Year: 2016
Type: article
Abstract: This paper presents the use of neural network classification thought- based commands for wheelchair control. The advantage is to assist the locked in people who are not able to use physical interfaces like joysticks or buttons. Electroencephalogram (EEG) was used to discriminate motor imagery mental tasks, such as imagination of left hand, right hand, both hands and both feet. The four task classifications were mapped into a wheelchair movement, such as forward, left, right, and backward. The motor imagery command data were collected from seven participants. A wireless device (Enobio) with 8 dry electrode recording was used. Discrete wavelet transform and Multiyear perceptron were utilized for signal processing. The results show that the proposed system provides a good classification performance with an average classification rate of 81.046%.
Institutions: Universiti Teknologi Petronas, Al-Neelain University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: diamond
Funder: Universiti Teknologi Petronas
OpenAlex ID: W2299241096