Traffic Jam Prediction Based on Analysis of Residents Spatial Activities

The prediction of urban traffic congestion has always been one of the important contents in the research of intelligent transportation systems. The difficulty in predicting urban traffic congestion is that urban traffic operation is essentially a collection of spatial activity planning for residents under certain conditions. The huge group of residents themselves has great complexity and uncertainty. Traditional neural networks mostly focus on road characteristic data and road condition data, and lack of in-depth exploration of the fundamental factors of traffic congestion for residents’ travel. So we propose a traffic congestion prediction model based on the analysis of residents’ spatial activities. Starting from the residents’ activities, the simulation of urban traffic operation conditions can more realistically reflect the traffic congestion situation of the city at specific times and roads, and quickly generate model results. The experimental results show that the model analyzed by residents’ spatial activities runs fast and has high prediction accuracy. The results are in line with the actual situation and have strong practical value.

Recommended citation: Lv, Z., Fu, H., Tang, W., & Chen, X. (2020, April). Traffic jam prediction based on analysis of residents spatial activities. In 2020 International Conference on Computer Information and Big Data Applications (CIBDA) (pp. 37-40). IEEE.
Download Paper