Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies.
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, yield...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0316645 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555601909350400 |
|---|---|
| author | Mehdi Hosseinzadeh Amir Haider Mazhar Hussain Malik Mohammad Adeli Olfa Mzoughi Entesar Gemeay Mokhtar Mohammadi Hamid Alinejad-Rokny Parisa Khoshvaght Thantrira Porntaveetus Amir Masoud Rahmani |
| author_facet | Mehdi Hosseinzadeh Amir Haider Mazhar Hussain Malik Mohammad Adeli Olfa Mzoughi Entesar Gemeay Mokhtar Mohammadi Hamid Alinejad-Rokny Parisa Khoshvaght Thantrira Porntaveetus Amir Masoud Rahmani |
| author_sort | Mehdi Hosseinzadeh |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-606d7ec0a25e45188cc5d3101b42a98c |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-606d7ec0a25e45188cc5d3101b42a98c2025-01-08T05:32:01ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e031664510.1371/journal.pone.0316645Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies.Mehdi HosseinzadehAmir HaiderMazhar Hussain MalikMohammad AdeliOlfa MzoughiEntesar GemeayMokhtar MohammadiHamid Alinejad-RoknyParisa KhoshvaghtThantrira PorntaveetusAmir Masoud RahmaniThis 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.https://doi.org/10.1371/journal.pone.0316645 |
| spellingShingle | Mehdi Hosseinzadeh Amir Haider Mazhar Hussain Malik Mohammad Adeli Olfa Mzoughi Entesar Gemeay Mokhtar Mohammadi Hamid Alinejad-Rokny Parisa Khoshvaght Thantrira Porntaveetus Amir Masoud Rahmani Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. PLoS ONE |
| title | Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. |
| title_full | Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. |
| title_fullStr | Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. |
| title_full_unstemmed | Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. |
| title_short | Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies. |
| title_sort | enhanced heart sound classification using mel frequency cepstral coefficients and comparative analysis of single vs ensemble classifier strategies |
| url | https://doi.org/10.1371/journal.pone.0316645 |
| work_keys_str_mv | AT mehdihosseinzadeh enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT amirhaider enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT mazharhussainmalik enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT mohammadadeli enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT olfamzoughi enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT entesargemeay enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT mokhtarmohammadi enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT hamidalinejadrokny enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT parisakhoshvaght enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT thantriraporntaveetus enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies AT amirmasoudrahmani enhancedheartsoundclassificationusingmelfrequencycepstralcoefficientsandcomparativeanalysisofsinglevsensembleclassifierstrategies |