Statistical Analysis of Time-Frequency Features Based On Multivariate Synchrosqueezing Transform for Hand Gesture Classification
This work addresses hand gesture classification using sEMG signals, but it appears incremental as it applies existing statistical methods to new features without demonstrating clear performance gains.
The study tackled hand gesture recognition by proposing four joint time-frequency moments (mean, variance, skewness, kurtosis) from the Multivariate Synchrosqueezing Transform as features, and concluded they are candidate feature sets for this task.
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.