Tree based classification of tabla strokes

TL;DR

This study evaluates the effectiveness of tree-based classifiers, especially random forest, in classifying overlapping tabla strokes using a custom dataset and multiple features, demonstrating superior performance over other methods.

Contribution

It introduces a novel application of tree classifiers to classify overlapping tabla strokes with a custom dataset and comprehensive feature extraction.

Findings

Random forest outperforms decision tree and ID3 classifiers.

All classifiers achieved high accuracy and ROC scores.

Random forest shows superior performance in classifying overlapping strokes.

Abstract

The paper attempts to validate the effectiveness of tree classifiers to classify tabla strokes especially the ones which are overlapping in nature. It uses decision tree, ID3 and random forest as classifiers. A custom made data sets of 650 samples of 13 different tabla strokes were used for experimental purpose. 31 different features with their mean and variances were extracted for classification. Three data sets consisting of 21361, 18802 and 19543 instances respectively were used for the purpose. Validation has been done using measures like ROC curve and accuracy. The experimental results showed that all the classifiers showing excellent results with random forest outperforming the other two. The effectiveness of random forest in classifying strokes which are overlapping in nature is done by comparing the known results of that with multi-layer perceptron.