Forecasting Daily Pedestrian Flows in the Tiananmen Square Based on Historical Data and Weather Conditions
Lida Huang, Tao Chen, Yan Wang, Hongyong Yuan
It is important to forecast the pedestrian flows for organizing crowd activities and making risk assessments. In this article, the daily pedestrian flows in the Tiananmen Square are forecasted based on historical data, the distribution of holidays and weather conditions including rain, wind, temperature, relative humidity, and AQI (Air Quality Index). Three different methods have been discussed and the Support Vector Regression based on the Adaptive Particle Swarm Optimization (APSO-SVR) has been proved the most reliable and accurate model to forecast the daily pedestrian flows. The results of this paper can help to conduct security pre-warning system and enhance emergency preparedness and management for crowd activities.