1. | Miguel A. Becerra; Edilson Delgado Trejos; Cristian Mejía-Arboleda; Diego H. Peluffo-Ordóñez; Ana C. Umaquinga-Criollo Stochastic-and Neuro-Fuzzy-Analysis-based characterization and classification of 4-Channel Phonocardiograms for Cardiac Murmur Detection Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação. , vol. 2020, no. E33, pp. 65-78, 2020, ISBN: 1646-9895. @article{becerra2020,
title = {Stochastic-and Neuro-Fuzzy-Analysis-based characterization and classification of 4-Channel Phonocardiograms for Cardiac Murmur Detection},
author = {Miguel A. Becerra and Edilson Delgado Trejos and Cristian Mejía-Arboleda and Diego H. Peluffo-Ordóñez and Ana C. Umaquinga-Criollo},
editor = {AISTI 2020},
url = {http://www.risti.xyz/issues/ristie33.pdf},
isbn = {1646-9895},
year = {2020},
date = {2020-08-20},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação. },
volume = {2020},
number = {E33},
pages = {65-78},
abstract = {Abstract: Cardiac murmurs (CMs) are the most common heart’s diseases that are typically diagnosed from phonocardiogram (PCG) and echocardiogram tests -often supported by computerized systems. Research works have traditionally addressed the automatic CM diagnosis with no distinctively use of the four auscultation areas (one of each cardiac valve), resulting -most probably- in a constrained, nonimpartial diagnostic procedure. This study presents a comparison among four different CM detection systems from a 4-channel PCG. We first evaluate the acoustic characteristics derived from Mel-Frequency Cepstral Coefficients, Empirical Mode Decomposition (EMD), and statistical measures. Secondly, a relevance analysis is carried out using Fuzzy Rough Feature Selection. Thirdly, Hidden Markov Models (HMM), Adaptative Neuro-Fuzzy Inference System (ANFIS), Naïve Bayes, and Gaussian Mixture Model were applied for classification and validated using a 50-fold cross-validation procedure with a 70/30 split demonstrating the functionality and capability of EMD, Hidden Markov Model and ANFIS for CM classification.},
keywords = {ANFIS, cardiac murmur, empirical mode decomposition, hidden markov models, phonocardiogram.},
pubstate = {published},
tppubtype = {article}
}
Abstract: Cardiac murmurs (CMs) are the most common heart’s diseases that are typically diagnosed from phonocardiogram (PCG) and echocardiogram tests -often supported by computerized systems. Research works have traditionally addressed the automatic CM diagnosis with no distinctively use of the four auscultation areas (one of each cardiac valve), resulting -most probably- in a constrained, nonimpartial diagnostic procedure. This study presents a comparison among four different CM detection systems from a 4-channel PCG. We first evaluate the acoustic characteristics derived from Mel-Frequency Cepstral Coefficients, Empirical Mode Decomposition (EMD), and statistical measures. Secondly, a relevance analysis is carried out using Fuzzy Rough Feature Selection. Thirdly, Hidden Markov Models (HMM), Adaptative Neuro-Fuzzy Inference System (ANFIS), Naïve Bayes, and Gaussian Mixture Model were applied for classification and validated using a 50-fold cross-validation procedure with a 70/30 split demonstrating the functionality and capability of EMD, Hidden Markov Model and ANFIS for CM classification. |