Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11] [ 12] [ 13]

¡@

Journal of Information Science and Engineering, Vol. 32 No. 1, pp. 229-241 (January 2016)


Command Recognition Based on Single-Channel Electroencephalography*


WEI-HO TSAI AND WEN-BIN JHENG
Department of Electronic Engineering
National Taipei University of Technology
Taipei, 116 Taiwan
E-mail: whtsai@ntut.edu.tw; t9418037@ntut.org.tw

This study proposes to recognize a user¡¦s intentions in selecting from a set of machine- controlling commands by measuring his/her brainwaves. Our strategy is to convert a multiple-choice decision into yes-no decisions. For example, in a task of dialing assistance, our system prompts the user to select from each of the digits, and then analyzes his/her brainwave to determine if each digit is what he/she wants. Assume that the user¡¦s intention is 7. Then, when the system prompts the user whether to choose digit 7, the resulting electroencephalogram (EEG) measured from the user should present a certain pattern of ¡§Yes¡¨; otherwise, the result should present a certain pattern of ¡§No¡¨. Hence, our system's goal is to determine whether the user¡¦s intention is ¡§Yes¡¨ or ¡§No¡¨ based on the measured EEG. This study uses a simple, portable, and cheap instrument that extracts a single-channel EEG from the user¡¦s frontal lobe. The underlying beta waves of EEG are then distilled and examined by a recurrent neural network to determine the user¡¦s intention. Our experiments conducted using 2400 test EEG samples from 10 subjects show that the recognition accuracy obtained with our system is 79.2%.

Keywords: binary decision, brainwave, command recognition, electroencephalogram, recurrent neural network

Full Text (¥ş¤åÀÉ) Retrieve PDF document (201601_13.pdf)

Received August 27, 2014; revised November 8, 2014, January 26, 2015; accepted March 3, 2015.
Communicated by Jen-Tzung Chien.
* This work was supported in part by the National Science Council, Taiwan, under Grant No. NSC101-2221-E- 027-128-MY2.