@article{EhrnspergerBrennerHoeseetal.2021,
  author    = {Ehrnsperger, Matthias G. and Brenner, Thomas and Hoese, Henri L. and Siart, Uwe and Eibert, Thomas F.},
  title     = {Real-Time Gesture Detection Based on Machine Learning Classification of Continuous Wave Radar Signals},
  journal   = {IEEE Sensors Journal},
  volume    = {21},
  number    = {6},
  issn      = {1530-437X},
  doi       = {10.1109/JSEN.2020.3045616},
  pages     = {8310 -- 8322},
  year      = {2021},
  abstract  = {Classical signal processing methodologies have been infiltrated by machine learning (ML) approaches for a long time, where the ML approaches are in particular applied when it comes to gesture recognition. In this paper, we investigate na{\"i}ve gesture recognition methodologies and compare classical and novel machine learning (nML) algorithms. The considered gestures are simple human gestures such as swiping a hand or kicking with a foot. For the sake of comparability, the algorithms are assessed with respect to their true positive rate (TPR), false-positive rate (FPR), their real-time capability together with the required computational power, and their implementability on low-cost hardware. Two different data sets are utilized separately for the training process of the ML algorithms, where both have been recorded by making use of low-cost radar hardware. The results show that all ML approaches are superior to na{\"i}ve gesture recognition methodologies, e.g., threshold detection. ML algorithms allow almost assured gesture detection. However, our primary contribution is a design approach for scalable neural networks (NNs) that allow such gesture recognition algorithms to be executable on low-cost microcontroller units (MCUs).},
  language  = {en}
}