Best Paper Award at prestigious IEEE Conference

We are very happy to announce that a joint work developed within the DFG SFB 876 between machine-learning (Nico Piatkowski from the Computer Science department) and communication experts (Benjamin Sliwa, Christian Wietfeld from CNI) has received a best paper award at the IEEE flagship conference International Communications Conference (ICC). At ICC 2020 which was originally planned to take place in Dublin this year over 2100 papers were presented in a virtualized format. The award-winning contribution of TU Dortmund "LIMITS: Lightweight Machine Learning for IoT Systems with Resource Limitations" presents 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. In two case studies focusing on cellular data rate prediction and radio-based vehicle classification, LIMITS is validated by comparing different learning models and real world IoT platforms with memory constraints from 16 kB to 4 MB. Furthermore its potential to catalyze the development of machine learning enabled IoT systems is demonstrated.