By Topic

A Chromatic Transient Visual Evoked Potential Based Encoding/Decoding Approach for Brain–Computer Interface

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Sui Man Lai ; Dept. of Electr. & Electron. Eng., Univ. of Hong Kong, Hong Kong, China ; Zhiguo Zhang ; Yeung Sam Hung ; Zhendong Niu
more authors

This paper presents a new encoding/decoding approach to brain-computer interface (BCI) based on chromatic transient visual evoked potential (CTVEP). The proposed CTVEP-based encoding/decoding approach is designed to provide a safer and more comfortable stimulation method than the conventional VEP-based stimulation methods for BCI without loss of efficiency. For this purpose, low-frequency isoluminant chromatic stimuli are time-encoded to serve as different input commands for BCI control, and the superior comfortableness of the proposed stimulation method is validated by a survey. A combination of diversified signal processing techniques are further employed to decode the information from CTVEP. Based on experimental results, a properly designed configuration of the CTVEP-based stimulation method and a tailored signal processing framework are developed. It is demonstrated that high performance (at information transfer rate: 58.0 bits/min, accuracy: 94.9%, false alarm rate: 1.3%) for BCI can be achieved by means of the CTVEP-based encoding/decoding approach. It turns out that to achieve such good performance, only simple signal processing algorithms with very low computational complexity are required, which makes the method suitable for the development of a practical BCI system. A preliminary prototype of such a system has been implemented with demonstrated applicability.

Published in:

Emerging and Selected Topics in Circuits and Systems, IEEE Journal on  (Volume:1 ,  Issue: 4 )