Abstract:
The phonocardiogram (PCG) signals provide valuable information about the heart condition for exact and timely detection of heart diseases. Accurate localization of heart beats in phonocardiogram signal is very crucial for correct segmentation and classification of heart sounds into S1 and S2. This task becomes challenging due to introduction of noise in acquisition process due to many factors like wrong positioning of stethoscope, rubbing of stethoscope with clothes and undesirable background music/sounds etc. In this thesis, a system for heart sound localization and classification into S1 and S2 is proposed. The proposed system introduces the concept of quality assessment before extraction of features and classification of heart sounds. The signal quality is assessed by predefined criteria based upon number of peaks and zero crossing of PCG signal. Once quality assessment is performed then localization of heart beats within PCG signal is done by envelope extraction using homomorphic envelogram and finding prominent peaks. In order to classify extracted peaks into S1 and S2, temporal and time-frequency based statistical features have been used. Support Vector machine using radial basis function kernel is used for classification of heart beats into S1 and S2 based upon extracted features. The results are validated by leave one out cross validation. The performance of the proposed system is evaluated using Accuracy, Sensitivity, Specificity-measure and Total Error. The Dataset provided by the PASCAL classifying heart sound challenge is used for testing. The system provides firm foundation for the detection of normal and abnormal heart sounds for cardiovascular disease detection.
