A Modification to the Blind Source Separation and its Application on SEMG
Wei Guo Zhou · Chuangan jishu xuebao · 2009
In order to eliminate the signal aliasing of multi-channel Surface Electromyography(SEMG),this paper proposes a new separation method based on the referenced cumulant on the time-frequency.First,the technique calculates the cumulant matrices through taking the observation signals as the cross-reference signals.;second,gets the time-scale cumulant matrices through the time-frequency analysis;third,constructs the contrast function by the time-scale cumulant matrices.The estimation of the SEMG can be performed by the non-orthogonal joint diagonalization.The experimental results indicate that this method is an effective way to separate multi-channel SEMG,its separating effect is better than the FastICA and the JADE from the coefficient of similarity and the Performance Index,and the efficiency of this algorithm is also improved.