Hand Motion Identification using Independent Component Analysis of data glove and multichannel surface EMG

摘要

This study presents an approach to identify hand motions using muscle activity separated from multichannel surface electromyogram (SEMG) and the information of data glove. There are nigh features included six features are extracted from each SEMG channel, and three features are computed from five bend sensors in the data glove. Independent Component Analysis (ICA) was used to examine its effect on independent component extraction and features reduction in this study. The results demonstrate that ICA can effectively reduce the amount of required computation data with the price of reduced identification rates. The results also indicate that the proposed method provides high accuracy (>90%) and fast processing time that is achieved to the performance of real-time system.