Performance Analysis of ICA Algorithms against Multiple-Sources Interference in Biomedical Systems

This paper evaluates the performance of some major ICA algorithms like Cardoso’s Joint Approximate Diagonalization of Eigen matrices (JADE), Bell and Sejnowski’s Infomax algorithm and Comon’s algorithm in a biomedical blind source separation problem. Independent signals representing Fetal ECG (FECG) and Maternal ECG (MECG) generated and then mixed linearly to simulate a recording of electrocardiogram. ICA has been used to extract FECG, but very less literature is available on the performance, i.e., how does it behave in clinical environment? Therefore, there is a used to evaluate performance of these algorithms in biomedical. To quantify the performance of ICA algorithms, different samples values of simulated maternal and fetal ECG investigated. Separation performance of ICA algorithms measure by performance index. The performance of algorithms are compared and discussed.