Preprint Virtual Geographic Environment Based Coach Passenger Flow Forecasting

TL;DR

This paper presents a virtual geographic environment-based approach for coach passenger flow forecasting, utilizing regression models to analyze real-time traffic data and improve visualization and analysis of dynamic traffic information.

Contribution

It introduces a virtual geographic environment framework for coach passenger flow forecasting, applying regression models to enhance real-time traffic analysis and visualization.

Findings

Regression forecasting effectively predicts coach passenger flow.

Virtual geographic environment improves traffic data analysis.

Stable passenger flow patterns identified.

Abstract

This is the preprint version of our paper on 2015 IEEE Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA). There are lacks of integrated analysis and visual display of multiple real-time dynamic traffic information. This research proposed a deep research and application examples on this basis which is conducted in virtual geographic environment. Currently, there are many kinds of traffic passenger flow forecasting models, and the common models include regression forecasting model and time series prediction model. The coach passenger flow shows strong regularity and stability without longterm change trend, so this research adopts regression forecasting model to forecast the coach passenger flow