{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T19:13:24Z","timestamp":1791400404844,"version":"4.3.3"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This paper seeks to enhance the performance of Mel Frequency Cepstral Coefficients (MFCCs) for detecting abnormal heart sounds. Heart sounds are first pre-processed to remove noise and then segmented into S1, systole, S2, and diastole intervals, with thirteen MFCCs estimated from each segment, yielding 52 MFCCs per beat. Finally, MFCCs are used for heart sound classification. For that purpose, a single classifier and an innovative ensemble classifier strategy are presented and compared. In the single classifier strategy, the MFCCs from nine consecutive beats are averaged to classify heart sounds by a single classifier (either a support vector machine (SVM), the k nearest neighbors (kNN), or a decision tree (DT)). Conversely, the ensemble classifier strategy employs nine classifiers (either nine SVMs, nine kNN classifiers, or nine DTs) to individually assess beats as normal or abnormal, with the overall classification based on the majority vote. Both methods were tested on a publicly available phonocardiogram database. The heart sound classification accuracy was 91.95% for the SVM, 91.9% for the kNN, and 87.33% for the DT in the single classifier strategy. Also, the accuracy was 93.59% for the SVM, 91.84% for the kNN, and 92.22% for the DT in the ensemble classifier strategy. Overall, the results demonstrated that MFCCs were more effective than other features, including time, time-frequency, and statistical features, evaluated in similar studies. In addition, the ensemble classifier strategy improved the accuracies of the DT and the SVM by 4.89% and 1.64%, implying that the averaging of MFCCs across multiple phonocardiogram beats in the single classifier strategy degraded the important cues that are required for detecting the abnormal heart sounds, and therefore should be avoided.<\/jats:p>","DOI":"10.1371\/journal.pone.0316645","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:07:08Z","timestamp":1735672028000},"page":"e0316645","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":14,"title":["Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies"],"prefix":"10.1371","volume":"19","author":[{"given":"Mehdi","family":"Hosseinzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Haider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8890-1310","authenticated-orcid":true,"given":"Mazhar Hussain","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Adeli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olfa","family":"Mzoughi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Entesar","family":"Gemeay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mokhtar","family":"Mohammadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Alinejad-Rokny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parisa","family":"Khoshvaght","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thantrira","family":"Porntaveetus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir Masoud","family":"Rahmani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"pone.0316645.ref001","volume-title":"Encyclopedia of medical devices and instrumentation","author":"J.G. Webster","year":"1990","edition":"2"},{"issue":"2","key":"pone.0316645.ref002","first-page":"22","article-title":"Classification of phonocardiograms with convolutional neural networks","volume":"9","author":"O. Deperlioglu","year":"2018","journal-title":"BRAIN. Broad Research in Artificial Intelligence and Neuroscience"},{"issue":"5","key":"pone.0316645.ref003","doi-asserted-by":"crossref","first-page":"055006","DOI":"10.1088\/1361-6579\/ab8770","article-title":"Automatic heart sound classification from segmented\/unsegmented phonocardiogram signals using time and frequency features","volume":"41","author":"F.A. Khan","year":"2020","journal-title":"Physiological measurement"},{"issue":"11","key":"pone.0316645.ref004","doi-asserted-by":"crossref","first-page":"115011","DOI":"10.1088\/1361-6579\/aae7fa","article-title":"Supervised threshold-based heart sound classification algorithm","volume":"39","author":"W. Han","year":"2018","journal-title":"Physiological Measurement"},{"issue":"8","key":"pone.0316645.ref005","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2023.0140889","article-title":"Systematic Review for Phonocardiography Classification Based on Machine Learning","volume":"14","author":"A. Altaf","year":"2023","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"pone.0316645.ref006","doi-asserted-by":"crossref","first-page":"160882","DOI":"10.1109\/ACCESS.2020.3020806","article-title":"Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals","volume":"8","author":"T.H. Chowdhury","year":"2020","journal-title":"Ieee Access"},{"key":"pone.0316645.ref007","doi-asserted-by":"crossref","first-page":"8316","DOI":"10.1109\/ACCESS.2018.2889437","article-title":"Algorithms for automatic analysis and classification of heart sounds\u2013a systematic review","volume":"7","author":"A.K. Dwivedi","year":"2018","journal-title":"IEEE Access"},{"issue":"8","key":"pone.0316645.ref008","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1088\/1361-6579\/aa724c","article-title":"Heart sound classification from unsegmented phonocardiograms","volume":"38","author":"P. Langley","year":"2017","journal-title":"Physiological measurement"},{"issue":"2","key":"pone.0316645.ref009","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1007\/s13246-020-00851-w","article-title":"Automated heart sound classification system from unsegmented phonocardiogram (PCG) using deep neural network","volume":"43","author":"P.T. Krishnan","year":"2020","journal-title":"Physical and Engineering Sciences in Medicine"},{"key":"pone.0316645.ref010","doi-asserted-by":"crossref","first-page":"100194","DOI":"10.1016\/j.smhl.2021.100194","article-title":"Abnormal heart sound classification using phonocardiography signals","volume":"21","author":"M. Milani","year":"2021","journal-title":"Smart Health"},{"key":"pone.0316645.ref011","doi-asserted-by":"crossref","first-page":"101688","DOI":"10.1016\/j.bspc.2019.101688","article-title":"Classification and evaluation of the severity of tricuspid regurgitation using phonocardiogram","volume":"57","author":"A. Rujoie","year":"2020","journal-title":"Biomedical Signal Processing and Control"},{"issue":"7","key":"pone.0316645.ref012","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1080\/03091902.2019.1576789","article-title":"Phonocardiogram classification using deep neural networks and weighted probability comparisons","volume":"42","author":"M. Sotaquir\u00e1","year":"2018","journal-title":"Journal of medical engineering & technology"},{"issue":"8","key":"pone.0316645.ref013","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1088\/1361-6579\/aa7982","article-title":"Ensemble methods with outliers for phonocardiogram classification","volume":"38","author":"M.N. Homsi","year":"2017","journal-title":"Physiological measurement"},{"key":"pone.0316645.ref014","doi-asserted-by":"crossref","unstructured":"Vernekar, S., S. Nair, D. Vijaysenan, and R. Ranjan. A novel approach for classification of normal\/abnormal phonocardiogram recordings using temporal signal analysis and machine learning. in 2016 computing in cardiology conference (CinC). 2016. IEEE.","DOI":"10.22489\/CinC.2016.326-144"},{"key":"pone.0316645.ref015","doi-asserted-by":"crossref","unstructured":"Ozkan, I. and A. Yilmaz. Performance of using Mel-Frequency Cepstrum Based Features in Nonlinear Classifiers for Phonocardiography Recordings. in 2023 31st European Signal Processing Conference (EUSIPCO). 2023. IEEE.","DOI":"10.23919\/EUSIPCO58844.2023.10289832"},{"issue":"1","key":"pone.0316645.ref016","doi-asserted-by":"crossref","first-page":"14392","DOI":"10.1038\/s41598-023-41102-8","article-title":"Novel phonocardiography system for heartbeat detection from various locations","volume":"13","author":"R. Jaros","year":"2023","journal-title":"Scientific Reports"},{"key":"pone.0316645.ref017","doi-asserted-by":"crossref","first-page":"105186","DOI":"10.1016\/j.bspc.2023.105186","article-title":"CNN-based classification of phonocardiograms using fractal techniques","volume":"86","author":"D. Riccio","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"4","key":"pone.0316645.ref018","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1088\/0967-3334\/31\/4\/004","article-title":"Segmentation of heart sound recordings by a duration-dependent hidden Markov model","volume":"31","author":"S.E. Schmidt","year":"2010","journal-title":"Physiological measurement"},{"issue":"4","key":"pone.0316645.ref019","first-page":"822","article-title":"Logistic regression-HSMM-based heart sound segmentation","volume":"63","author":"D.B. Springer","year":"2015","journal-title":"IEEE transactions on biomedical engineering"},{"key":"pone.0316645.ref020","doi-asserted-by":"crossref","first-page":"102208","DOI":"10.1016\/j.bspc.2020.102208","article-title":"Robust heart sound segmentation based on spectral change detection and genetic algorithms","volume":"63","author":"M.A. Alonso-Ar\u00e9valo","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0316645.ref021","doi-asserted-by":"crossref","first-page":"100283","DOI":"10.1016\/j.smhl.2022.100283","article-title":"A critical review of heart sound signal segmentation algorithms","volume":"24","author":"M.M. Milani","year":"2022","journal-title":"Smart Health"},{"key":"pone.0316645.ref022","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.bspc.2017.08.002","article-title":"Classification of heart sound signal using curve fitting and fractal dimension","volume":"39","author":"M. Hamidi","year":"2018","journal-title":"Biomedical Signal Processing and Control"},{"issue":"6","key":"pone.0316645.ref023","doi-asserted-by":"crossref","first-page":"2435","DOI":"10.1109\/JBHI.2019.2894222","article-title":"Deep convolutional neural networks for heart sound segmentation","volume":"23","author":"F. Renna","year":"2019","journal-title":"IEEE journal of biomedical and health informatics"},{"issue":"5","key":"pone.0316645.ref024","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1002\/jemt.22998","article-title":"Microscopic abnormality classification of cardiac murmurs using ANFIS and HMM","volume":"81","author":"H. Fahad","year":"2018","journal-title":"Microscopy research and technique"},{"issue":"4","key":"pone.0316645.ref025","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"S. Davis","year":"1980","journal-title":"IEEE transactions on acoustics, speech, and signal processing"},{"key":"pone.0316645.ref026","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10772-010-9088-7","article-title":"Front end analysis of speech recognition: a review.","volume":"14","author":"M. Anusuya","year":"2011","journal-title":"International Journal of Speech Technology"},{"issue":"12","key":"pone.0316645.ref027","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1088\/0967-3334\/37\/12\/2181","article-title":"An open access database for the evaluation of heart sound algorithms","volume":"37","author":"C. Liu","year":"2016","journal-title":"Physiological measurement"},{"issue":"23","key":"pone.0316645.ref028","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","author":"A.L. Goldberger","year":"2000","journal-title":"circulation"},{"key":"pone.0316645.ref029","volume-title":"MIT automated auscultation system","author":"Z.H. Syed","year":"2003"},{"issue":"4","key":"pone.0316645.ref030","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1109\/TBME.2006.889189","article-title":"A framework for the analysis of acoustical cardiac signals","volume":"54","author":"Z. Syed","year":"2007","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"11","key":"pone.0316645.ref031","doi-asserted-by":"crossref","first-page":"2611","DOI":"10.1109\/TBME.2015.2432129","article-title":"Acoustic features for the identification of coronary artery disease","volume":"62","author":"S.E. Schmidt","year":"2015","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"4","key":"pone.0316645.ref032","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1109\/JBHI.2013.2294399","article-title":"Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features","volume":"18","author":"C.D. Papadaniil","year":"2014","journal-title":"IEEE journal of biomedical and health informatics"},{"issue":"9","key":"pone.0316645.ref033","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1016\/j.compbiomed.2013.05.020","article-title":"Noise\/spike detection in phonocardiogram signal as a cyclic random process with non-stationary period interval","volume":"43","author":"H. Naseri","year":"2013","journal-title":"Computers in biology and medicine"},{"issue":"3","key":"pone.0316645.ref034","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.bspc.2012.11.008","article-title":"A robust heart sounds segmentation module based on S-transform","volume":"8","author":"A. Moukadem","year":"2013","journal-title":"Biomedical Signal Processing and Control"},{"issue":"10","key":"pone.0316645.ref035","doi-asserted-by":"crossref","first-page":"2438","DOI":"10.1109\/TBME.2010.2051225","article-title":"Separation of heart sound signal from noise in joint cycle frequency\u2013time\u2013frequency domains based on fuzzy detection","volume":"57","author":"H. Tang","year":"2010","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"pone.0316645.ref036","doi-asserted-by":"crossref","unstructured":"Samieinasab, M. and R. Sameni. Fetal phonocardiogram extraction using single channel blind source separation. in 2015 23rd Iranian Conference on Electrical Engineering. 2015. IEEE.","DOI":"10.1109\/IranianCEE.2015.7146186"},{"issue":"1","key":"pone.0316645.ref037","first-page":"8","article-title":"The Mystery and Clarity of Leonardo da Vinci\u2019s Coefficient of Friction","volume":"1","author":"S.V. Fedorov","year":"2023","journal-title":"Journal of Materials"},{"key":"pone.0316645.ref038","first-page":"122136","volume-title":"Mel frequency cepstral coefficient and its applications: A review","author":"Z.K. Abdul","year":"2022"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0316645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:07:25Z","timestamp":1735672045000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0316645"}},"subtitle":[],"editor":[{"given":"Xizhe","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":38,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0316645","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]}}}