Nonparametric Single-Trial EEG Feature Extraction and Classification of Driver's Cognitive Responses. (29th May 2008)

• Record Type: Journal Article
• Authors: Lin Lin, Chin-Teng Chin-Teng; Lin Lin, Ken-Li Ken-Li; Ko Ko, Li-Wei Li-Wei; Liang Liang, Sheng-Fu Sheng-Fu; Kuo Kuo, Bor-Chen Bor-Chen; Chung Chung, I-Fang I-Fang
• Other Names: Lee Lee Chien-Cheng Chien-Cheng Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2008(2008)
• Publication Date: 2008-05-29
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2008/849040
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : We proposed an electroencephalographic (EEG) signal analysis approach to investigate the driver's cognitive response to traffic-light experiments in a virtual-reality-(VR-) based simulated driving environment. EEG signals are digitally sampled and then transformed by three different feature extraction methods including nonparametric weighted feature extraction (NWFE), principal component analysis (PCA), and linear discriminant analysis (LDA), which were also used to reduce the feature dimension and project the measured EEG signals to a feature space spanned by their eigenvectors. After that, the mapped data could be classified with fewer features and their classification results were compared by utilizing two different classifiers includingk nearest neighbor classification (KNNC) and naive bayes classifier (NBC). Experimental data were collected from 6 subjects and the results show that NWFE+NBC gives the best classification accuracy ranging from71 % ∼ 77 %, which is over10 % ∼ 24 % higher than LDA+KNN1. It also demonstrates the feasibility of detecting and analyzing single-trial EEG signals that represent operators' cognitive states and responses to task events.