Classification of Melakartha ragas using neural networks

The objective of this paper is to classify all the 72 Melakartha Ragas of South Indian Carnatic Music using musical features. Melakartha raga classification is done by incorporating the well known classifier named Artificial Neural Network (ANN) which is structured by Feed-forward network architecture with back propagation learning algorithm and Counter propagation network. This paper represents one of the first attempts to classify all the seventy two Melakartha ragas of Carnatic music using ANN. The musical features that efficiently classify the Melakartha ragas are found. The classification results show that the counter propagation networks perform better classification compared to back propagation neural networks.