Gaber, M., Mohamed Wahaballa, A., Mahmoud Othman, A., Diab, A. (2017). TRAFFIC ACCIDENTS PREDICTION MODEL USING FUZZY LOGIC: ASWAN DESERT ROAD CASE STUDY. JES. Journal of Engineering Sciences, 45(No 1), 28-44. doi: 10.21608/jesaun.2017.116084
Mohammed Gaber; Amr Mohamed Wahaballa; Ayman Mahmoud Othman; Aboelkasim Diab. "TRAFFIC ACCIDENTS PREDICTION MODEL USING FUZZY LOGIC: ASWAN DESERT ROAD CASE STUDY". JES. Journal of Engineering Sciences, 45, No 1, 2017, 28-44. doi: 10.21608/jesaun.2017.116084
Gaber, M., Mohamed Wahaballa, A., Mahmoud Othman, A., Diab, A. (2017). 'TRAFFIC ACCIDENTS PREDICTION MODEL USING FUZZY LOGIC: ASWAN DESERT ROAD CASE STUDY', JES. Journal of Engineering Sciences, 45(No 1), pp. 28-44. doi: 10.21608/jesaun.2017.116084
Gaber, M., Mohamed Wahaballa, A., Mahmoud Othman, A., Diab, A. TRAFFIC ACCIDENTS PREDICTION MODEL USING FUZZY LOGIC: ASWAN DESERT ROAD CASE STUDY. JES. Journal of Engineering Sciences, 2017; 45(No 1): 28-44. doi: 10.21608/jesaun.2017.116084
TRAFFIC ACCIDENTS PREDICTION MODEL USING FUZZY LOGIC: ASWAN DESERT ROAD CASE STUDY
Department of Civil Engineering, Faculty of Engineering, Aswan University
Abstract
Transportation system plays an important role in human life and is one of the main indicators of the standard of living. Traffic accidents represent a major problem threatening people’s lives, health, and property. Also, these accidents on roads can threat the management of transportation system. Being unsafe, this system will be unable to work properly. Therefore, traffic accidents prediction models may help for understanding accident causes and the number of their occurrence under certain circumstances. This study aims at developing a prediction model for Aswan western desert road by using fuzzy logic which is known for its benefits in dealing with uncertainty problems. This is to be carried out by the use of actual accident data obtained from the Egyptian General Authority for Roads, Bridges, and Land Transport (GARBLT) with survey data for pavement conditions, traffic flow presented as average hourly traffic per lane (AHTL), speed, minor access, traffic signs conditions and road width which are the inputs of the model. Several types of model were developed using the Poisson regression model, negative binomial regression model and negative multinomial model based on generalized linear regression technique. On the contrary, the relationship between an accident and the influencing factors is nonlinear and complicated and the using of fuzzy is preferable because fuzzy logic system is good for dealing with nonlinear input and output relationship. The overall results of the study reveal that the predicted results using the proposed fuzzy logic system produce accurate and stable traffic accident predictions.