A Real-Time Machine Learning-Based Road Safety Monitoring and Assessment System

In this paper a system to monitor road conditions, detect unsafe driving behaviours and determine the influence of rainfall on traffic safety in real time using different machine learning algorithms, has been proposed. The system developed consists of a mobile application that captures car movement using its in-built accelerometer and gyroscope sensors and a server that monitors weather conditions at 16 key locations in Mauritius using the OpenWeather API. Road conditions, pothole, speed bumps as well as driving events were analysed using the K-Nearest Neighbour (KNN) and Multi-Layer Perceptron (MLP) algorithms. Moreover, a mathematical model, which incorporates the predicted rainfall in the estimation of braking distance and recommended speed, has been proposed. An average accuracy of 80.9% was obtained for pothole detection, 70% for speed bumps and 85.5% for unsafe driving behaviours detection. The proposed model with rainfall data predicted the braking distance and recommended speed with a Mean Absolute Percentage Error (MAPE) of 14.7% and 0.735% respectively.