Adaptive feature extractions in an EEG-based alertness estimation system

Chin Teng Lin, Wen Hung Chao, Yu Chieh Chen, Sheng Fu Liang

Research output: Contribution to journal › Conference article

Abstract

During the past years, the public security has become an important issue, especially, the safe manipulation and control of various vehicles. Maintaining high cognition is particularly important for the drivers behind the steering wheel. It requires an optimal estimation system to online continuously detect drivers' cognitive state related to abilities in perception, recognition, and vehicle control. In this paper, we proposed an EEG-based alertness estimation system with automatic feature selection mechanism. The independent component analysis (ICA) is used first to decompose the measured electroencephalogram (EEG). Then, a time-frequency analysis is performed to evaluate the time-frequency characteristic of each ICA component. We also proposed a new adaptive feature extracting mechanism for selections of frequency bands and ICA components. Different ranges of the alpha rhythm of subjects can be evaluated by the adaptive feature extracting mechanism according to the correlation coefficient between the ICA time-frequency response and the driving performance. The extracted features are then trained both by linear regression model and Self-cOnstructing Neuro-Fuzzy Inference Network (SONFIN) for the estimation of driving performance. The training and testing results of SONFIN are 96% and 91%, while the results of linear regression model are 90% and 85%, respectively. It demonstrates that the proposed adaptive feature extracting mechanism can achieve a great performance in alertness estimation with frequency band and component selection.

Original languageEnglish
Pages (from-to)2096-2101
Number of pages6
JournalConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume3
Publication statusPublished - 2005 Dec 1
EventIEEE Systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on Systems, Man and Cybernetics - Waikoloa, HI, United States
Duration: 2005 Oct 10 → 2005 Oct 12

Fingerprint

Independent component analysis
Electroencephalography
Feature extraction
Fuzzy inference
Linear regression
Frequency bands
Bioelectric potentials
Frequency response
Wheels
Testing

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Lin, Chin Teng ; Chao, Wen Hung ; Chen, Yu Chieh ; Liang, Sheng Fu. / Adaptive feature extractions in an EEG-based alertness estimation system. In: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2005 ; Vol. 3. pp. 2096-2101.
@article{efcc38bc22504ab68306793850811cd0,
title = "Adaptive feature extractions in an EEG-based alertness estimation system",
abstract = "During the past years, the public security has become an important issue, especially, the safe manipulation and control of various vehicles. Maintaining high cognition is particularly important for the drivers behind the steering wheel. It requires an optimal estimation system to online continuously detect drivers' cognitive state related to abilities in perception, recognition, and vehicle control. In this paper, we proposed an EEG-based alertness estimation system with automatic feature selection mechanism. The independent component analysis (ICA) is used first to decompose the measured electroencephalogram (EEG). Then, a time-frequency analysis is performed to evaluate the time-frequency characteristic of each ICA component. We also proposed a new adaptive feature extracting mechanism for selections of frequency bands and ICA components. Different ranges of the alpha rhythm of subjects can be evaluated by the adaptive feature extracting mechanism according to the correlation coefficient between the ICA time-frequency response and the driving performance. The extracted features are then trained both by linear regression model and Self-cOnstructing Neuro-Fuzzy Inference Network (SONFIN) for the estimation of driving performance. The training and testing results of SONFIN are 96{\%} and 91{\%}, while the results of linear regression model are 90{\%} and 85{\%}, respectively. It demonstrates that the proposed adaptive feature extracting mechanism can achieve a great performance in alertness estimation with frequency band and component selection.",
author = "Lin, {Chin Teng} and Chao, {Wen Hung} and Chen, {Yu Chieh} and Liang, {Sheng Fu}",
year = "2005",
month = "12",
day = "1",
language = "English",
volume = "3",
pages = "2096--2101",
journal = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",
issn = "1062-922X",

}

Lin, CT, Chao, WH, Chen, YC & Liang, SF 2005, 'Adaptive feature extractions in an EEG-based alertness estimation system', Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, vol. 3, pp. 2096-2101.

Adaptive feature extractions in an EEG-based alertness estimation system. / Lin, Chin Teng; Chao, Wen Hung; Chen, Yu Chieh; Liang, Sheng Fu.

In: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, Vol. 3, 01.12.2005, p. 2096-2101.

Research output: Contribution to journal › Conference article

TY - JOUR

T1 - Adaptive feature extractions in an EEG-based alertness estimation system

AU - Lin, Chin Teng

AU - Chao, Wen Hung

AU - Chen, Yu Chieh

AU - Liang, Sheng Fu

PY - 2005/12/1

Y1 - 2005/12/1

N2 - During the past years, the public security has become an important issue, especially, the safe manipulation and control of various vehicles. Maintaining high cognition is particularly important for the drivers behind the steering wheel. It requires an optimal estimation system to online continuously detect drivers' cognitive state related to abilities in perception, recognition, and vehicle control. In this paper, we proposed an EEG-based alertness estimation system with automatic feature selection mechanism. The independent component analysis (ICA) is used first to decompose the measured electroencephalogram (EEG). Then, a time-frequency analysis is performed to evaluate the time-frequency characteristic of each ICA component. We also proposed a new adaptive feature extracting mechanism for selections of frequency bands and ICA components. Different ranges of the alpha rhythm of subjects can be evaluated by the adaptive feature extracting mechanism according to the correlation coefficient between the ICA time-frequency response and the driving performance. The extracted features are then trained both by linear regression model and Self-cOnstructing Neuro-Fuzzy Inference Network (SONFIN) for the estimation of driving performance. The training and testing results of SONFIN are 96% and 91%, while the results of linear regression model are 90% and 85%, respectively. It demonstrates that the proposed adaptive feature extracting mechanism can achieve a great performance in alertness estimation with frequency band and component selection.

AB - During the past years, the public security has become an important issue, especially, the safe manipulation and control of various vehicles. Maintaining high cognition is particularly important for the drivers behind the steering wheel. It requires an optimal estimation system to online continuously detect drivers' cognitive state related to abilities in perception, recognition, and vehicle control. In this paper, we proposed an EEG-based alertness estimation system with automatic feature selection mechanism. The independent component analysis (ICA) is used first to decompose the measured electroencephalogram (EEG). Then, a time-frequency analysis is performed to evaluate the time-frequency characteristic of each ICA component. We also proposed a new adaptive feature extracting mechanism for selections of frequency bands and ICA components. Different ranges of the alpha rhythm of subjects can be evaluated by the adaptive feature extracting mechanism according to the correlation coefficient between the ICA time-frequency response and the driving performance. The extracted features are then trained both by linear regression model and Self-cOnstructing Neuro-Fuzzy Inference Network (SONFIN) for the estimation of driving performance. The training and testing results of SONFIN are 96% and 91%, while the results of linear regression model are 90% and 85%, respectively. It demonstrates that the proposed adaptive feature extracting mechanism can achieve a great performance in alertness estimation with frequency band and component selection.

UR - http://www.scopus.com/inward/record.url?scp=27944496835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27944496835&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:27944496835

VL - 3

SP - 2096

EP - 2101

JO - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

JF - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SN - 1062-922X

ER -

Lin CT, Chao WH, Chen YC, Liang SF. Adaptive feature extractions in an EEG-based alertness estimation system. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2005 Dec 1;3:2096-2101.

Access to Document