Seite drucken

Volker Turau

Foto von Volker Turau
Prof. Dr. rer. nat. Volker Turau
Raum 4.088, Gebäude E
Am Schwarzenberg-Campus 3
21073 Hamburg
Telefon040 42878 - 3530
E-Mail

Seit Oktober 2002 bin ich Professor an der Technischen Universität Hamburg.


Program Committee Activities | Editorial Activities | CV | Doktoranden

Bücher

Algorithmische Graphentheorie - 4., erweiterte und überarbeitete Auflage
De Gruyter Studium, 2015, ISBN 978-3-110-41727-2 (Lösungen)

Erdős-Zahl

Meine Erdős-Zahl ist 3.

Lehre

Publikationen

Nisal Hemadasa, Marcus Venzke, Volker Turau und Yanqiu Huang. Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments. In Proceedings of OkIP International Conference on Automated and Intelligent Systems, CAIS 2023, OkIP Books, Oktober 2023. Oklahoma, USA.
@InProceedings{Telematik_cais_2023, author = {Nisal Hemadasa and Marcus Venzke and Volker Turau and Yanqiu Huang}, title = {Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments}, booktitle = {Proceedings of OkIP International Conference on Automated and Intelligent Systems, CAIS 2023}, pages = , publisher = {OkIP Books}, day = {2-5}, month = oct, year = 2023, location = {Oklahoma, USA}, }
Abstract: Indoor Positioning Systems (IPS) gained importance in many industrial applications. State-of-the-art solutions heavily rely on external infrastructures and are subject to potential privacy compromises, external information requirements, and assumptions, that make it unfavorable for environments demanding privacy and prolonged functionality. In certain environments deploying supplementary infrastructures for indoor positioning could be infeasible and expensive. Recent developments in machine learning (ML) offer solutions to address these limitations relying only on the data from onboard sensors of IoT devices. However, it is unclear which model fits best considering the resource constraints of IoT devices. This paper presents a machine learning-based indoor positioning system, using motion and ambient sensors, to localize a moving entity in privacy concerned factory environments. The problem is formulated as a multivariate time series classification (MTSC) and a comparative analysis of different machine learning models is conducted in order to address it. We introduce a novel time series dataset emulating the assembly lines of a factory. This dataset is utilized to assess and compare the selected models in terms of accuracy, memory footprint and inference speed. The results illustrate that all evaluated models can achieve accuracies above 80 %. CNN-1D shows the most balanced performance, followed by MLP. DT was found to have the lowest memory footprint and inference latency, indicating its potential for a deployment in real-world scenarios.
Ivonne Andrea Mantilla Gonzales und Volker Turau. Comparison of WiFi Interference Mitigation Strategies in DSME Networks: Leveraging Reinforcement Learning with Expected SARSA. In Proceedings of IEEE International Mediterranean Conference on Communications and Networking, IEEE, September 2023, pp. 270–275. Dubrovnik, Croatia.
@InProceedings{Telematik_MeditCom_2023, author = {Ivonne Andrea Mantilla Gonzales and Volker Turau}, title = {Comparison of WiFi Interference Mitigation Strategies in DSME Networks: Leveraging Reinforcement Learning with Expected SARSA}, booktitle = {Proceedings of IEEE International Mediterranean Conference on Communications and Networking}, pages = {270-275}, publisher = {IEEE}, day = {4-7}, month = sep, year = 2023, location = {Dubrovnik, Croatia}, }
Abstract: IEEE 802.15.4 Deterministic and Synchronous Multichannel Extension (DSME) networks have demonstrated their robustness in industrial environments, particularly in data collection scenarios. However, their performance in coexistence with other wireless technologies, such as WiFi, remains largely unexplored. In this work, we perform a simulation analysis using the OpenDSME framework to evaluate the effect of WiFi interference on a DSME network for data collection, considering different channel diversity mechanisms. The proposed strategies include an overprovisioning scheme and the adoption of the recently proposed virtual sink strategy to countermeasure the inherent funnel effect. Our findings indicate that, in general, channel adaptation outperforms channel hopping, except in scenarios with high transmission rates and limited resources, where channel hopping is more effective. When comparing the proposed strategies, the frequency selection algorithm based on reinforcement learning using Expected State-Action-Reward-State-Action (SARSA) demonstrates the most favorable overall performance in the presence of WiFi interference.
Nisal Manikku Badu, Marcus Venzke, Volker Turau und Yanqiu Huang. Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments. Technical Report Report arXiv:2308.11670, arXiv.org e-Print Archive - Computing Research Repository (CoRR), Cornell University, August 2023.
@TechReport{Telematik_arxiv_2023, author = {Nisal Manikku Badu and Marcus Venzke and Volker Turau and Yanqiu Huang}, title = {Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments}, number = {Report arXiv:2308.11670}, institution = {arXiv.org e-Print Archive - Computing Research Repository (CoRR)}, address = {Cornell University}, month = aug, year = 2023, }
Abstract: Indoor Positioning Systems (IPS) gained importance in many industrial applications. State-of-the-art solutions heavily rely on external infrastructures and are subject to potential privacy compromises, external information requirements, and assumptions, that make it unfavorable for environments demanding privacy and prolonged functionality. In certain environments deploying supplementary infrastructures for indoor positioning could be infeasible and expensive. Recent developments in machine learning (ML) offer solutions to address these limitations relying only on the data from onboard sensors of IoT devices. However, it is unclear which model fits best considering the resource constraints of IoT devices. This paper presents a machine learning-based indoor positioning system, using motion and ambient sensors, to localize a moving entity in privacy concerned factory environments. The problem is formulated as a multivariate time series classification (MTSC) and a comparative analysis of different machine learning models is conducted in order to address it. We introduce a novel time series dataset emulating the assembly lines of a factory. This dataset is utilized to assess and compare the selected models in terms of accuracy, memory footprint and inference speed. The results illustrate that all evaluated models can achieve accuracies above 80 %. CNN-1D shows the most balanced performance, followed by MLP. DT was found to have the lowest memory footprint and inference latency, indicating its potential for a deployment in real-world scenarios.

Die vollständige Publikationsliste ist separat verfügbar.

Betreute Arbeiten

Offene Arbeiten

Abgeschlossene Arbeiten