Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels

Mihong Yang, Huiyan Li, Xiaozhou Sun, Li Yang, Hailong Duan, Yanqiu Che, Chunxiao Han

Research output: Contribution to journalConference article

Abstract

Alertness is the state of attention by high sensory awareness. A lack of alertness is one of the main reasons of serious accidents. Traffic accidents caused by driver's drowsy driving have a high fatality rate. This paper presents an EEG-based alertness detection system. In order to ensure the convenience and long-Term wearing comfort of EEG recordings, the wearable electrode cap will be the principal choice in the future, and the selection of channels will be limited. We first built a 3-D simulated driving platform using Unity3D. Then, we perform an experiment with driving drift task. EEG signals are recorded form frontal and occipital regions. We select data segments using the driving reaction time, classify the state of alertness with a support vector machine (SVM), and select the optimal combination of channels with minimum number of channels. Our results demonstrate that alertness can be classified efficiently with one channel (PO6) at accuracy of 93.52%, with two channels (FP1+PO6) at 95.85% and with three channels (FP1+PO6+PO5 and FP1+PO6+POZ) at 96.11%.

Original languageEnglish (US)
Article number03009
JournalMATEC Web of Conferences
Volume214
DOIs
StatePublished - Oct 15 2018
Event2nd International Conference on Information Processing and Control Engineering, ICIPCE 2018 - Shanghai, China
Duration: Jul 27 2018Jul 29 2018

Fingerprint

Electroencephalography
Support vector machines
Highway accidents
Accidents
Electrodes
Experiments

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Yang, Mihong ; Li, Huiyan ; Sun, Xiaozhou ; Yang, Li ; Duan, Hailong ; Che, Yanqiu ; Han, Chunxiao. / Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels. In: MATEC Web of Conferences. 2018 ; Vol. 214.
@article{af1d0c7c03444d66aecabcd573c23572,
title = "Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels",
abstract = "Alertness is the state of attention by high sensory awareness. A lack of alertness is one of the main reasons of serious accidents. Traffic accidents caused by driver's drowsy driving have a high fatality rate. This paper presents an EEG-based alertness detection system. In order to ensure the convenience and long-Term wearing comfort of EEG recordings, the wearable electrode cap will be the principal choice in the future, and the selection of channels will be limited. We first built a 3-D simulated driving platform using Unity3D. Then, we perform an experiment with driving drift task. EEG signals are recorded form frontal and occipital regions. We select data segments using the driving reaction time, classify the state of alertness with a support vector machine (SVM), and select the optimal combination of channels with minimum number of channels. Our results demonstrate that alertness can be classified efficiently with one channel (PO6) at accuracy of 93.52{\%}, with two channels (FP1+PO6) at 95.85{\%} and with three channels (FP1+PO6+PO5 and FP1+PO6+POZ) at 96.11{\%}.",
author = "Mihong Yang and Huiyan Li and Xiaozhou Sun and Li Yang and Hailong Duan and Yanqiu Che and Chunxiao Han",
year = "2018",
month = "10",
day = "15",
doi = "10.1051/matecconf/201821403009",
language = "English (US)",
volume = "214",
journal = "MATEC Web of Conferences",
issn = "2261-236X",
publisher = "EDP Sciences",

}

Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels. / Yang, Mihong; Li, Huiyan; Sun, Xiaozhou; Yang, Li; Duan, Hailong; Che, Yanqiu; Han, Chunxiao.

In: MATEC Web of Conferences, Vol. 214, 03009, 15.10.2018.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels

AU - Yang, Mihong

AU - Li, Huiyan

AU - Sun, Xiaozhou

AU - Yang, Li

AU - Duan, Hailong

AU - Che, Yanqiu

AU - Han, Chunxiao

PY - 2018/10/15

Y1 - 2018/10/15

N2 - Alertness is the state of attention by high sensory awareness. A lack of alertness is one of the main reasons of serious accidents. Traffic accidents caused by driver's drowsy driving have a high fatality rate. This paper presents an EEG-based alertness detection system. In order to ensure the convenience and long-Term wearing comfort of EEG recordings, the wearable electrode cap will be the principal choice in the future, and the selection of channels will be limited. We first built a 3-D simulated driving platform using Unity3D. Then, we perform an experiment with driving drift task. EEG signals are recorded form frontal and occipital regions. We select data segments using the driving reaction time, classify the state of alertness with a support vector machine (SVM), and select the optimal combination of channels with minimum number of channels. Our results demonstrate that alertness can be classified efficiently with one channel (PO6) at accuracy of 93.52%, with two channels (FP1+PO6) at 95.85% and with three channels (FP1+PO6+PO5 and FP1+PO6+POZ) at 96.11%.

AB - Alertness is the state of attention by high sensory awareness. A lack of alertness is one of the main reasons of serious accidents. Traffic accidents caused by driver's drowsy driving have a high fatality rate. This paper presents an EEG-based alertness detection system. In order to ensure the convenience and long-Term wearing comfort of EEG recordings, the wearable electrode cap will be the principal choice in the future, and the selection of channels will be limited. We first built a 3-D simulated driving platform using Unity3D. Then, we perform an experiment with driving drift task. EEG signals are recorded form frontal and occipital regions. We select data segments using the driving reaction time, classify the state of alertness with a support vector machine (SVM), and select the optimal combination of channels with minimum number of channels. Our results demonstrate that alertness can be classified efficiently with one channel (PO6) at accuracy of 93.52%, with two channels (FP1+PO6) at 95.85% and with three channels (FP1+PO6+PO5 and FP1+PO6+POZ) at 96.11%.

UR - http://www.scopus.com/inward/record.url?scp=85059046442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059046442&partnerID=8YFLogxK

U2 - 10.1051/matecconf/201821403009

DO - 10.1051/matecconf/201821403009

M3 - Conference article

VL - 214

JO - MATEC Web of Conferences

JF - MATEC Web of Conferences

SN - 2261-236X

M1 - 03009

ER -