Artificial Intelligence in the Prevention and Prediction of Traffic Accidents in Campinas

• Grant number: 25/12514-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2025
• End date: July 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Luiz Carlos Pereira da Silva
• Grantee: Lucas Machado
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 21/11380-5 - CPTEn - São Paulo Center for the Study of Energy Transition, AP.CCD

Abstract

This Scientific Initiation project proposes the development and application of ArtificialIntelligence (AI) techniques, focusing on Machine Learning (ML), to analyze, predict theseverity, and identify risk factors associated with traffic accidents in the city of Campinas, SP,Brazil. Using historical data provided by EMDEC, the study aims to explore models such asLogistic Regression, Random Forests, and Artificial Neural Networks to classify accidentseverity (fatal, serious injury, minor injury, property damage). The project includes stages ofliterature review, data collection and preprocessing, feature engineering, model training andoptimization, including handling imbalanced classes. The analysis of feature importance andmodel interpretability will allow for the derivation of actionable insights and the formulationof recommendations for road safety public policies in Campinas, with the ultimate goal ofcontributing to the reduction of traffic victims.