Comparison of crossing time estimation models in the Mediterranean Region to optimize safe pedestrian crossing behavior in signalized intersections

ABSTRACT

The present study examined pedestrian movements in five pedestrian crossings in Adana, Mersin, and Isparta provinces in the Mediterranean Region of Turkey. The effects of factors that contribute significantly to pedestrian crossing time were considered. Linear (multiple linear regression [MLR]), nonlinear (artificial neural network [ANN], adaptive neuro-fuzzy inference system [ANFIS]), particle swarm optimization (PSO), and crossing time models reported in the literature were used to estimate crossing times and compare the estimations to the collected data. The nonlinear ANN and ANFIS models achieved better predictions than the linear MLR. The models from the literature achieved worse results compared to the other models due to the limited number of included parameters, The model coefficients were calibrated with PSO to improve regional specificity and the accuracy of the predictions improved. Calibrating the models according to the characteristics of the study region improves the accuracy of the findings.

GRAPHICAL ABSTRACT

KEYWORDS:

• Safe crossing
• pedestrian
• ANN
• ANFIS
• PSO

Highlight

• Different pedestrian crossing times were calculated in different regions due to the different human behavior.

• Pedestrians acting as a platoon experience more delays than individual pedestrians because they interact with each other.

• In order to generalize the results of the study, it should be studied regionally instead of a single province.

• The higher the number of independent variables, the more accurately the crossing time is estimated.

• The models in the literature should be used after being calibrated with the appropriate optimization method.

• Nonlinear models (YSA, ANFIS) give better estimation results than linear models (MLR).

Acknowledgments

The study was funded by the Member Training (OYP) Unit of S. Demirel University. Project No: OYP09498-DR-17. We would like to thank Member Training (OYP) Unit of S. Demirel University, Isparta Municipal Traffic Office, Adana Municipal Traffic Office, Mersin Municipal Traffic Office for the kindly assistance.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the member training (oyp) unit of s. demirel university. project no: OYP09498-DR-17.].