Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization
Electroencephalogram (EEG) signal peak detection is widely used in clinical applications. The peak point can be detected using several approaches, including time, frequency, time-frequency, and nonlinear domains depending on various peak features from several models. However, there is no study that...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Publishing Corporation
2014
|
Subjects: | |
Online Access: | http://eprints.utm.my/52873/1/Mohd.IbrahimShapiai2014_Featureselectionandclassifier.pdf |
_version_ | 1796859801539444736 |
---|---|
author | Adam, Asrul Shapiai, Mohd. Ibrahim Mohd. Tumari, Mohd. Zaidi Mohamad, Mohd. Saberi Mubin, Marizan |
author_facet | Adam, Asrul Shapiai, Mohd. Ibrahim Mohd. Tumari, Mohd. Zaidi Mohamad, Mohd. Saberi Mubin, Marizan |
author_sort | Adam, Asrul |
collection | ePrints |
description | Electroencephalogram (EEG) signal peak detection is widely used in clinical applications. The peak point can be detected using several approaches, including time, frequency, time-frequency, and nonlinear domains depending on various peak features from several models. However, there is no study that provides the importance of every peak feature in contributing to a good and generalized model. In this study, feature selection and classifier parameters estimation based on particle swarm optimization (PSO) are proposed as a framework for peak detection on EEG signals in time domain analysis. Two versions of PSO are used in the study: (1) standard PSO and (2) random asynchronous particle swarm optimization (RA-PSO). The proposed framework tries to find the best combination of all the available features that offers good peak detection and a high classification rate from the results in the conducted experiments. The evaluation results indicate that the accuracy of the peak detection can be improved up to 99.90% and 98.59% for training and testing, respectively, as compared to the framework without feature selection adaptation. Additionally, the proposed framework based on RA-PSO offers a better and reliable classification rate as compared to standard PSO as it produces low variance model. |
first_indexed | 2024-03-05T19:32:36Z |
format | Article |
id | utm.eprints-52873 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T19:32:36Z |
publishDate | 2014 |
publisher | Hindawi Publishing Corporation |
record_format | dspace |
spelling | utm.eprints-528732018-07-19T07:18:43Z http://eprints.utm.my/52873/ Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization Adam, Asrul Shapiai, Mohd. Ibrahim Mohd. Tumari, Mohd. Zaidi Mohamad, Mohd. Saberi Mubin, Marizan TK Electrical engineering. Electronics Nuclear engineering Electroencephalogram (EEG) signal peak detection is widely used in clinical applications. The peak point can be detected using several approaches, including time, frequency, time-frequency, and nonlinear domains depending on various peak features from several models. However, there is no study that provides the importance of every peak feature in contributing to a good and generalized model. In this study, feature selection and classifier parameters estimation based on particle swarm optimization (PSO) are proposed as a framework for peak detection on EEG signals in time domain analysis. Two versions of PSO are used in the study: (1) standard PSO and (2) random asynchronous particle swarm optimization (RA-PSO). The proposed framework tries to find the best combination of all the available features that offers good peak detection and a high classification rate from the results in the conducted experiments. The evaluation results indicate that the accuracy of the peak detection can be improved up to 99.90% and 98.59% for training and testing, respectively, as compared to the framework without feature selection adaptation. Additionally, the proposed framework based on RA-PSO offers a better and reliable classification rate as compared to standard PSO as it produces low variance model. Hindawi Publishing Corporation 2014 Article PeerReviewed application/pdf en http://eprints.utm.my/52873/1/Mohd.IbrahimShapiai2014_Featureselectionandclassifier.pdf Adam, Asrul and Shapiai, Mohd. Ibrahim and Mohd. Tumari, Mohd. Zaidi and Mohamad, Mohd. Saberi and Mubin, Marizan (2014) Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization. Scientific World Journal, 2014 . ISSN 2356-6140 http://dx.doi.org/10.1155/2014/973063 DOI: 10.1155/2014/973063 |
spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Adam, Asrul Shapiai, Mohd. Ibrahim Mohd. Tumari, Mohd. Zaidi Mohamad, Mohd. Saberi Mubin, Marizan Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title | Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title_full | Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title_fullStr | Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title_full_unstemmed | Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title_short | Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization |
title_sort | feature selection and classifier parameters estimation for eeg signals peak detection using particle swarm optimization |
topic | TK Electrical engineering. Electronics Nuclear engineering |
url | http://eprints.utm.my/52873/1/Mohd.IbrahimShapiai2014_Featureselectionandclassifier.pdf |
work_keys_str_mv | AT adamasrul featureselectionandclassifierparametersestimationforeegsignalspeakdetectionusingparticleswarmoptimization AT shapiaimohdibrahim featureselectionandclassifierparametersestimationforeegsignalspeakdetectionusingparticleswarmoptimization AT mohdtumarimohdzaidi featureselectionandclassifierparametersestimationforeegsignalspeakdetectionusingparticleswarmoptimization AT mohamadmohdsaberi featureselectionandclassifierparametersestimationforeegsignalspeakdetectionusingparticleswarmoptimization AT mubinmarizan featureselectionandclassifierparametersestimationforeegsignalspeakdetectionusingparticleswarmoptimization |