SYSTEM AND METHOD OF EXTRACTION OF THE HEART VALVE SIGNALS

A system for monitoring and diagnosing heart conditions includes a sensor array with accelerometers, an electrocardiogram sensor, and a system to capture and process the composite heart signals. The system performs source separation to extract information contained in cardio pulmonic vibrations. The system can use machine learning, auditory scene analysis, spare coding, determined Models, Principal Component Analysis (PCA), Independent Component Analysis ICA, Singular Value Decomposition (SVD), Bin-wise Clustering and Permutation posterior probability alignment, Undetermined Models, Sparseness condition, Dictionary learning, Convolutive models, K-SVD Matching Pursuit, Non-negative matrix factorization and Deep Belief Networks (Restricted Boltzmann Machine) approaches to the source separation problem. Other embodiments are disclosed.