Heart Sound Classification Using Deep Learning Techniques Based on Log-mel Spectrogram

In this study, two models for classifying heart rate sounds are proposed to classify heart sound by deep learning techniques based on the log-mel spectrogram of heart sound signals. The heart sound dataset comprises five classes, one normal class and four anomalous classes, namely, Aortic Stenosis, Mitral Regurgitation, Mitral Stenosis, and Murmur in systole. First, the heart sound signals are framed to a consistent length and thereafter extract the log-mel spectrogram features. Two deep learning models, long short-term memory and convolution neural network are proposed to classify heartbeat sounds based on the extracted features. Analysis results demonstrated the high performance of classification models, with an overall accuracy of about 99.67%. The results also showed higher performance compared to previous studies.