Identification of number of independent sources in surface EMG recordings using over complete ICA

Artifacts in bioelectric signals can make bioelectric signals unreliable. Spectral and temporal overlap can make the removal of artifact or separation of different bioelectric signals extremely difficult. Often, the sources of the bioelectric signals may be considered as independent at the local level and this makes an argument for separating the signals using independent component analysis (ICA). This paper reports research conducted to evaluate the use of ICA for the separation of bioelectric signals when the number of sources exceed number of sensors. The paper proposes the use of value of the determinant of the global matrix generated using subband ICA for identifying the number of active sources. The results indicate that the technique is successful in identifying the number of active muscles for complex hand gestures. The results support the applications such as human computer