An Improved Particle Swarm Optimization for Prediction of Accident Severity

In recent time, road traffic accidents are increased day by due to incremental growth in number of vehicles. Traffic also the crucial and important issue for achieving sustainable transportation development. One tasks is reduce design assessment policy. Many researchers consider accident developed prediction models measuring severity accidents. But accuracy one major issues. this work, an attempt made improve severity. To achieve same, a particle swarm optimization-based algorithm applied evaluating Prior implement PSO, two modification incorporated into PSO algorithm, called improved PSO. These modifications can be described as mutation operator trail candidate generation. The performance examined over dataset results evaluated using accuracy, recall@5 precision@5 metrics. Several existing techniques considered comparing IPSO algorithm. It revealed that achieves more accurate among all techniques.