Open AccessComparison of Multiscale Entropy for Lung Sound Classification
Author(s) -
Achmad Rizal,
Risanuri Hidayat,
Hanung Adi Nugroho
Publication year - 2018
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v12.i3.pp984-994
Subject(s) - entropy (arrow of time) , signal processing , mathematics , computer science , algorithm , pattern recognition (psychology) , artificial intelligence , physics , digital signal processing , quantum mechanics , computer hardware
Lung sound is a biological signal used to determine the health level of the respiratory tract. Various digital signal processing techniques have been developed for the automatic lung sound classification. Entropy is one of the parameters used to measure the biomedical signal complexity. Multiscale entropy is introduced to measure the entropy of a signal at a particular scale range. Over time, various multiscale entropy techniques are used to measure the signal complexity on biological signal and other physical signals. In this paper, a number of multiscale entropy techniques for the lung sound classification are discussed. The results showed that Multiscale Permutation Entropy (MPE) could produce the highest accuracy of 97.98% for five classes of lung sound data. Results achieved for the scale 1-10 producing ten features for each lung sound data. This result is better than other seven entropies. The use of Permutation entropy (PE) on a multiscale scheme was to obtain a better accuracy compared to PE on one scale only