• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.142-145
• /
• 2011

뇌전도 기반 뇌-컴퓨터 인터페이스 기술은 신체 움직임이 불가능하거나 불편한 사람에게 새로운 의사전달 수단이 될 수 있으며 일반인에게도 상상만으로 컴퓨터 혹은 기계에 명령을 내릴 수 있게 하는 기술이다. 본 논문에서는 뇌-컴퓨터 인터페이스 연구 분야에 잘 알려진 Common Spatial Pattern (CSP), Invariant Common Spatial Pattern (iCSP) 그리고 Common Spatio-Spectral Pattern (CSSP) 알고리즘들의 성능을 비교 분석하였고, CSSP에 불변성(invariant)을 고려한 iCSSP를 제안하였다. 9명의 피험자로부터 상상움직임 실험을 통해 18셋의 뇌전도 데이터를 측정하였고, 4가지 알고리즘들을 성능 면에서 비교하였다. 그 결과 CSSP의 성능과 차이가 크지는 않지만, 본 연구에서 제안한 노이즈를 고려하여 최적의 필터를 구성하는 iCSSP에 대하여 더 나은 성능을 보여주는 결과들을 확인할 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.178-183
• /
• 2013

In this study, we proposed a method for electroencephalogram (EEG) classification using invariant CSP at special channels for improving the accuracy of classification. Based on the naive EEG signals from left and right hand movement experiment, the noises of contaminated data set should be eliminate and the proposed method can deal with the de-noising of data set. The considering data set are collected from the special channels for right and left hand movements around the motor cortex area. The proposed method is based on the fit of the adjusted parameter to decline the affect of invariant parts in raw signals and can increase the classification accuracy. We have run the simulation for hundreds time for each parameter and get averaged value to get the last result for comparison. The experimental results show the accuracy is improved more than the original method, the highest result reach to 89.74%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.1022-1028
• /
• 2013

It is well knowns that based on the CSP (Common Spatial Pattern) algorithm, the linear projection of an EEG (Electroencephalography) signal can be made to spaces that optimize the discriminant between two patterns. Sharing disadvantages from linear time invariant systems, CSP suffers from the non-stationary nature of EEGs causing the performance of the classification in a BCI (Brain-Computer Interface) system to drop significantly when comparing the training data and test data. The author has suggested a simple idea based on the parallel model of CSP filters to improve the performance of BCI systems. The model was tested with a simple CSP algorithm (without any elaborate regularizing methods) and a perceptron learning algorithm as a classifier to determine the improvement of the system. The simulation showed that the parallel model could improve classification performance by over 10% compared to conventional CSP methods.