A New Systematic Approach of Using SVM, KNN, PNN and CNN to Achieve Higher Accuracy for Classification and Recognition of Music Genre

Nandkishor  Narkhede; Sumit  Mathur; Anand  Bhaskar; Mukesh  Kalla

Journal of Operating Systems Development & Trends

A New Systematic Approach of Using SVM, KNN, PNN and CNN to Achieve Higher Accuracy for Classification and Recognition of Music Genre

Abstract

In order to overcome challenges like finding songs that are similar, figuring out which cultures would enjoy particular music, conducting surveys, and using music as therapy, classification and recognition of music genres are essential. The expansion of music-related content available online has created new opportunities for the development of music referral systems, which support user communities in searching, finding, sharing, and producing digitally. Our aim is to develop a systematic approach to select the most optimum machine-learning algorithm for predicting song genre using Support Vector Machine (SVM), k-nearest neighbor (k-NN), Probabilistic Neural Network (PNN) and Convolutional Neural Network (CNN). We got the results for CNN having system’s accuracy level is 98.9% and a precision of 98.7%, f1 score of 97.5%, recall of 98.5%. and the accuracy level of the system is 98.3% from SVM, 98.5% from PNN, 99.9% from KNN.

Keywords

How to cite

Nandkishor Narkhede, Sumit Mathur, Anand Bhaskar, Mukesh Kalla. A New Systematic Approach of Using SVM, KNN, PNN and CNN to Achieve Higher Accuracy for Classification and Recognition of Music Genre. Journal of Operating Systems Development & Trends. 2023;10(1):1–11.

Download the citation: