Abstract
Pedestrian behavior and safety are emerging issues in current transportation. One way to safely study pedestrian dynamics, especially at potential conflict points such as crosswalks, is through micro-simulation. This tool provides the opportunity to repeatedly study pedestrian behavior and safety under different scenarios of interest. However, to obtain reliable results, micro-simulation models need to be calibrated and their parameters fine-tuned. One way to methodically calibrate these models is to identify the outcomes of interest, develop a predictive model for those specific outcomes, and use it as a tool to fine-tune the input parameters of the micro-simulation model. To be reliable, the results of the predictive model should be comparable to those of the micro-simulation model, and these should be validated. The aim of this research is to present a predictive model of pedestrian behavior and to evaluate this model and a conventional micro-simulation model developed using Vissim/Viswalk, given that the chosen common output is pedestrian crossing time. To achieve this goal, a multi-step procedure is followed, which is part of a more general methodological framework for calibrating the Vissim/Viswalk micro-simulation model. This evaluation consisted in a three-step validation procedure, i.e. visual, conceptual and operational validation. Operational (statistical) validation was performed by comparing the variances of the results to understand whether the predicted sample is representative of the simulated sample. A correlation of 97% have been found between the predicted and micro-simulated crossing time values, with mean values of 6.41s and 6.32s for the simulated and predicted crossing times, respectively. Furthermore, both the predicted and simulated crossing time values fall within the ranges found in the literature for field measurements of this variable, indicating good agreement with real observed pedestrian behavior.
Highlights
A sophisticated tool for transport infrastructure planning and design is micro-simulation: it allows to study different infrastructural options without their actual realization, in order to better meet the needs of the considered road users
Vissim/Viswalk simulations were run to obtain a set of simulated crossing times that could be compared to the predicted ones, and to generate a dataset consisting of combinations of input parameters and associated crossing times, which was used as a training set for the formulated neural network
The presented prediction model is based on the application of neural networks to reproduce a selected output of Vissim/Viswalk micro-simulation model, i.e. crossing time
Summary
A sophisticated tool for transport infrastructure planning and design is micro-simulation: it allows to study different infrastructural options without their actual realization, in order to better meet the needs of the considered road users. This paper is part of a broader research aimed at developing a calibration method for pedestrian micro-simulation models by applying a structured neural network as a prediction tool. This research topic is studied in relation to the action of pedestrians crossing the road at a roundabout entry leg. This type of location has been extensively studied from vehicular traffic perspective, focusing on the impact of pedestrians on vehicular capacity (Bak, & Kiec 2012; Brilon, & Miltner, 2005; Chen, Shao, & Hao 2008), research on pedestrian behavior at this type of urban location is still ongoing (Obsu, Meurer, Kassa, & Klar, 2016; Thakur, & Biswas, 2019). The widespread use of this type of infrastructure in today’s transport networks, highlighting the benefits in terms of safety and capacity for motorized traffic (Ambros, Novak, Borsos, Hoz, Kiec, Machcinik, & Ondrejka, 2016; Chen, 2013), makes it even more important to examine these benefits for the most vulnerable road users as well
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
