Estimation of independent and dependent components of non-invasive EMG using fast ICA: validation in recognising complex gestures

The identification of a number of active muscles during complex actions is the useful information to identify different gestures. Biosignals such as surface electromyogram (sEMG) are a result of the summation of electrical activity of a number of sources. The complexity of the anatomy and actions makes it difficult in identifying the number of active sources from the multiple channel recordings. This paper addresses two applications of independent component analysis (ICA) on sEMG: the first one is to evaluate the use of ICA for the separation of bioelectric signals when the number of active sources may not be known. The second application is to identify complex hand gestures using decomposed sEMG. The theoretical analysis and experimental results demonstrate that the ICA is suitable for the separation of myoelectric signals. The results identify the usage of ICA for identifying complex gestures.