Venzke, MarcusMarcusVenzkeKlisch, DanielDanielKlischKubik, PhilippPhilippKubikAli, AsadAsadAliDell Missier, JesperJesperDell MissierTurau, VolkerVolkerTurau2020-12-182020-12-182020-12-15arXiv: 2012.08403 (2020)http://hdl.handle.net/11420/8295In this paper we investigate the usage of machine learning for interpreting measured sensor values in sensor modules. In particular we analyze the potential of artificial neural networks (ANNs) on low-cost micro-controllers with a few kilobytes of memory to semantically enrich data captured by sensors. The focus is on classifying temporal data series with a high level of reliability. Design and implementation of ANNs are analyzed considering Feed Forward Neural Networks (FFNNs) and Recurrent Neural Networks (RNNs). We validate the developed ANNs in a case study of optical hand gesture recognition on an 8-bit micro-controller. The best reliability was found for an FFNN with two layers and 1493 parameters requiring an execution time of 36 ms. We propose a workflow to develop ANNs for embedded devices.enComputer Science - LearningComputer Science - LearningComputer Science - Neural and Evolutionary ComputingMachine LearningArtificial Neural NetworksEmbedded SystemsHand Gesture RecognitionMLE@TUHHAllgemeines, WissenschaftPreprint10.48550/arXiv.2012.084032012.08403v1Preprint