TY - GEN
T1 - Real-Time Gesture Recognition with Shallow Convolutional Neural Networks Employing an Ultra Low Cost Radar System
AU - Ehrnsperger, Matthias G.
AU - Brenner, Thomas
AU - Siart, Uwe
AU - Eibert, Thomas F.
N1 - Publisher Copyright:
© 2020 IMA-Institut fur Mikrowellen-und Antennentechnik e.V.
PY - 2020/3
Y1 - 2020/3
N2 - Ultra-low-cost radar hardware (HW) in combination with low-cost processing units is investigated in order to create and evaluate a holistic ultra-low-cost gesture recognition system. We study the real-time performance of novel machine learning (nML) methods: Neural networks (NNs), in particular shallow architectures of convolutional neural networks (CNNs). The real-time performance of each approach is judged by computational complexity, prediction time, accuracy, and false-positive rate (FPR). As HW, a two-channel radar system with continuous wave (CW) modulation at a carrier frequency of 10 GHz has been employed throughout the investigations. The algorithms are designed, trained, evaluated, and juxtaposed. The results show that the classification process on low-cost HW is feasible and allows to achieve accuracies of 97.9% and FPRs of 1.72%, all of which with a response time of less than 180 ms.
AB - Ultra-low-cost radar hardware (HW) in combination with low-cost processing units is investigated in order to create and evaluate a holistic ultra-low-cost gesture recognition system. We study the real-time performance of novel machine learning (nML) methods: Neural networks (NNs), in particular shallow architectures of convolutional neural networks (CNNs). The real-time performance of each approach is judged by computational complexity, prediction time, accuracy, and false-positive rate (FPR). As HW, a two-channel radar system with continuous wave (CW) modulation at a carrier frequency of 10 GHz has been employed throughout the investigations. The algorithms are designed, trained, evaluated, and juxtaposed. The results show that the classification process on low-cost HW is feasible and allows to achieve accuracies of 97.9% and FPRs of 1.72%, all of which with a response time of less than 180 ms.
KW - artificial intelligence
KW - gesture recognition
KW - low-cost
KW - machine learning
KW - neural networks
KW - radar
KW - real-time
UR - http://www.scopus.com/inward/record.url?scp=85085050242&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85085050242
T3 - GeMIC 2020 - Proceedings of the 2020 German Microwave Conference
SP - 88
EP - 91
BT - GeMIC 2020 - Proceedings of the 2020 German Microwave Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 German Microwave Conference, GeMIC 2020
Y2 - 9 March 2020 through 11 March 2020
ER -