Lung Sounds Classification Using Stacked Autoencoder and Support Vector Machine

Various methods have developed to analyze and classify many types of lung sound to reduce subjectivity in the auscultation procedure. In this paper, another proposed approach as a lung sound classification system has developed. This method combined a feature selection using unsupervised learning by stacked autoencoder (SAE) and support vector machine (SVM) as the classifier. Another feature extraction method using discrete wavelet transform also employed to bring a performance comparison to the proposed method. The result of this study showed that the proposed method scored 86.51%.