Data-driven road safety enhancement: neural network–based accident classification and safe route identification using spatial network analysis

Abstract

Road traffic accidents continue to pose a significant challenge to public safety, resulting in substantial human suffering, economic losses, and increasing pressure on transportation systems. This study proposes a data-driven intelligent transportation framework that integrates machine learning and spatial network analysis to support accident severity prediction, risk-aware route recommendation, and emergency response. A comprehensive dataset comprising traffic conditions, weather information, temporal attributes, roadway characteristics, vehicle information, and driver-related factors was analysed to identify the key determinants of accident severity. Multiple machine-learning models were evaluated, and the Multi-Layer Perceptron (MLP) classifier achieved the highest predictive performance, attaining an overall accuracy of 91.2%. To transform predictive outcomes into practical safety interventions, the proposed framework combines accident severity prediction with GPS-enabled spatial network analysis to identify high-risk road segments and recommend safer alternative routes. In addition, an automated SMS notification mechanism is incorporated to provide location-aware emergency alerts when high-risk situations are detected. The integration of predictive analytics, spatial risk assessment, safety-oriented routing, and emergency communication establishes a comprehensive decision-support framework for proactive accident prevention and transportation-safety management. The experimental results demonstrate that the proposed approach can effectively support safer mobility, improved situational awareness, and enhanced emergency response within intelligent transportation environments.