Optimal wavelet sub-band selection using genetic algorithm
Peng Xu, Andrew K. Chan · 2003
In this paper, we proposed a technique to select optimal subset of features extracted from subbands generated from wavelet packets. The algorithm first selects an optimal subset of subbands, then it selects the subset of features belongs to these subbands. The genetic algorithm was used for the selection task. Our experiment shows that the algorithm effectively reduces the computation time and increases the accuracy.