Abstract—In this study, respiratory sounds of asthmatic patients and healthy individuals are analyzed and classified to diagnose asthma. Normal and asthmatic breath sound signals are divided into segments which include a single respiration cycle as inspiration and expiration. Analyses of these sound segments are carried out by using both discrete wavelet transform (DWT) and wavelet packet transform (WPT). Each sound segment is decomposed into frequency sub-bands using DWT and WPT. Feature vectors are constructed by extracting statistical features from the sub-bands. Artificial neural network (ANN) is used to classify respiratory sound signals as normal and level of asthmatic diseases (mild asthma, moderate asthma and severe asthma). The classification results of DWT and WPT are compared with each other in terms of classification accuracy.
 

Index Terms—respiratory sounds, discrete wavelet transform, wavelet packet transform, artificial neural network