Heart Murmur Recognition Based on Hidden Markov Model

• DOI: 10.4236/jsip.2013.42020
• Publication Date: 2013-05-10T04:29:40Z
• Authors: Lisha Zhong; Jiangzhong Wan; Zhiwei Huang; Gaofei Cao; Bo Xiao
• Keywords: Mel-frequency cepstrum; Heart sounds; Heart murmur; Cepstrum

Heart murmur recognition and classification play an important role in the auscultative diagnosis. The method based on hidden markov model (HMM) was presented to recognize heart murmur. isolated basis of principle wavelet analysis considering time-frequency characteristics This uses Mel frequency cepstral coefficient (MFCC) extract representative features develops Markov for signal classification. result shows that this is able efficiently superior BP neural network (94.2% vs 82.8%). And findings suggest may have potential be used assist doctors a more objective