EEG Signal Analysis And Characterization For The Aid Of Disabled People
Free (open access)
M. B. I. Reaz, M. S. Hussain, M. I. Ibrahimy & F. Mohd-Yasin
The effectiveness of assistive devices for disabled people is often limited by the human machine interface. This research proposes an intelligent wheelchair system especially for severely disabled people based on analysing electroencephalographic signals by using discrete wavelet transform and higher order statistical methods. The system to be implemented in Field Programmable Gate Array enables an accurate and efficient system of processing signals to control the wheelchair, which makes an attractive option in the hardware realization. Keywords: EEG, wavelet, higher order statistic, bispectrum, FPGA, wheelchair. 1 Introduction As a result of accident or disease, millions of people worldwide suffer from loss of motor function. These people are forced to accept a reduced quality of life dependent on other individuals. Many assistive devices targeted at the integration of disabled individuals into society have been developed in the past, but the effectiveness of these aids for individuals with severe disabilities is often limited by the human machine interface. Probably, the most important one, as far as people with physical disabilities who are unable to walk are concerned, is a wheelchair. Nakanishi et al.  in 1999 proposed a powered wheelchair controlled by the face directional gestures recognized by a high-speed image processing hardware. However they did not discriminate whether the given gesture is intentional or unintentional behaviour. A Hands-free wheelchair control system relied on muscle contraction was proposed by Felzer and Freisleben  in 2002.
EEG, wavelet, higher order statistic, bispectrum, FPGA, wheelchair.