To content
Fakultät für Elektrotechnik und Informationstechnik

International Best Paper Awards / Competitions / Presentations:

B. Sliwa, N. Piatkowski, C. Wietfeld, LIMITS: Lightweight machine learning for IoT systems with resource limitations, In 2020 IEEE International Conference on Communications (ICC), Dublin, Ireland, June 2020.

-
in
  • Best Paper Awards
Best paper awards certificate © CNI
Abstract - Exploiting big data knowledge on small devices will pave the way for building truly cognitive Internet of Things (IoT) systems. Although machine learning has led to great advancements for IoT-based data analytics, there remains a huge methodological gap for the deployment phase of trained machine learning models. For given resource-constrained platforms such as Microcontroller Units (MCUs), model choice and parametrization are typically performed based on heuristics or analytical models. However, these approaches are only able to provide rough estimates of the required system resources as they do not consider the interplay of hardware, compiler specific optimizations, and code dependencies. In this paper, we present the novel open source framework LIghtweight Machine learning for IoT Systems (LIMITS), which applies a platform-in-the-loop approach explicitly considering the actual compilation toolchain of the target IoT platform. LIMITS focuses on high level tasks such as experiment automation, platform-specific code generation, and sweet spot determination. The solid foundations of validated low-level model implementations are provided by the coupled well-established data analysis framework Waikato Environment for Knowledge Analysis (WEKA). We apply and validate LIMITS in two case studies focusing on cellular data rate prediction and radio-based vehicle classification, where we compare different learning models and real world IoT platforms with memory constraints from 16 kB to 4 MB and demonstrate its potential to catalyze the development of machine learning enabled IoT systems.

Awards by Informationstechnische Gesellschaft (ITG) in the VDE

VDE Logo © VDE

2016 - Advancement Award Dr.-Ing. Christoph Ide

Dr.-Ing. Christoph Ide, former head of the research groups of the CNI and Alumni of SFB 876, received one of the prestigious junior awards by the Informationstechnische Gesellschaft (ITG) in the VDE for his thesis "Resource-Efficient LTE Machine-Type Communication in Vehicular Environments" in November 2016. The nationally fiercely contested award was handed over at a solemn celebration at the Berlin-Brandenburgische Akademie der Wissenschaften in Berlin on November 29, 2016. The research results of the DFG Sonderforschungsbereich SFB 876 "Datenanalyse unter Ressourcenbeschränkungen" are an excellent contribution to the development of future mobile radio-based traffic systems, which will support growing automation of the reliable, simultaneous and efficient communication between the single system components. This research also makes a valuable contribution to future 5G networks, especially in terms of the Internet of Things.

2013 ITG Awards 2013 for Dr.-Ing. Niklas Goddemeier, Dr.-Ing. Kai Daniel and Prof. Dr.-Ing. Christian Wietfeld

For their research in the field of networked robotic systems, Dr.-Ing. Niklas Goddemeier, Dr.-Ing. Kai Daniel and Prof. Dr.-Ing. Christian Wietfeld received the coveted ITG Awards 2013 by the Informationstechnische Gesellschaft in the VDE at Berlin-Brandenburgische Akademie der Wissenschaften in Berlin on November 12, 2013.

The ITG Award is being advertised annually and awarded for outstanding publications, in this case for an article in the internationally well-known IEEE Journal on Selected Areas of Communications.

Role-Based Connectivity Management with Realistic Air-to-Ground Channels for Cooperative UAVs: Ad-hoc aerial sensor networks leveraging MUAVs (Micro Unmanned Aerial Vehicles) are ideally suited to cost-efficiently explore unknown or hostile environments for example in case of incidents producing harmful gases or radiation. In this manuscript we present results on the investigations of communication-aware steering algorithms for cooperative MUAV swarms. The mission objective is to achieve a maximum spatial exploration efficiency with the simultaneous ability to self-optimize the communication links by exploiting controlled mobility. While our previous work has mainly considered the performance of the Air-to-Air mesh network, in this paper we focus on the Air-to-Ground-link connectivity control. To achieve appropriate communication links to a central sensor data sink even while exploring larger search areas, an agent-based role management strategy is used to provide suitable multi-hop connectivity. The novel algorithms are investigated for static as well as dynamically changing environments. Key results include a detailed realistic aerial channel characterization and network dimensioning analysis considering numbers of MUAVs and density of ground stations vs. exploration speed and sensor data latency.

2014 VDE-Award for Master Graduate - M.Sc. David Öhmann

Once a year, the VDE Rhein-Ruhr e.V. awards junior engineers for excellent bachelor's and master's degrees. Also this year,  the organization honored excellent degrees and continued its active dedication to young engineers. The solemn ceremony took place at the trade fair "E-world" in Essen on February 12, 2014, for the first time. For TU Dortmund, David Öhmann, whose master thesis "Kooperatives Verbindungsmanagement von heterogenen Funkzugangssystemen im Automobilumfeld" was supervised by the CNI and collaborated with BMW in Munich, has been awarded.

 

Other Awards