Comparative Study of KNN Over CNN for Music Genre Classification to Improve Accuracy

In the study of music genre recognition, a comparison was made between K-Nearest Neighbors and Convolutional Neural Networks to determine which method provides better classification accuracy. The analysis was conducted using ten iterations for each algorithm, with the dataset split into 70% for training and 30% for testing. The results revealed that K-Nearest Neighbors achieved a remarkable accuracy of 95.3%, significantly outperforming CNN, which had an accuracy of 90.49%. The statistical significance of these results was confirmed with a p-value of 0.01, indicating that the observed difference in performance is statistically significant (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$p&lt;0.05$</tex>). This study clearly demonstrates that K-Nearest Neighbors is more effective for music genre classification compared to CNN. The KNN algorithm not only provided higher accuracy but also proved to be a more reliable method for identifying different types of music genres. This suggests that for tasks involving genre recognition, K-Nearest Neighbors may offer a more precise and dependable solution than CNN.