Heart murmur detection with SVM classification

This paper presents an approach to detect low frequency vibrations from the human chest and correlate them to cardiac conditions. Our system which includes data acquisition via a TekScan FlexiForce sensor, signal processing, and hardware/software interfacing is developed and tested through clinical trials. A Support Vector Machine (SVM) learning algorithm is used to train and classify signals. Our results show that a SVM is able to separate and distinguish signals between normal and abnormal cardiac conditions.