Mental tasks discrimination by neural networks with wavelet transform

Abstract

The study mainly focuses on the analysis of Electroencephalogram (EEG), to classify mental tasks by using features based on wavelet transform. We have used the daubechies family wavelets, level 6, to transform obtained signal from independent component analyzed EEG signal. As Fourier analysis consists of breaking up a signal into sine waves of various frequencies. Similarly, wavelet analysis is the breaking up of a signal into shifted and scaled versions of the original wavelet. Signals with sharp changes might be better analyzed with a Wavelet than with a Fourier transform. It also makes sense that local features can be described well with wavelets that have local extent. This offers improved features to the neural networks obtaining several classified mental tasks. Through several processes, it led us more developed variety mental tasks classification results. We find that the neural networks perform over 75% success resulting with small number of electrodes better than a previous 70% resulting.

A BCI System for Physically Challenged Based on Alpha Dynamics of EEG Signals

“…Wavelet Packet Transform (WPT) method was used for feature extraction in the alpha frequency band for optimal discrimination between the mental imagery tasks [33]. Wavelet packet analysis is a generalization of wavelet decomposition that offers richer range of possibilities of signal analysis [34][35].…”

Estimation of Viewpoint Direction and Viewing Angle Using EOG

“…Support for independence of careers and the reduction of the burden on the caregiver side are huge problems. Recently, research on human-machine interface using biomedical signals that can be handled even by people with disabilities were undertaken for supporting the self-reliance of elderly people and persons with disabilities and reducing the burden of nursing persons [1][2][3][4][5][6][7][8][9][10][11].…”