Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square
This paper describes the classification of infant cry with asphyxia using integration of Orthogonal Least Square and Support Vector Machine with Radial Basis Function kernel (OLS-SVM) and integration of Orthogonal Least Square with Multilayer Perceptron (OLS-MLP). The information embedded in the cry...
Published in: | Proceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics: Global Grand Challenge of Health Informatics, BHI 2012 |
---|---|
Main Author: | |
Format: | Conference paper |
Language: | English |
Published: |
2012
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84864249983&doi=10.1109%2fBHI.2012.6211734&partnerID=40&md5=50618ac3b00c1b92a14199083d826e7a |
id |
2-s2.0-84864249983 |
---|---|
spelling |
2-s2.0-84864249983 Sahak R.; Mansor W.; Khuan L.Y.; Zabidi A.; Yassin A.I.M. Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square 2012 Proceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics: Global Grand Challenge of Health Informatics, BHI 2012 10.1109/BHI.2012.6211734 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84864249983&doi=10.1109%2fBHI.2012.6211734&partnerID=40&md5=50618ac3b00c1b92a14199083d826e7a This paper describes the classification of infant cry with asphyxia using integration of Orthogonal Least Square and Support Vector Machine with Radial Basis Function kernel (OLS-SVM) and integration of Orthogonal Least Square with Multilayer Perceptron (OLS-MLP). The information embedded in the cry signal was extracted using Mel Frequency Cepstrum Coefficient (MFCC) analysis. The extracted features were then selected according to its error reduction ratio (ERR) using OLS. MLP and SVM were then used to distinguish between asphyxiated infant cry and normal cry. Classification accuracy was computed to evaluate the performance of both methods. The OLS-SVM has produced high classification accuracy (94.34%) compared to OLS-MLP when C and γ were set to 1 and 0.013 respectively, and the selection of coefficients is 30% of 33 filter banks. © 2012 IEEE. English Conference paper |
author |
Sahak R.; Mansor W.; Khuan L.Y.; Zabidi A.; Yassin A.I.M. |
spellingShingle |
Sahak R.; Mansor W.; Khuan L.Y.; Zabidi A.; Yassin A.I.M. Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
author_facet |
Sahak R.; Mansor W.; Khuan L.Y.; Zabidi A.; Yassin A.I.M. |
author_sort |
Sahak R.; Mansor W.; Khuan L.Y.; Zabidi A.; Yassin A.I.M. |
title |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
title_short |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
title_full |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
title_fullStr |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
title_full_unstemmed |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
title_sort |
Detection of asphyxia from infant cry using support vector machine and multilayer perceptron integrated with Orthogonal Least Square |
publishDate |
2012 |
container_title |
Proceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics: Global Grand Challenge of Health Informatics, BHI 2012 |
container_volume |
|
container_issue |
|
doi_str_mv |
10.1109/BHI.2012.6211734 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84864249983&doi=10.1109%2fBHI.2012.6211734&partnerID=40&md5=50618ac3b00c1b92a14199083d826e7a |
description |
This paper describes the classification of infant cry with asphyxia using integration of Orthogonal Least Square and Support Vector Machine with Radial Basis Function kernel (OLS-SVM) and integration of Orthogonal Least Square with Multilayer Perceptron (OLS-MLP). The information embedded in the cry signal was extracted using Mel Frequency Cepstrum Coefficient (MFCC) analysis. The extracted features were then selected according to its error reduction ratio (ERR) using OLS. MLP and SVM were then used to distinguish between asphyxiated infant cry and normal cry. Classification accuracy was computed to evaluate the performance of both methods. The OLS-SVM has produced high classification accuracy (94.34%) compared to OLS-MLP when C and γ were set to 1 and 0.013 respectively, and the selection of coefficients is 30% of 33 filter banks. © 2012 IEEE. |
publisher |
|
issn |
|
language |
English |
format |
Conference paper |
accesstype |
|
record_format |
scopus |
collection |
Scopus |
_version_ |
1809677913294897152 |