Urban Noise Classification Using Machine Learning Techniques: Comparative Analysis and Future

This research paper investigates the effectiveness of various machine learning models for the classification of urban noise, focusing on Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), Long Short-Term Memory Networks (LSTM), and Random Forest (RF). Utilizing the UrbanSound8K dataset, the study aims to determine which model offers the highest accuracy and performance for categorizing urban sounds. The results reveal that the DNN model achieved the highest accuracy at 94.5%, followed by CNN at 90%, RF at 87%, and LSTM at 79%. The DNN’s superior performance is attributed to its deep hierarchical learning capabilities, while the CNN excels at spatial feature extraction from spectrograms. The RF model demonstrated robust generalization capabilities, and the LSTM model highlighted the need for further optimization in capturing temporal dependencies. The paper discusses the challenges faced, including data quality, computational limitations, and the need for efficient feature extraction, and suggests future research directions. These include advancing automated sound event detection, optimizing feature selection, exploring hybrid neural network architectures, and deploying models on edge devices. The findings emphasize the potential of deep learning models in enhancing urban noise monitoring systems and improving urban living conditions.