Feature selection is a well-studied problem in the areas of pattern recognition and artificial intelligence. Apart from reducing computational cost and time, a good feature subset is also imperative in improving the classification accuracy of automated classifiers. In this work, a wrapper-based feature selection approach is proposed using the evolutionary harmony search algorithm, whereas the classifiers used are the wavelet neural networks. The metaheuristic algorithm is able to find near-optimal solutions within a reasonable amount of iterations. The modifications are accomplished in two ways—initialization of harmony memory and improvisation of solutions. The proposed algorithm is tested and verified using UCI benchmark data sets, as well as two real life binary classification problems, namely epileptic seizure detection and prediction. The simulation results show that the standard harmony search algorithm and other similar metaheuristic algorithms give comparable performance. In addition, the enhanced harmony search algorithm outperforms the standard harmony search algorithm.