Enhancing road safety in internet of vehicles using deep learning approach for real-time accident prediction and prevention

Abstract

The paper proposes an Internet of Vehicles (IoV)-based Accident Prediction and Prevention System that leverages the Internet of Things (IoT) to tackle the road safety challenges arising from the increased rate and volume of traffic due to population growth. In order to enhance road safety and efficiency, the IoV devices enable real-time data transmission and analysis. The proposed multi-tier framework tracks vehicle and roadside unit (RSU) data, encompassing road traffic conditions and vehicle data. The framework integrates vehicles, road traffic, weather conditions, and external factors. On a cloud-based control server, the proposed Spatio-Temporal Conv-Long Short-Term Memory Autoencoder (STCLA) framework deals with and analyzes the resulting data. This research addresses road safety on the Internet of Vehicles via DL. It proposes a novel framework for real-time accident prevention and prediction, demonstrating its effectiveness and potential impact. In a year-long research in Hubei Province, China, data from two road segments demonstrated a substantial boost in predictive accuracy, achieving an Area Under the Receiver Operating Characteristic Curve (AUROC) score of 0.94.