Music Genre Classification Using GA-Induced Minimal Feature-Set

We propose a genetic algorithm-based feature-selection method for music genre classification that not only increases the efficiency of standard classifiers, but also reduces the feature space to a bare-minimum. While previous works have been more focused on finding near-optimal features devoid of noise, we go for a modified fitness function capable of finding both the near-optimal and the near-minimal feature subset for classification. In addition to an enhanced performance, our model can also reduce the computational load for ill-formed sets and has the flexibility to incorporate trade-offs between efficiency and computational load. We finally demonstrate that the modified GA is capable of bringing about an 80% reduction in the feature space dimension at similar classification rates.