A Machine Learning Driven IoT Solution for Noise Classification in Smart Cities

TL;DR

This paper introduces a low-cost IoT-based noise classification system for smart cities using machine learning algorithms like SVM and KNN, achieving high accuracy and fast processing on embedded devices.

Contribution

It presents a novel, low-power IoT solution utilizing audio features and supervised learning for real-time noise classification in urban environments.

Findings

Achieved 85-100% classification accuracy.

Fast training and testing on Raspberry Pi Zero W.

Effective parameter optimization for classifiers.

Abstract

We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate our approach experimentally with a dataset of about 3000 sound samples grouped in eight sound classes (such as, car horn, jackhammer, or street music). We explore the parameter space of support vector machine and k-nearest neighbors algorithms to estimate the optimal parameter values for classification of sound samples in the dataset under study. We achieve a noise classification accuracy in the range 85% -- 100%. Training and testing of our k-nearest neighbors (k = 1) implementation on Raspberry Pi Zero W is less than a second for a dataset with features of more than 3000 sound samples.