Statistical Analysis of Time-Frequency Features Based On Multivariate Synchrosqueezing Transform for Hand Gesture Classification

TL;DR

This paper proposes using statistical features derived from the multivariate synchrosqueezing transform of sEMG signals for hand gesture classification, demonstrating their potential as effective recognition features.

Contribution

It introduces a novel set of time-frequency statistical features from MSST for hand gesture recognition, evaluated on a public dataset.

Findings

TF features show significant discriminative power (p<0.05) for gesture classification.

Mean, variance, skewness, and kurtosis are promising features for hand gesture recognition.

Features derived from MSST can be used as candidate features in gesture recognition systems.

Abstract

In this study, the four joint time-frequency (TF) moments; mean, variance, skewness, and kurtosis of TF matrix obtained from Multivariate Synchrosqueezing Transform (MSST) are proposed as features for hand gesture recognition. A publicly available dataset containing surface EMG (sEMG) signals of 40 subjects performing 10 hand gestures, was used. The distinguishing power of the feature variables for the tested gestures was evaluated according to their p values obtained from the Kruskal-Wallis (KW) test. It is concluded that the mean, variance, skewness, and kurtosis of TF matrices can be candidate feature sets for the recognition of hand gestures.