Improving EEG Signal Peak Detection Using Feature Weight Learning of a Neural Network with Random Weights for Eye Event-Related Applications

Asrul, Adam and Zuwairie, Ibrahim and Norrima, Mokhtar and Mohd Ibrahim, Shapiai and Cumming, Paul and Marizan, Mubin (2017) Improving EEG Signal Peak Detection Using Feature Weight Learning of a Neural Network with Random Weights for Eye Event-Related Applications. Sadhana, 42 (5). pp. 1-13. ISSN 0256-2499(print); 0973-7677(online). (Published)

PDF
Improving EEG signal peak detection using feature weight learning of a neural network with random weights for eye event-related applications.pdf - Published Version
Restricted to Repository staff only
Download (974kB) | Request a copy

Preview

PDF
Improving EEG signal peak detection using feature weight learning of a neural network with random weights for eye event-related applications 1.pdf - Published Version
Download (199kB) | Preview

DOI/Official URL: https://doi.org/10.1007/s12046-017-0633-9

Abstract

The optimization of peak detection algorithms for electroencephalogram (EEG) signal analysis is an ongoing project; previously existing algorithms have been used with different models to detect EEG peaks in various applications. However, none of the existing techniques perform adequately in eye event-related applications. Therefore, we aimed to develop a general procedure for eye event-related applications based on feature weight learning (FWL), through the use of a neural network with random weights (NNRW) as the classifier. The FWL is performed using a particle swarm optimization algorithm, applied to the well-studied Dumpala, Acir, Liu and Dingle peak detection models, where the associated features are considered as inputs to the NNRW with and without FWL. The combination of all the associated features from the four models is also considered, as a comprehensive model for validation purposes. Real EEG data recorded from two channels of 20 healthy volunteers were used to perform the model simulations. The data set consisted of 40 peaks arising in the frontal eye field in association with a change of horizontal eye gaze direction. It was found that the NNRW in conjunction with FWL has better performance than NNRW alone for all four peak detection models, of which the Dingle model gave the highest performance, with 74% accuracy.

Item Type:	Article
Uncontrolled Keywords:	Neural network with random weights (NNRW); Feature weight learning (FWL); Electroencephalogram (EEG); Peak detection algorithm; Pattern recognition; Particle swarm optimization (PSO)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division:	Faculty of Electrical & Electronic Engineering
Depositing User:	Mrs. Neng Sury Sulaiman
Date Deposited:	21 Jul 2017 01:27
Last Modified:	07 Feb 2018 07:43
URI:	http://umpir.ump.edu.my/id/eprint/17480
Download Statistic:	View Download Statistics

Actions (login required)

View Item