Sustainable travel prediction of Intelligent Transportation System based on big data analysis

Based on big data analysis technology, the sustainable travel prediction of intelligent transportation system (ITS) monitors road network congestion in real time and predicts future transportation demand, thus adjusting traffic signals in a targeted manner, optimizing route planning, reducing traffic congestion, and improving road capacity. The highly dynamic traffic conditions are influenced by various factors, such as weather, holidays, and emergencies, which leads to limitations of existing methods, possibly causing unsatisfactory prediction results in practical applications. Therefore, this research studied the sustainable travel prediction of ITS based on big data analysis technology. First, the sustainable travel demand prediction of ITS in the context of big data was defined. Then the spatial correlation of urban areas in the sustainable travel prediction was modeled based on Graph Attention Network (GAT), thus improving the demand prediction accuracy of the model. In order to further improve the accuracy and practicality of prediction, various spatial dependence of sustainable travel demand was modeled using multi-graph convolutional network (GCN). Finally, the experimental results demonstrated the constructed model was effective.