Neural Network Based Detection of Drowsiness with Eyes Open using AR Modelling

ABSTRACT

This paper proposes a method of neural network based drowsiness detection with eyes open using power spectrum analysis and auto-regressive modelling. After the electroencephalogram measurements are complete, alertness, transient, and drowsy periods are classified according to alpha spectrum changes and alpha-blocking phenomena. Although the subject's eyes are open, alpha spectrum changes such as drowsiness patterns are detected. Consequently, drowsiness detection with eyes open is applied into the proposed system. The neural network based proposed method shows that LPC (linear predictive coding) coefficients are the proper feature vectors and average classification rate is about 92%.

KEYWORDS:

• Drowsiness detection
• EEG
• Feature extraction
• LPC coefficients
• Neural network
• Multi-layer perceptron

ACKNOWLEDGMENTS

This research was supported by University of Ulsan.

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Funding

University of Ulsan.

Notes on contributors

Hyungseob Han

Hyungseob Han received his BS and MS degrees in computer engineering from the University of Ulsan, Ulsan, Korea in 2009 and 2011, respectively. He has been studying computer engineering at the University of Ulsan to earn his PhD degree since 2011. He worked for the School of Electrical Engineering at the University of Ulsan as a guest professor in 2013 and 2014. His current research interests include biomedical signal processing, fault detection and diagnosis in the plants, nonlinear signal analysis, and feature extraction algorithms.

E-mail: [email protected]

Uipil Chong

Uipil Chong received the BS degree in electrical engineering from the University of Ulsan, Ulsan, Korea, in 1978, and his MS degree in electrical engineering from Korea University, Seoul, Korea in 1980. He studied in the field of computer engineering of Oregon State University and received MS degree in 1985 and received PhD degree at New York University (POLY), in 1997. In January of 1997, Dr Chong joined the School of Electrical Engineering, University of Ulsan in Ulsan City, Korea where he has been promoted to full professor since 2006. He has more than 300 papers and holds 30 Korean patents in the area of digital signal processing, fault detection and diagnosis, biomedical engineering, and multimedia applications. He is a member of IEEE since 1993 and Eta Kappa Nu since 1995. Currently, he is the head of Whale Research Institute in University of Ulsan.

E-mail: [email protected]