Pedestrian choice behavior analysis and simulation of vertical walking facilities in transfer station

Abstract

Considering the interlayer height, luggage, the difference between queuing pedestrians, and walking speed, the pedestrian choice model of vertical walking facilities is established based on a support vector machine. This model is verified with the pedestrian flow data of Changchun light-rail transfer station and Beijing Xizhimen transfer station. Adding the pedestrian choice model of vertical walking facilities into the pedestrian simulation model which is based on cellular automata, the pedestrian choice behavior is simulated. In the simulation, the effects of the dynamic influence factors are analyzed. To reduce the conflicts between pedestrians in opposite directions, the layout of vertical walking facilities is improved. The simulations indicate that the improved layout of vertical walking facilities can improve the efficiency of pedestrians passing.

Simulation of Pedestrian Evacuation in University Canteen Based on Cellular Automata

“…In the simulation, we set k static = 3 and k dynamic = 0 following the relevant researches [32], [34]. From the observation, we find that when the number of pedestrians in line is greater than 10, pedestrians behind will not be lined up.…”

“…The concept of floor field has been proposed by Burstedde et al [33] in 2001, and it is subject to diffusion and decay. It has been demonstrated that the performance of floor field in CA-based pedestrian simulation is excellent [34]- [36]. Static floor field and dynamic floor field are both used in this study.…”

Modeling Pedestrian Choice Behavior of Vertical Walking Facilities in Rail Transit Station Considering Reminder Sign

“…In rail transit station, pedestrian choice of vertical walking facilities is the result of the interactions among many factors including sex, age, interlayer height, luggage, walking speed, the difference in the number of pedestrians in front of elevator and stairway (the difference in delay on waiting for escalator and stairway), walking time [3]- [5], [10]. These influence factors are interrelated with each other with collinearity and interdependence, and it is necessary to select the key influence factors [36].…”

“…In urban rail transit stations, vertical walking facilities including escalator and stairway are the main bottlenecks of pedestrian movement in the passage [1]- [3]. Pedestrian queuing is formed because the capacity of vertical walking facility is less than that of the passage.…”

“…However, logit model has the inherent defect that calibration result of the parameters is significantly influenced by the amount and quantity of survey data [8], [35]. Considering this problem, Li et al used the support vector machine (SVM) approach, which is indeed one of machine learning methods, to predict the pedestrian choice of vertical walking facilities, resulting in 89.38% of total prediction accuracy in the small-size test example [3]. As is well known, random forest (RF) is better in solving the problems featured with small sample and nonlinear classification.…”