An integrated Gaussian mixture model to estimate vigilance level based on EEG recordings

Vigilance level estimation can be used to prevent disastrous accident occurring frequently in high-risk tasks. Electroencephalograph (EEG) based Brain Computer Interface (BCI) is one of the most important tools for detecting one's brain electrical activities. Unfortunately, several problems inc...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2014-04, Vol.129, p.107-113
Main Authors: Gu, Jing-Nan, Lu, Hong-Tao, Lu, Bao-Liang
Format: Article
Language:English
Subjects:
Applied sciences
Biological and medical sciences
Brain
Computer science
control theory
systems
Computer systems and distributed systems. User interface
Data processing. List processing. Character string processing
EEG
Electrodiagnosis. Electric activity recording
Electroencephalography
Estimates
Exact sciences and technology
Gaussian mixture model
Human-computer interface
Investigative techniques, diagnostic techniques (general aspects)
Labeling
Mathematical models
Medical sciences
Memory organisation. Data processing
Nervous system
Software
Vigilance
Vigilance estimation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Vigilance level estimation can be used to prevent disastrous accident occurring frequently in high-risk tasks. Electroencephalograph (EEG) based Brain Computer Interface (BCI) is one of the most important tools for detecting one's brain electrical activities. Unfortunately, several problems including its sensitivity to artifacts, inaccurate labels and the great diversity of patterns within EEG signals present great challenges to predict vigilance level reliably. In this paper we propose an integrated approach to estimate vigilance level, which incorporates an automatically artifact removing preprocess, a novel vigilance labeling method and finally a Gaussian Mixed Model (GMM) to discover the underlying pattern of EEG signals. Extensive off-line experiments are conducted on 12 groups of data sets to show the effectiveness of our integrated approach in the real-time application. A reasonably high classification performance (88.46% over 12 data sets) is obtained with low delay by employing only one channel in the frontal lobe, which is in accordance with the conclusions of brain science and is of significance in practice.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2012.10.042