Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry

Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry

The performance Mel Frequency Cepstrum Coefficient (MFCC) in extracting significant feature is influence by several important parameter settings, namely the number of filter banks, and the number of coefficients used in the final representation. These settings affect the way the features are represe...

Full description

Bibliographic Details
Published in:ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics
Main Author: Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
Format: Conference paper
Language:English
Published: 2011
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858785477&doi=10.1109%2fICCAIE.2011.6162147&partnerID=40&md5=b9e17a38216d602ca979da8224e0e1e1
id 2-s2.0-84858785477
spelling 2-s2.0-84858785477
Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
2011
ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics


10.1109/ICCAIE.2011.6162147
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858785477&doi=10.1109%2fICCAIE.2011.6162147&partnerID=40&md5=b9e17a38216d602ca979da8224e0e1e1
The performance Mel Frequency Cepstrum Coefficient (MFCC) in extracting significant feature is influence by several important parameter settings, namely the number of filter banks, and the number of coefficients used in the final representation. These settings affect the way the features are represented, and in turn, effect the performance of the classifier for diagnosis of the disease. Particle Swarm Optimization (PSO) algorithm is used in this work to adjust the parameters of the MFCC feature extraction method, together with the Multi-Layer Perceptron (MLP) classifier structure for diagnosis of infants with asphyxia. The extracted MFCC features were then used to train several MLP classifiers over different initialization values. The simultaneous optimization of MFCC parameters and MLP structure using PSO yielded 93.9% of classification accuracy. © 2011 IEEE.


English
Conference paper
author Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
spellingShingle Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
author_facet Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
author_sort Zabidi A.; Mansor W.; Khuan L.Y.; Yassin I.M.; Sahak R.
title Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
title_short Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
title_full Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
title_fullStr Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
title_full_unstemmed Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
title_sort Three-dimensional particle swam optimisation of Mel Frequency Cepstrum Coefficient computation and multilayer perceptron neural network for classifying asphyxiated infant cry
publishDate 2011
container_title ICCAIE 2011 - 2011 IEEE Conference on Computer Applications and Industrial Electronics
container_volume
container_issue
doi_str_mv 10.1109/ICCAIE.2011.6162147
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-84858785477&doi=10.1109%2fICCAIE.2011.6162147&partnerID=40&md5=b9e17a38216d602ca979da8224e0e1e1
description The performance Mel Frequency Cepstrum Coefficient (MFCC) in extracting significant feature is influence by several important parameter settings, namely the number of filter banks, and the number of coefficients used in the final representation. These settings affect the way the features are represented, and in turn, effect the performance of the classifier for diagnosis of the disease. Particle Swarm Optimization (PSO) algorithm is used in this work to adjust the parameters of the MFCC feature extraction method, together with the Multi-Layer Perceptron (MLP) classifier structure for diagnosis of infants with asphyxia. The extracted MFCC features were then used to train several MLP classifiers over different initialization values. The simultaneous optimization of MFCC parameters and MLP structure using PSO yielded 93.9% of classification accuracy. © 2011 IEEE.
publisher
issn
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1809677914504953856

Similar Items