@inproceedings{27494, author = {{Hüsing, Sven}}, booktitle = {{Koli Calling '21: 21st Koli Calling International Conference on Computing Education Research, Joensuu, Finland, November 18 - 21, 2021}}, editor = {{Seppälä, Otto and Petersen, Andrew}}, pages = {{42:1--42:3}}, publisher = {{ACM}}, title = {{{Epistemic Programming - An insight-driven programming concept for Data Science}}}, doi = {{10.1145/3488042.3490510}}, year = {{2021}}, } @inproceedings{27495, author = {{Bovermann, Klaus and Fleischer, Yannik and Hüsing, Sven and Opitz, Christian}}, booktitle = {{19. GI-Fachtagung Informatik und Schule, INFOS 2021, Wuppertal, Germany, September 8-10, 2021}}, editor = {{Humbert, Ludger}}, pages = {{319}}, publisher = {{Gesellschaft für Informatik, Bonn}}, title = {{{Künstliche Intelligenz und maschinelles Lernen im Informatikunterricht der Sek. I mit Jupyter Notebooks und Python am Beispiel von Entscheidungsbäumen und künstlichen neuronalen Netzen}}}, doi = {{10.18420/infos2021\_w283}}, volume = {{P-313}}, year = {{2021}}, } @phdthesis{27503, author = {{Hasnain, Asif}}, title = {{{Automating Network Resource Allocation for Coflows with Deadlines}}}, doi = {{10.17619/UNIPB/1-1241 }}, year = {{2021}}, } @inbook{27504, author = {{Spath, Dieter and Gausemeier, Jürgen and Dumitrescu, Roman and Winter, Johannes and Steglich, Steffen and Drewel, Marvin}}, booktitle = {{ Handbook of Engineering Systems Design}}, editor = {{Maier, Anja and Oehmen, Josef and Vermaas, Pieter E.}}, pages = {{2--27}}, publisher = {{Springer, Cham}}, title = {{{Digitalisation of Society}}}, year = {{2021}}, } @inproceedings{27847, author = {{Lugovtsova, Yevgeniya and Zeipert, Henning and Johannesmann, Sarah and Nicolai, Marcel and Prager, Jens and Henning, Bernd}}, booktitle = {{МАТЕМАТИЧЕСКОЕ МОДЕЛИРОВАНИЕ В ЕСТЕСТВЕННЫХ НАУКАХ - XXX Всероссийская школа-конференция}}, location = {{Perm}}, title = {{{К ОПРЕДЕЛЕНИЮ ПРОЧНОСТИ КЛЕЕВОГО СОЕДИНЕНИЯ В МНОГОСЛОЙНЫХ МАТЕРИАЛАХ ПУТЕМ ИССЛЕДОВАНИЯ ОБЛАСТЕЙ РАСТАЛКИВАНИЯ БЕГУЩИХ УПРУГИХ ВОЛН}}}, year = {{2021}}, } @article{21004, abstract = {{Automated machine learning (AutoML) supports the algorithmic construction and data-specific customization of machine learning pipelines, including the selection, combination, and parametrization of machine learning algorithms as main constituents. Generally speaking, AutoML approaches comprise two major components: a search space model and an optimizer for traversing the space. Recent approaches have shown impressive results in the realm of supervised learning, most notably (single-label) classification (SLC). Moreover, first attempts at extending these approaches towards multi-label classification (MLC) have been made. While the space of candidate pipelines is already huge in SLC, the complexity of the search space is raised to an even higher power in MLC. One may wonder, therefore, whether and to what extent optimizers established for SLC can scale to this increased complexity, and how they compare to each other. This paper makes the following contributions: First, we survey existing approaches to AutoML for MLC. Second, we augment these approaches with optimizers not previously tried for MLC. Third, we propose a benchmarking framework that supports a fair and systematic comparison. Fourth, we conduct an extensive experimental study, evaluating the methods on a suite of MLC problems. We find a grammar-based best-first search to compare favorably to other optimizers.}}, author = {{Wever, Marcel Dominik and Tornede, Alexander and Mohr, Felix and Hüllermeier, Eyke}}, issn = {{0162-8828}}, journal = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}}, keywords = {{Automated Machine Learning, Multi Label Classification, Hierarchical Planning, Bayesian Optimization}}, pages = {{1--1}}, title = {{{AutoML for Multi-Label Classification: Overview and Empirical Evaluation}}}, doi = {{10.1109/tpami.2021.3051276}}, year = {{2021}}, } @inproceedings{21005, abstract = {{Data-parallel applications are developed using different data programming models, e.g., MapReduce, partition/aggregate. These models represent diverse resource requirements of application in a datacenter network, which can be represented by the coflow abstraction. The conventional method of creating hand-crafted coflow heuristics for admission or scheduling for different workloads is practically infeasible. In this paper, we propose a deep reinforcement learning (DRL)-based coflow admission scheme -- LCS -- that can learn an admission policy for a higher-level performance objective, i.e., maximize successful coflow admissions, without manual feature engineering. LCS is trained on a production trace, which has online coflow arrivals. The evaluation results show that LCS is able to learn a reasonable admission policy that admits more coflows than state-of-the-art Varys heuristic while meeting their deadlines.}}, author = {{Hasnain, Asif and Karl, Holger}}, booktitle = {{IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}}, keywords = {{Coflow scheduling, Reinforcement learning, Deadlines}}, location = {{Vancouver BC Canada}}, publisher = {{IEEE Communications Society}}, title = {{{Learning Coflow Admissions}}}, doi = {{10.1109/INFOCOMWKSHPS51825.2021.9484599}}, year = {{2021}}, } @article{21065, abstract = {{The machine recognition of speech spoken at a distance from the microphones, known as far-field automatic speech recognition (ASR), has received a significant increase of attention in science and industry, which caused or was caused by an equally significant improvement in recognition accuracy. Meanwhile it has entered the consumer market with digital home assistants with a spoken language interface being its most prominent application. Speech recorded at a distance is affected by various acoustic distortions and, consequently, quite different processing pipelines have emerged compared to ASR for close-talk speech. A signal enhancement front-end for dereverberation, source separation and acoustic beamforming is employed to clean up the speech, and the back-end ASR engine is robustified by multi-condition training and adaptation. We will also describe the so-called end-to-end approach to ASR, which is a new promising architecture that has recently been extended to the far-field scenario. This tutorial article gives an account of the algorithms used to enable accurate speech recognition from a distance, and it will be seen that, although deep learning has a significant share in the technological breakthroughs, a clever combination with traditional signal processing can lead to surprisingly effective solutions.}}, author = {{Haeb-Umbach, Reinhold and Heymann, Jahn and Drude, Lukas and Watanabe, Shinji and Delcroix, Marc and Nakatani, Tomohiro}}, journal = {{Proceedings of the IEEE}}, number = {{2}}, pages = {{124--148}}, title = {{{Far-Field Automatic Speech Recognition}}}, doi = {{10.1109/JPROC.2020.3018668}}, volume = {{109}}, year = {{2021}}, } @article{21067, abstract = {{Acoustic waves in plates have proven a viable tool for testing and material characterisation purposes. There are a multitude of options for excitation and detection of theses waves, such as optical and piezoelectric systems. While optical systems, with thermoelastic excitation and interferometric detection, have the benefit of being contactless, they usually require rather complex and expensive experimental setups. Piezoelectric systems are more easily realised but require direct contact with the specimen and usually have a limited bandwidth, especially in case of piezoelectric excitation. In this work, the authors compare the properties of piezoelectric and optical detection methods for broad-band acoustic signals. The shape (e. g. the displacement) of a propagating plate wave is given by its frequency and wave number, allowing to investigate correlations between mode shapes and received signal strengths. This is aided by evaluations in normalised frequency and wavenumber space, facilitating comparisons of different specimens. Further, the authors explore possibilities to utilise the specific properties of the detection methods to determine acoustic material parameters.}}, author = {{Claes, Leander and Schmiegel, Hanna and Grünsteidl, Clemens and Johannesmann, Sarah and Webersen, Manuel and Henning, Bernd}}, issn = {{2196-7113}}, journal = {{tm - Technisches Messen}}, number = {{3}}, pages = {{147--155}}, title = {{{Investigating peculiarities of piezoelectric detection methods for acoustic plate waves in material characterisation applications}}}, doi = {{10.1515/teme-2020-0098}}, volume = {{88}}, year = {{2021}}, } @article{21082, author = {{Itner, Dominik and Gravenkamp, Hauke and Dreiling, Dmitrij and Feldmann, Nadine and Henning, Bernd}}, issn = {{1617-7061}}, journal = {{PAMM}}, title = {{{Simulation of guided waves in cylinders subject to arbitrary boundary conditions for applications in material characterization}}}, doi = {{10.1002/pamm.202000232}}, year = {{2021}}, } @misc{21084, author = {{Werthmann, Julian}}, title = {{{Derandomization and Local Graph Problems in the Node-Capacitated Clique}}}, year = {{2021}}, } @article{21092, abstract = {{Automated Machine Learning (AutoML) seeks to automatically find so-called machine learning pipelines that maximize the prediction performance when being used to train a model on a given dataset. One of the main and yet open challenges in AutoML is an effective use of computational resources: An AutoML process involves the evaluation of many candidate pipelines, which are costly but often ineffective because they are canceled due to a timeout. In this paper, we present an approach to predict the runtime of two-step machine learning pipelines with up to one pre-processor, which can be used to anticipate whether or not a pipeline will time out. Separate runtime models are trained offline for each algorithm that may be used in a pipeline, and an overall prediction is derived from these models. We empirically show that the approach increases successful evaluations made by an AutoML tool while preserving or even improving on the previously best solutions.}}, author = {{Mohr, Felix and Wever, Marcel Dominik and Tornede, Alexander and Hüllermeier, Eyke}}, journal = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}}, publisher = {{IEEE}}, title = {{{Predicting Machine Learning Pipeline Runtimes in the Context of Automated Machine Learning}}}, year = {{2021}}, } @phdthesis{21183, abstract = {{Die präzise Kenntnis der Eigenschaften verwendeter Materialien hat große Bedeutung für den Entwurf technischer Systeme aller Art, aber auch für die Überwachung solcher Systeme im Betrieb. Für verschiedene physikalische Eigenschaften, Betriebsbedingungen und Materialklassen werden daher geeignete messtechnische Verfahren zur Materialcharakterisierung benötigt. In der vorliegenden Arbeit wird ein Verfahren zur ultraschallbasierten Charakterisierung der mechanischen Eigenschaften von homogenen und faserverstärkten thermoplastischen Polymeren unter Berücksichtigung der Richtungsabhängigkeit vorgestellt. Plattenförmige Probekörper werden dazu mittels Laser-Pulsen hoher Energie breitbandig angeregt und die resultierenden akustischen Lamb-Wellen aufgezeichnet. Auf Basis der dispersiven Eigenschaften der detektierten Wellenleitermoden werden in einem inversen Verfahren die Parameter eines linear-elastischen Materialmodells identifiziert. Darüber hinaus wird ein Verfahren zur vollständigen Charakterisierung der Richtungsabhängigkeit in orthotropen Materialien wie Faserverbundwerkstoffen unter Verwendung eines zweidimensionalen Simulationsmodells vorgestellt. Das Messverfahren wird anhand einer Untersuchungsreihe an künstlich gealterten Polymer- und Faserverbundwerkstoffen verifiziert und die Übertragbarkeit der Ergebnisse auf den quasistatischen Fall betrachtet. Im Vergleich mit den Ergebnissen mechanischer Zugversuche werden die Voraussetzungen und Einschränkungen, insbesondere durch die Annahme eines ideal-elastischen Materialmodells, diskutiert.}}, author = {{Webersen, Manuel}}, publisher = {{Universitätsbibliothek Paderborn}}, title = {{{Zerstörungsfreie Charakterisierung der elastischen Materialeigenschaften thermoplastischer Polymerwerkstoffe mittels Ultraschall}}}, doi = {{10.17619/UNIPB/1-1088}}, year = {{2021}}, } @article{21195, author = {{Goelz, Christian and Mora, Karin and Stroehlein, Julia Kristin and Haase, Franziska Katharina and Dellnitz, Michael and Reinsberger, Claus and Vieluf, Solveig}}, journal = {{Cognitive Neurodynamics}}, title = {{{Electrophysiological signatures of dedifferentiation differ between fit and less fit older adults}}}, doi = {{10.1007/s11571-020-09656-9}}, year = {{2021}}, } @misc{21197, author = {{Mengshi, Ma}}, title = {{{Self-stabilizing Arrow Protocol on Spanning Trees with a Low Diameter}}}, year = {{2021}}, } @article{21337, abstract = {{We present a flexible trust region descend algorithm for unconstrained and convexly constrained multiobjective optimization problems. It is targeted at heterogeneous and expensive problems, i.e., problems that have at least one objective function that is computationally expensive. The method is derivative-free in the sense that neither need derivative information be available for the expensive objectives nor are gradients approximated using repeated function evaluations as is the case in finite-difference methods. Instead, a multiobjective trust region approach is used that works similarly to its well-known scalar pendants. Local surrogate models constructed from evaluation data of the true objective functions are employed to compute possible descent directions. In contrast to existing multiobjective trust region algorithms, these surrogates are not polynomial but carefully constructed radial basis function networks. This has the important advantage that the number of data points scales linearly with the parameter space dimension. The local models qualify as fully linear and the corresponding general scalar framework is adapted for problems with multiple objectives. Convergence to Pareto critical points is proven and numerical examples illustrate our findings.}}, author = {{Berkemeier, Manuel Bastian and Peitz, Sebastian}}, issn = {{2297-8747}}, journal = {{Mathematical and Computational Applications}}, number = {{2}}, title = {{{Derivative-Free Multiobjective Trust Region Descent Method Using Radial Basis Function Surrogate Models}}}, doi = {{10.3390/mca26020031}}, volume = {{26}}, year = {{2021}}, } @inproceedings{21378, author = {{Hartel, Rita and Dunst, Alexander}}, booktitle = {{MANPU 2020: The 4th International Workshop on coMics ANalysis, Processing and Understanding@Pattern Recognition. ICPR International Workshops and Challenges}}, isbn = {{9783030687793}}, issn = {{0302-9743}}, title = {{{An OCR Pipeline and Semantic Text Analysis for Comics}}}, doi = {{10.1007/978-3-030-68780-9_19}}, year = {{2021}}, } @article{21535, author = {{Bengs, Viktor and Busa-Fekete, Róbert and El Mesaoudi-Paul, Adil and Hüllermeier, Eyke}}, journal = {{Journal of Machine Learning Research}}, number = {{7}}, pages = {{1--108}}, title = {{{Preference-based Online Learning with Dueling Bandits: A Survey}}}, volume = {{22}}, year = {{2021}}, } @inproceedings{21543, abstract = {{Services often consist of multiple chained components such as microservices in a service mesh, or machine learning functions in a pipeline. Providing these services requires online coordination including scaling the service, placing instance of all components in the network, scheduling traffic to these instances, and routing traffic through the network. Optimized service coordination is still a hard problem due to many influencing factors such as rapidly arriving user demands and limited node and link capacity. Existing approaches to solve the problem are often built on rigid models and assumptions, tailored to specific scenarios. If the scenario changes and the assumptions no longer hold, they easily break and require manual adjustments by experts. Novel self-learning approaches using deep reinforcement learning (DRL) are promising but still have limitations as they only address simplified versions of the problem and are typically centralized and thus do not scale to practical large-scale networks. To address these issues, we propose a distributed self-learning service coordination approach using DRL. After centralized training, we deploy a distributed DRL agent at each node in the network, making fast coordination decisions locally in parallel with the other nodes. Each agent only observes its direct neighbors and does not need global knowledge. Hence, our approach scales independently from the size of the network. In our extensive evaluation using real-world network topologies and traffic traces, we show that our proposed approach outperforms a state-of-the-art conventional heuristic as well as a centralized DRL approach (60% higher throughput on average) while requiring less time per online decision (1 ms).}}, author = {{Schneider, Stefan Balthasar and Qarawlus, Haydar and Karl, Holger}}, booktitle = {{IEEE International Conference on Distributed Computing Systems (ICDCS)}}, keywords = {{network management, service management, coordination, reinforcement learning, distributed}}, location = {{Washington, DC, USA}}, publisher = {{IEEE}}, title = {{{Distributed Online Service Coordination Using Deep Reinforcement Learning}}}, year = {{2021}}, } @misc{21564, author = {{Itner, Dominik and Gravenkamp, Hauke and Dreiling, Dmitrij and Feldmann, Nadine and Henning, Bernd}}, title = {{{On the forward simulation and cost functions for the ultrasonic material characterization of polymers }}}, year = {{2021}}, }