Parallel man-machine training in development of EEG-based cursor control

被引：109

作者：

Kostov, A ^{[1
]}

Polak, M

机构：

[1] Univ Alberta, Fac Rehabil Med, Edmonton, AB T6G 2G4, Canada

[2] Glenrose Rehabil Hosp, Edmonton, AB, Canada

[3] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2G4, Canada

来源：

IEEE TRANSACTIONS ON REHABILITATION ENGINEERING | 2000年 / 8卷 / 02期

关键词：

brain-computer interface (BCI); communication; control; electroencephalograph (EEG)-processing; machine learning; severe neuromuscular disability;

D O I：

10.1109/86.847816

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

A new parallel man-machine training approach to brain-computer interface (BCI) succeeded through a unique application of machine learning methods. The BCI system could train users to control an animated cursor on the computer screen by voluntary electroencephalogram (EEG) modulation. Our BCI system requires only two to four electrodes, and has a relatively short training time for both the user and the machine. Moving the cursor in one dimension, our subjects were able to hit 100% of randomly selected targets, while in two dimensions, accuracies of approximately 63% and 76% was achieved with our two subjects.

引用

页码：203 / 205

页数：3

共 8 条

[1] Armstrong W. W., 1996, HDB NEURAL COMPUTATI
[2] Klem G H, 1999, Electroencephalogr Clin Neurophysiol Suppl, V52, P3
[3] Kostov A., 1997, Proceedings of the RESNA '97 Annual Conference. Let's Tango - Partnering People and Technology, P54
[4] Pfurtscheller G, 1998, IEEE Trans Rehabil Eng, V6, P316, DOI 10.1109/86.712230
[5] PREDICTION OF THE SIDE OF HAND MOVEMENTS FROM SINGLE-TRIAL MULTICHANNEL EEG DATA USING NEURAL NETWORKS
PFURTSCHELLER, G
FLOTZINGER, D
MOHL, W
PELTORANTA, M
[J]. ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1992, 82 (04): : 313 - 315
[6] Polak M, 1998, P ANN INT IEEE EMBS, V20, P2058, DOI 10.1109/IEMBS.1998.747011
[7] WOLPAW JR, ELECTROENCEPHALGR CL, V90, P444
[8] WOLPAW JR, ELECTROENCEPHALOGR C, V78, P252

← 1 →