Title |
Multi-level basis selection of wavelet packet decomposition tree for heart sound classification
|
---|---|
Published in |
Computers in Biology & Medicine, July 2013
|
DOI | 10.1016/j.compbiomed.2013.06.016 |
Pubmed ID | |
Authors |
Fatemeh Safara, Shyamala Doraisamy, Azreen Azman, Azrul Jantan, Asri Ranga Abdullah Ramaiah |
Abstract |
Wavelet packet transform decomposes a signal into a set of orthonormal bases (nodes) and provides opportunities to select an appropriate set of these bases for feature extraction. In this paper, multi-level basis selection (MLBS) is proposed to preserve the most informative bases of a wavelet packet decomposition tree through removing less informative bases by applying three exclusion criteria: frequency range, noise frequency, and energy threshold. MLBS achieved an accuracy of 97.56% for classifying normal heart sound, aortic stenosis, mitral regurgitation, and aortic regurgitation. MLBS is a promising basis selection to be suggested for signals with a small range of frequencies. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United Kingdom | 1 | <1% |
Mexico | 1 | <1% |
Colombia | 1 | <1% |
Serbia | 1 | <1% |
Unknown | 125 | 97% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Master | 25 | 19% |
Student > Ph. D. Student | 23 | 18% |
Student > Bachelor | 19 | 15% |
Researcher | 10 | 8% |
Lecturer | 6 | 5% |
Other | 21 | 16% |
Unknown | 25 | 19% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 60 | 47% |
Computer Science | 15 | 12% |
Medicine and Dentistry | 5 | 4% |
Physics and Astronomy | 4 | 3% |
Neuroscience | 4 | 3% |
Other | 8 | 6% |
Unknown | 33 | 26% |