Journal
JOURNAL OF NEURAL ENGINEERING
Volume 5, Issue 3, Pages 342-349Publisher
IOP PUBLISHING LTD
DOI: 10.1088/1741-2560/5/3/007
Keywords
-
Categories
Funding
- National Natural Science Foundation of China [30630022]
- Science and Technology Ministry of China [2006BAI03A17]
- Tsinghua-Yu-Yuan Medical Sciences
Ask authors/readers for more resources
A motor imagery based brain-computer interface (BCI) provides a non-muscular communication channel that enables people with paralysis to control external devices using their motor imagination. Reducing the number of electrodes is critical to improving the portability and practicability of the BCI system. A novel method is proposed to reduce the number of electrodes to a total of four by finding the optimal positions of two bipolar electrodes. Independent component analysis (ICA) is applied to find the source components of mu and alpha rhythms, and optimal electrodes are chosen by comparing the projection weights of sources on each channel. The results of eight subjects demonstrate the better classification performance of the optimal layout compared with traditional layouts, and the stability of this optimal layout over a one week interval was further verified.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available