Comparison of Sound Classification Algorithms on NIGENS Dataset

This study examines the performance of several machine learning and deep learning algorithms in classifying sounds from the NIGENS dataset, which consists of 15 unique sound classes. The implementation included five distinct algorithms: Convolutional Neural Networks (CNN), k-Nearest Neighbors (KNN), Support Vector Machines (SVM), Long Short-Term Memory Networks (LSTM), and Random Forest. The models' performances are evaluated using classification measures such as Accuracy, precision, recall, F1-score, and Receiver Operating Characteristic (ROC) curves. The Random Forest method demonstrates the best overall accuracy of 86% when compared to other algorithms, with precision, recall, and F1-score values of 0.88, 0.86, and 0.86.