Invited Talks

A Bayesian Approach for Feature Extraction in EEG-based Brain-Computer Interface

Seong-Whan Lee, Korea University

Abstract

This talk introduces a method for EEG-based Brain-Computer Interface (BCI) with motor imagery. There are two challenging problems in classifying a single-trial EEG of motor imagery. One is spectral filter optimization - The frequency bands, in which Event-Related Desynchronization (ERD) and Event-Related Synchronization (ERS) patterns reflect activation and deactivation of rhythmic activity, are highly variable across subjects and across even trials for the same subject. The other problem is spatial filter optimization - The EEG electrodes measure the superimposed signals that originated from various sources in a brain.

In this talk, I will introduce a novel method for class-discriminative feature extraction by means of simultaneous optimization of spatio-spectral filter in a Bayesian framework for motor imagery based BCI. The problem of optimizing spatio-spectral filter is formulated as estimation of a posterior probability density function (pdf). The feasibility and effectiveness of the proposed method are demonstrated by analyzing the results and its success on public databases. In our extensive experiments, the proposed method was statistically significant (≥95% confidence level) in terms of classification performance compared to the state-of-the-art methods in the literature.

Short Biography

Seong-Whan Lee received the B.S. degree in computer science and statistics from Seoul National University, Seoul, Korea, in 1984, and the M.S. and Ph.D. degrees in computer science from Korea Advanced Institute of Science and Technology (KAIST), Seoul, Korea, in 1986 and 1989, respectively. A Fellow of the IEEE, IAPR, and Korean Academy of Science and Technology, he is currently the Hyundai Motor Chair Professor at Korea University, Seoul, where he is the head of the Department of Brain and Cognitive Engineering and the Director of the Institute for Brain and Cognitive Engineering. He is the Principal Investigator of the World Class University (WCU) project on "Brain and Cognitive Engineering" research, which is funded by the Ministry of Education, Science and Technology of Korea. His current research interests include pattern recognition, computer vision, and brain informatics. He has more than 250 publications in international journals and conference proceedings, and authored ten books.

Dr. Lee received the First Outstanding Young Researcher Award at the Second International Conference on Document Analysis and Recognition in 1993. He received the Outstanding Research Award from the Korea Information Science Society in 1996. He received the Lotfi Zadeh Best Paper Award at the IEEE International Conference on Machine Learning and Cybernetics in 2011. He also received the Scientist of the Month Award from the Ministry of Education, Science and Technology of Korea in 2012.