Coordinate rotation based low complexity architecture for 3D Single Channel Independent Component Analysis

In this paper, we have proposed a low complexity architecture of the Single Channel Independent Component Analysis Algorithm (SCICA) targeted for remote cardiac health monitoring by introducing the concept of coordinate rotation. The ECG is widely used for the diagnosis of cardiovascular diseases, and in remote healthcare applications, it is necessary to obtain clean ECG data by separating noise from the obtained signal. Independent Component Analysis is popularly used to solve the signal separation problem, however it requires as many signal sensors as the number of independent signals involved, and also requires the number of signals involved to be known a priori. This is not always possible in remote healthcare environments and thus, this motivates us to explore the use of the SCICA algorithm which requires only one input sensor for signal separation. SCICA is computationally intensive and thus there is a need for a low-complexity implementation of the algorithm for the development of healthcare devices. The proposed architecture is validated in terms of functionality and computational complexity and it has been observed that its performance compares favorably with the conventional algorithm.