Estimating The Number Of Traffic Accidents, Injuries And Fatalities In Turkey Using Adaptive Neuro-Fuzzy Inference System

Abstract

This study proposes Adaptive Neuro-Fuzzy Inference System (ANFIS) models to estimate the number of accidents, injuries and fatalities in Turkey. In the model development, population (P) and the number of vehicles (N) are selected as model parameters. Three different ANFIS structure models are developed using the data covering from 2000 to 2014. Developed models' results are statistically compared to observed values for training and test data in terms of root mean square errors (RMSE), mean absolute percentage errors (MAPE) and coefficient of determination (R-2). The results of the ANFIS models showed that they was suitable to estimate the number of accidents, injuries and fatalities. To investigate the performance of ANFIS models for future estimations, a ten-year period from 2015 to 2024 is considered. Thus, future values of population was obtained from the projection of Turkish Statistical Institute (TSI) and the vehicle ownership rate is expected to reach 0.4 by 2024. Therefore, population and the number of vehicles are considered to reach approximately 85 and 34 million, respectively. The results obtained from future estimations reveal the suitability of ANFIS approach for road safety applications.