into smaller embedding matrices during the training process. Hence, embeddings of knowledge graphs are not plainly retrieved but reconstructed on the fly. The decomposition ensures that elementwise interactions between three embedding vectors are extended with interactions within each embedding vector. This implicitly reduces redundancy in embedding vectors and encourages feature reuse. To quantify the impact of applying Kronecker decomposition on embedding matrices, we conduct a series of experiments on benchmark datasets. Our experiments suggest that applying Kronecker decomposition on embedding matrices leads to an improved parameter efficiency on all benchmark datasets. Moreover, empirical evidence suggests that reconstructed embeddings entail robustness against noise in the input knowledge graph. To foster reproducible research, we provide an open-source implementation of our approach, including training and evaluation scripts as well as pre-trained models in our knowledge graph embedding framework.}}, author = {{Demir, Caglar and Lienen, Julian and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{arXiv:2205.06560}}, title = {{{Kronecker Decomposition for Knowledge Graph Embeddings}}}, year = {{2022}}, } @phdthesis{31556, abstract = {{Mehrzieloptimierung behandelt Probleme, bei denen mehrere skalare Zielfunktionen simultan optimiert werden sollen. Ein Punkt ist in diesem Fall optimal, wenn es keinen anderen Punkt gibt, der mindestens genauso gut ist in allen Zielfunktionen und besser in mindestens einer Zielfunktion. Ein notwendiges Optimalitätskriterium lässt sich über Ableitungsinformationen erster Ordnung der Zielfunktionen herleiten. Die Menge der Punkte, die dieses notwendige Kriterium erfüllen, wird als Pareto-kritische Menge bezeichnet. Diese Arbeit enthält neue Resultate über Pareto-kritische Mengen für glatte und nicht-glatte Mehrzieloptimierungsprobleme, sowohl was deren Berechnung betrifft als auch deren Struktur. Im glatten Fall erfolgt die Berechnung über ein Fortsetzungsverfahren, im nichtglatten Fall über ein Abstiegsverfahren. Anschließend wird die Struktur des Randes der Pareto-kritischen Menge analysiert, welcher aus Pareto-kritischen Mengen kleinerer Subprobleme besteht. Schlussendlich werden inverse Probleme betrachtet, bei denen zu einer gegebenen Datenmenge ein Zielfunktionsvektor gefunden werden soll, für den die Datenpunkte kritisch sind.}}, author = {{Gebken, Bennet}}, title = {{{Computation and analysis of Pareto critical sets in smooth and nonsmooth multiobjective optimization}}}, doi = {{10.17619/UNIPB/1-1327}}, year = {{2022}}, } @article{33009, abstract = {{Abstract Purpose The present work aimed to delineate (i) a revised protocol according to recent methodological developments in evidence generation, to (ii) describe its interpretation, the assessment of the overall certainty of evidence and to (iii) outline an Evidence to Decision framework for deriving an evidence-based guideline on quantitative and qualitative aspects of dietary protein intake. Methods A methodological protocol to systematically investigate the association between dietary protein intake and several health outcomes and for deriving dietary protein intake recommendations for the primary prevention of various non-communicable diseases in the general adult population was developed. Results The developed methodological protocol relies on umbrella reviews including systematic reviews with or without meta-analyses. Systematic literature searches in three databases will be performed for each health-related outcome. The methodological quality of all selected systematic reviews will be evaluated using a modified version of AMSTAR 2, and the outcome-specific certainty of evidence for systematic reviews with or without meta-analysis will be assessed with NutriGrade. The general outline of the Evidence to Decision framework foresees that recommendations in the derived guideline will be given based on the overall certainty of evidence as well as on additional criteria such as sustainability. Conclusion The methodological protocol permits a systematic evaluation of published systematic reviews on dietary protein intake and its association with selected health-related outcomes. An Evidence to Decision framework will be the basis for the overall conclusions and the resulting recommendations for dietary protein intake. }}, author = {{Kroke, Anja and Schmidt, Annemarie and Amini, Anna M. and Kalotai, Nicole and Lehmann, Andreas and Haardt, Julia and Bauer, Jürgen M. and Bischoff-Ferrari, Heike A. and Boeing, Heiner and Egert, Sarah and Ellinger, Sabine and Kühn, Tilman and Louis, Sandrine and Lorkowski, Stefan and Nimptsch, Katharina and Remer, Thomas and Schulze, Matthias B. and Siener, Roswitha and Stangl, Gabriele I. and Volkert, Dorothee and Zittermann, Armin and Buyken, Anette E. and Watzl, Bernhard and Schwingshackl, Lukas}}, issn = {{1436-6207}}, journal = {{European Journal of Nutrition}}, keywords = {{Nutrition and Dietetics, Medicine (miscellaneous)}}, number = {{4}}, pages = {{2091--2101}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Dietary protein intake and health-related outcomes: a methodological protocol for the evidence evaluation and the outline of an evidence to decision framework underlying the evidence-based guideline of the German Nutrition Society}}}, doi = {{10.1007/s00394-021-02789-5}}, volume = {{61}}, year = {{2022}}, } @inproceedings{29934, abstract = {{Tire and road wear are a major source of emissions of nonexhaust particulate matter (PM) and make up the largest share of microplastics in the environment. To reduce tire wear through numerical optimization of a vehicle's suspension system, fast simulations of the representative usage of a vehicle are needed. Therefore, this contribution evaluates if instead of a full simulation of a representative test drive, only specific driving maneuvers resulting from a clustering of the driving data can be used to predict tire wear. As a measure for tire wear, the friction work between tire and road is calculated. It is shown that enough clusters result in negligible deviations between the total friction work of the full simulation and the cluster simulations as well as between the distributions of the friction work over the tire width. The calculation time can be reduced to about 1% of the full simulation.}}, author = {{Muth, Lars and Noll, Christian and Sextro, Walter}}, booktitle = {{Advances in Dynamics of Vehicles on Roads and Tracks II - Proceedings of the 27th Symposium of the International Association of Vehicle System Dynamics, IAVSD 2021}}, editor = {{Orlova, Anna and Cole, David}}, isbn = {{978-3-031-07304-5}}, keywords = {{Tire Wear, Vehicle Dynamics, Clustering, Virtual Test}}, location = {{Saint Petersburg, Russia}}, publisher = {{Springer}}, title = {{{Generation of a Reduced, Representative, Virtual Test Drive for Fast Evaluation of Tire Wear by Clustering of Driving Data}}}, doi = {{10.1007/978-3-031-07305-2_92}}, year = {{2022}}, } @article{33090, abstract = {{AbstractHeated tool butt welding is a method often used for joining thermoplastics, especially when the components are made out of different materials. The quality of the connection between the components crucially depends on a suitable choice of the parameters of the welding process, such as heating time, temperature, and the precise way how the parts are then welded. Moreover, when different materials are to be joined, the parameter values need to be tailored to the specifics of the respective material. To this end, in this paper, three approaches to tailor the parameter values to optimize the quality of the connection are compared: a heuristic by Potente, statistical experimental design, and Bayesian optimization. With the suitability for practice in mind, a series of experiments are carried out with these approaches, and their capabilities of proposing well-performing parameter values are investigated. As a result, Bayesian optimization is found to yield peak performance, but the costs for optimization are substantial. In contrast, the Potente heuristic does not require any experimentation and recommends parameter values with competitive quality.}}, author = {{Gevers, Karina and Tornede, Alexander and Wever, Marcel Dominik and Schöppner, Volker and Hüllermeier, Eyke}}, issn = {{0043-2288}}, journal = {{Welding in the World}}, keywords = {{Metals and Alloys, Mechanical Engineering, Mechanics of Materials}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{A comparison of heuristic, statistical, and machine learning methods for heated tool butt welding of two different materials}}}, doi = {{10.1007/s40194-022-01339-9}}, year = {{2022}}, } @unpublished{33150, abstract = {{In this article, we build on previous work to present an optimization algorithm for nonlinearly constrained multi-objective optimization problems. The algorithm combines a surrogate-assisted derivative-free trust-region approach with the filter method known from single-objective optimization. Instead of the true objective and constraint functions, so-called fully linear models are employed and we show how to deal with the gradient inexactness in the composite step setting, adapted from single-objective optimization as well. Under standard assumptions, we prove convergence of a subset of iterates to a quasi-stationary point and if constraint qualifications hold, then the limit point is also a KKT-point of the multi-objective problem.}}, author = {{Berkemeier, Manuel Bastian and Peitz, Sebastian}}, booktitle = {{arXiv:2208.12094}}, title = {{{Multi-Objective Trust-Region Filter Method for Nonlinear Constraints using Inexact Gradients}}}, year = {{2022}}, } @inproceedings{33240, author = {{Götte, Thorsten and Scheideler, Christian}}, booktitle = {{SPAA ’22: 34th ACM Symposium on Parallelism in Algorithms and Architectures, Philadelphia, PA, USA, July 11 - 14, 2022}}, editor = {{Agrawal, Kunal and Lee, I-Ting Angelina}}, pages = {{99–101}}, publisher = {{ACM}}, title = {{{Brief Announcement: The (Limited) Power of Multiple Identities: Asynchronous Byzantine Reliable Broadcast with Improved Resilience through Collusion}}}, doi = {{10.1145/3490148.3538556}}, year = {{2022}}, } @inbook{30941, abstract = {{Decision support systems are crucial in helping decision makers to quickly identify optimal business decisions in increasingly volatile and complex business environments. However, the ideal DSS for one decision maker may not optimally address the requirements for decision support of another decision maker. This is due to differences between decision makers in business goals, regulatory restrictions or availability of resources such as data. By using a suboptimal DSS, decision makers risk implementing suboptimal decision recommendations which endanger the success of their business. This presents DSS developers with the challenge to implement a customizable DSS which can be tailored to the individual requirements for decision support of a single decision maker. In order to address this challenge, we suggest a decision support ecosystem in which DSS developers, decision makers and other domain experts collaborate using a shared platform to provide and combine reusable decision support services into a tailored DSS. The contribution of our paper is twofold: First, we define the concept of a decision support ecosystem with respect to existing digital business ecosystems and discuss expected benefits and challenges. Second, we present a reference architecture for a shared platform supporting the realization of a decision support ecosystem. We demonstrate our contributions in the example application domain of regional energy distribution network planning.}}, author = {{Kirchhoff, Jonas and Weskamp, Christoph and Engels, Gregor}}, booktitle = {{Decision Support Systems XII: Decision Support Addressing Modern Industry, Business, and Societal Needs}}, publisher = {{Springer}}, title = {{{Decision Support Ecosystems: Definition and Platform Architecture}}}, doi = {{10.1007/978-3-031-06530-9_8}}, volume = {{447}}, year = {{2022}}, } @inproceedings{33508, abstract = {{In this work, methods will be evaluated to numerically calculate the passive electrical parameters of planar coils. These parameters can then be used to optimize inductive applications such as wireless power transmission. The focus here will be on inductive localization, which uses high-frequency magnetic fields and the resulting induced voltage to provide localization through the coupling parameter mutual inductance. To achieve localization with high accuracy and best possible operation (resonance, signal strength, etc.), the coil parameters need to be well known. For this reason, some numerical methods for the calculation of these quantities are presented and validated. In addition, the physical effects are thereby considered in more detail, allowing the localization procedure to be better optimized compared to simulative black-box methods. The goal should be a dedicated simulation platform for planar coils to be able to develop training data for neural networks and to test and optimize localization algorithms.}}, author = {{Lange, Sven and Hedayat, Christian and Kuhn, Harald and Hilleringmann, Ulrich}}, booktitle = {{2022 Smart Systems Integration (SSI)}}, keywords = {{Simulation Environment, Inductive Localization, Coil Parameters, Inductive Applications, Near-Field}}, location = {{Grenoble, France}}, publisher = {{IEEE}}, title = {{{Modeling and Characterization of a 3D Environment for the Design of an Inductively Based Locating Method by Coil Couplings}}}, doi = {{10.1109/ssi56489.2022.9901416}}, year = {{2022}}, } @article{33714, abstract = {{AbstractIndustry 4.0 promises many potentials in production. Examples are a data-driven optimization of production processes of individual machines, driverless transport systems, and assistance systems. Nevertheless, companies are still hesitant to invest in Industry 4.0 applications. Studies show that one of the main reasons for that is the unclear economic benefit. In this work, we present a systematic approach for the evaluation of Industry 4.0 applications in production. The main goal of the systematic is to create transparency over the evaluation process of an investment in an Industry 4.0 application in production. The evaluation of a concrete technical solution in an existing production system is supported. As a theoretical foundation, a characterization of investments in Industry 4.0 applications is given. From that, a procedure model is derived. It puts the activities to be carried out, the tools to be used and results in a temporal context. The application of the systematic is shown on the basis of an application example.}}, author = {{Joppen, Robert and Kühn, Arno and Förster, Magdalena and Dumitrescu, Roman}}, issn = {{1868-7865}}, journal = {{Journal of the Knowledge Economy}}, keywords = {{Economics and Econometrics}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Evaluation of Industry 4.0 Applications in Production}}}, doi = {{10.1007/s13132-022-00959-2}}, year = {{2022}}, } @article{33713, abstract = {{AbstractThe development of technical systems requires close cooperation of stakeholders from different disciplines. This collaboration takes place in workshops. Driven by digitalization and by the current pandemic such workshops take place primarily online. Suitable collaboration tools and methods are crucial to success. At the beginning of such workshops, use and damage scenarios are identified. In this paper, we presented a method and tool for identifying and modeling use and damage scenarios, which we evaluated in 14 online workshops with a total of 118 participants over a period of almost 3 years.}}, author = {{Japs, Sergej and Schmidt, Sebastian and Kargl, Frank and Kaiser, Lydia and Kharatyan, Aschot and Dumitrescu, Roman}}, issn = {{2732-527X}}, journal = {{Proceedings of the Design Society}}, pages = {{1599--1608}}, publisher = {{Cambridge University Press (CUP)}}, title = {{{Collaborative Modeling of Use Case & Damage Scenarios in Online Workshops Using a 3D Environment}}}, doi = {{10.1017/pds.2022.162}}, volume = {{2}}, year = {{2022}}, }