The Fusion of HRV and EMG Signals for Automatic Gender Recognition during Stepping Exercise

Abstract

In this paper, a new gender recognition approach in accordance with the fusion of features extracted from electromyogram (EMG) and heart rate variability (HRV) during stepping activity using a stair stepper device is proposed. The fusion of EMG and HRV is investigated based on feature fusion approach. The feature fusion is carried out by chaining the feature vector extracted from the EMG and HRV signals. A proposed approach comprises of a sequence of processing steps which are preprocessing, feature extraction, feature selection and the feature fusion. The results demonstrated that the fusion approach had enhanced the performance of gender recognition compared to solely on EMG or HRV for the gender recognition.