“…In general, almost all the feature selection methods described in the previous sections can be applied to WT coefficients; most used are filter and wrapper methods, e.g., GA [46,78]. Specific of feature selection in WT domain is that it can be applied scale/level-wise [79] or coefficients-wise [46,80,81], as well as the fact that WT decomposition parameters have to be set, such as a wavelet filter, decomposition level; some algorithms try to automatically iterate on these settings [46].…”