Hand Movement Classification from Measured Scattering Parameters using Deep Convolutional Neural Network

Abstract Human body movement analysis aids in implementing the physical rehabilitation process to regain the diminished motor abilities. In this work, the feasibility of using antennas and no dedicated sensors for movement identification is explored. Compact dual-band transmitting and receiving antennas of size 37.6 mm × 27 mm with frequency accuracy of 87% at lower band and 76% at higher band are simulated, fabricated and placed on the body of ten healthy subjects with normal BMI (18.5–24.9) kg/m2. Subjects are made to demonstrate five different hand movements. The dataset for each hand movement is experimentally measured using a Vector Network Analyzer (VNA). Measurement results reveal that the Reflection and Transmission coefficients (S11 and S21) of on-body antennas for each hand movement exhibit unique channel functionalities with respect to frequency. The uniqueness of the exhibited parameters aids in identifying the hand movements. Classification of hand movements based on measured data set is carried out using Deep Convolutional Neural Network (DCNN). The classification accuracy of movement comes out to be 93.32% when classifying using S11 parameters, and an accuracy of 98.67% when classifying using S21 parameters.