Limitations and applications of ICA in facial sEMG and hand gesture sEMG for human computer interaction

In the recent past, there has been an increasing trend of using Blind Signal Separation (BSS) or Independent Component Analysis (ICA) algorithm for bio medical data, especially in prosthesis and Human Computer Interaction (HCI) applications. This paper reviews the concept of BSS and demonstrates its usefulness and limitations in the context of surface electromyogram related to hand movements and vowel classification. In the first experiment ICA has been used to separate the electrical activity from different hand gestures. The second part of our study considers separating electrical activity from facial muscles during vowel utterance. In both instances surface electromyogram has been used as an indicator of muscle activity. The theoretical analysis and experimental results demonstrate that ICA is suitable for identification of different hand gestures using SEMG signals. The results identify the unsuitability of ICA when the similar techniques are used for the facial muscles in order to perform different vowel classification. This technique could be used as a pre-requisite tool to measure the reliability of sEMG based systems in HCI.