基于多源数据融合和BP神经网络的公交客流预测研究OA

This study aims to explore the effective integration and application of multi-source data(including IC card data,passenger flow meters data,etc.)in the context of new urban ground public transportation travel patterns and prediction methods for urban ground public transportation passenger flow prediction.The core objective of the study is to address the issues of integrating and utilizing multi-source data,as well as the specific application and optimization of BP neural networks in urban public transportation passenger flow prediction.To this end,this paper systematically elaborates on the types and interrelationships of urban ground public transportation multi-source data,combines bus IC card data and passenger flow meter data,and uses Matlab and multi-source data fusion technology to systematically construct and optimize the BP neural network.Through the comparative analysis of the predicted results and actual values,it is found that the model has a good fitting degree and has achieved substantive progress in urban ground public transportation passenger flow prediction.