Volume 3 Machine Learning under Resource Constraints - Applications

book: Volume 3 Machine Learning under Resource Constraints - Applications

Open Access Published by De Gruyter 2023

Volume 3 Machine Learning under Resource Constraints - Applications

Edited by: Katharina Morik , Jörg Rahnenführer and Christian Wietfeld

Part of the multi-volume work Machine Learning under Resource Constraints

In the series De Gruyter STEM

https://doi.org/10.1515/9783110785982

Overview
Contents

About this book

Machine Learning under Resource Constraints addresses novel machine learning algorithms that are challenged by high-throughput data, by high dimensions, or by complex structures of the data in three volumes. Resource constraints are given by the relation between the demands for processing the data and the capacity of the computing machinery. The resources are runtime, memory, communication, and energy. Hence, modern computer architectures play a significant role. Novel machine learning algorithms are optimized with regard to minimal resource consumption. Moreover, learned predictions are executed on diverse architectures to save resources. It provides a comprehensive overview of the novel approaches to machine learning research that consider resource constraints, as well as the application of the described methods in various domains of science and engineering.

Volume 3 describes how the resource-aware machine learning methods and techniques are used to successfully solve real-world problems. The book provides numerous specific application examples. In the areas of health and medicine, it is demonstrated how machine learning can improve risk modelling, diagnosis, and treatment selection for diseases. Machine learning supported quality control during the manufacturing process in a factory allows to reduce material and energy cost and save testing times is shown by the diverse real-time applications in electronics and steel production as well as milling. Additional application examples show, how machine-learning can make traffic, logistics and smart cities more effi cient and sustainable. Finally, mobile communications can benefi t substantially from machine learning, for example by uncovering hidden characteristics of the wireless channel.

Ranges from embedded systems to large computing clusters.
Provides application of the methods in various domains of science and engineering.

Author / Editor information

Katharina Morik received her doctorate from the University of Hamburg in 1981 and her habilitation from the TU Berlin in 1988. In 1991, she established the chair of Artificial Intelligence at the TU Dortmund University. She is a pioneer of machine learning contributing substantially to inductive logic programming, support vector machines, probabilistic graphical models. In 2011, she acquired the Collaborative Research Center SFB 876 "Providing Information by Resource-Constrained Data Analysis", of which she is the spokesperson. and computing architectures together so that machine learning models may be executed or even trained on resource restricted devices. It consists of 12 projects and a graduate school for more than 50 Ph. D. students. She is a spokesperson of the Competence Center for Machine Learning Rhein Ruhr (ML2R) and coordinator of the German competence centers for AI. She is the author of more than 200 publications in prestigious journals and conferences. She was a founding member, Program Chair and Vice Chair of the conference IEEE International Conference on Data Mining (ICDM) and is a member of the steering committee of and was Program Chair of ECML PKDD. Together with Volker Markl, Katharina Morik heads the working group "Technological Pioneers" of the platform "Learning Systems and Data Science" of the BMBF. Prof. Morik has been a member of the Academy of Technical Sciences since 2015 and of the North Rhine-Westphalian Academy of Sciences and Arts since 2016. She has been awarded Fellow of the German Society of Computer Science GI e.V. in 2019. Christian Wietfeld: Prof. Christian Wietfeld is head of the Chair of Communication Networks at TU Dortmund University since 2005. He graduated and received his doctorate from RWTH Aachen. His research interest focusses on future mobile communications networks, especially for safety-critical applications, e.g., in road traffic, logistics, energy technology, and robotics. His research work is documented in numerous publications as well as patents (13 international best paper awards, 5300+ citations). He has also co-founded several award-winning start-ups. Currently, the focus of his research is on 5G and 6G networks, e.g., in the 5G Competence Center funded by the state of North Rhine-Westphalia, where the potential of 5G technology for industrial production and other scenarios with particularly demanding requirements is being explored. Being the Co-Speaker of the Collaborative Research Center 876, he is investigating the use of novel artificial intelligence methods for reliable mobile networks of future generations. Since August 2021, he has been leading the activities of TU Dortmund University in the BMBF-funded 6G Research Hub 6GEM as site spokesperson.

Jörg Rahnenführer: Prof. Dr. Jörg Rahnenführer is professor for "Statistical methods in genetics and chemometrics" at the Department of Statistics at TU Dortmund University. After obtaining a PhD in mathematics from the University of Düsseldorf he worked as a postdoc in Vienna, Berkeley, Omaha, and at the Max Planck Institute for Informatics in Saarbrücken. The respective departments covered a wide range of fields, including mathematics, statistics, biostatistics, genetics, and computer science. His group at TU Dortmund develops and applies in interdisciplinary projects statistical methods mainly for applications in bioinformatics, toxicology, and medicine. He has particularly worked successfully on the meaningful exploitation of high-dimensional omics data and as a member of the SFB 876 on hyperparameter optimization in statistical learning methods. Since 2021 he is the spokesperson of the DFG-funded Research Training Group (RTG) 2624 "Biostatistical Methods for High-Dimensional Data in Toxicology".

Topics

Frontmatter Publicly Available Download PDF	I
Contents Publicly Available Download PDF	VII
1 Editorial Katharina Morik, Jörg Rahnenführer and Christian Wietfeld Open Access Download PDF	1
2 Health / Medicine
2.1 Machine Learning in Medicine Catherine Jutzeler and Karsten Borgwardt Open Access Download PDF	3
2.2 Virus Detection Roland Hergenröder, Frank Weichert, Konstantin Wüstefeld and Victoria Shpacovitch Open Access Download PDF	21
2.3 Cancer Diagnostics and Therapy from Molecular Data Sven Rahmann, Alexander Schramm and Johannes Köster Open Access Download PDF	43
2.4 Bayesian Analysis for Dimensionality and Complexity Reduction Zeyu Ding, Katja Ickstadt and Alexander Munteanu Open Access Download PDF	58
2.5 Survival Prediction and Model Selection Jörg Rahnenführer, Michel Lang and Jakob Richter Open Access Download PDF	71
2.6 Protein Complex Similarity Bianca K Stöcker, Till Schäfer, Petra Mutzel, Johannes Köster, Nils Kriege and Sven Rahmann Open Access Download PDF	85
3 Industry 4.0
3.1 Keynote on Industry 4.0 Michael ten Hompel and Moritz Roidl Open Access Download PDF	103
3.2 Quality Assurance in Interlinked Manufacturing Processes Jochen Deuse, Katharina Morik, Amal Saadallah, Jan Büscher and Thorben Panusch Open Access Download PDF	114
3.3 Label Proportion Learning Marco Stolpe and Katharina Morik Open Access Download PDF	136
3.4 Simulation and Machine Learning Petra Wiederkehr, Katharina Morik, Amal Saadallah and Felix Finkeldey Open Access Download PDF	157
3.5 High-Precision Wireless Localization Janis Tiemann Open Access Download PDF	180
3.6 Indoor Photovoltaic Energy Harvesting Mojtaba Masoudinejad Open Access Download PDF	195
3.7 Micro-UAV Swarm Testbed for Indoor Applications Nils Gramse, Moritz Roidl, Shrutarv Awasthi and Christopher Reining Open Access Download PDF	212
4 Smart City and Traffic
4.1 Inner-City Traffic Flow Prediction with Sparse Sensors Thomas Liebig Open Access Download PDF	225
4.2 Privacy-Preserving Detection of Persons and Classification of Vehicle Flows Marcus Haferkamp, Benjamin Sliwa and Christian Wietfeld Open Access Download PDF	241
4.3 Green Networking and Resource Constrained Clients for Smart Cities Pascal Jörke and Christian Wietfeld Open Access Download PDF	261
4.4 Vehicle to Vehicle Communications: Machine Learning-Enabled Predictive Routing Cedrik Krieger, Benjamin Sliwa and Christian Wietfeld Open Access Download PDF	272
4.5 Modelling of Hybrid Vehicular Traffic with Extended Cellular Automata Michael Schreckenberg and Tim Vranken Open Access Download PDF	285
4.6 Embedded Crowdsensing for Pavement Monitoring and its Incentive Mechanisms Maximillian Machado, Ran Ran and Liang Cheng Open Access Download PDF	297
5 Communication Networks
5.1 Capacity Analysis of IoT Networks in the Unlicensed Spectrum Stefan Böcker, Christian Arendt and Christian Wietfeld Open Access Download PDF	313
5.2 Resource-Efficient Vehicle-to-Cloud Communications Benjamin Sliwa Open Access Download PDF	331
5.3 Mobile-Data Network Analytics Highly Reliable Networks Robert Falkenberg, Karsten Heimann and Benjamin Sliwa Open Access Download PDF	342
5.4 Machine Learning-Enabled 5G Network Slicing Caner Bektas, Fabian Kurtz, Dennis Overbeck and Christian Wietfeld Open Access Download PDF	354
5.5 Potential of Millimeter Wave Communications Karsten Heimann, Simon Häger and Christian Wietfeld Open Access Download PDF	375
6 Privacy
6.1 Keynote: Construction of Inference-Proof Agent Interactions Joachim Biskup Open Access Download PDF	391
Bibliography Open Access Download PDF	413
Index Open Access Download PDF	461
List of Contributors Open Access Download PDF	467

(Deutsch)

Language: English
Publisher: De Gruyter
Audience: Computer Scientists, Physicists, Engineers, Libraries.
Pages
- Front matter: 8
- Main content: 470
Illustrations
- Illustrations: 200
- Coloured Illustrations: 100
- Tables: 50
- Coloured Tables: 50
Keywords: Resource-Constrained Data Analysis; Resource-Aware Machine Learning; Embedded Systems and Machine Learning; Big Data and Machine Learning; Artificial Intelligence; Highly Distributed Data; ML on Small devices; Data mining for Ubiquitous System Software; Cyber-physical systems; Machine learning in high-energy physics; Machine learning for knowledge discovery

eBook

Published: December 31, 2022
ISBN: 9783110785982

Paperback

Published: December 31, 2022
ISBN: 9783110785975