Automatic wheeze detection using histograms of sample entropy

In this paper, we propose a robust and automatic wheeze detection method using sample entropy (SampEn) histograms of the filtered narrow band respiratory sound signals. The sound signals are segmented first into their respective inspiration/expiration phases. Time-frequency distribution of each segment is then obtained using Gabor spectrogram. After the construction of SampEn plane, histograms of the selected frequency bins of the SampEn plane are calculated. The mean distortion of the histograms are used as discriminating features for segment-wise wheeze detection. Detection experiments are carried out irrespective of inspiration/expiration segments of the respiration sound signals recorded and preprocessed under different conditions, and the overall wheeze detection accuracy is 97.9% for high intensity wheezes during expirations and is up to 85.3% for low intensity wheezes occurring in inspirations.