Urban road short time based on machine learning algorithm empirical study on traffic flow forecast

Abstract

As one of the effective technical means to improve traffic management and alleviate traffic congestion, short-term traffic flow prediction on urban roads has been rapidly applied and developed with the development of machine learning algorithms, and has achieved good prediction results. Reviewed the basic characteristics of traffic flow and the classification of prediction models. On this basis, the development trajectory of deep learning technology and its application in the future field of transportation engineering were discussed. Based on the actual traffic data of Chongqing Dadukou, a deep learning model framework, overall data preprocessing method, and feature engineering idea for short-term traffic flow prediction were designed. Based on the actual collection of data in the experimental area and the establishment of relevant models, the training process of the model and the adjustment and optimization of hyperparameters were optimized to make it more stable and accurate in prediction. At the same time, quantitative analysis was conducted on different evaluation indicators, and it was concluded that the model has strong robustness and generalization ability for different traffic conditions. The conclusion indicates that the model has good accuracy and universality when applied to short-term traffic flow prediction on urban roads, and can assist in intelligent management of urban traffic. Summarized the main conclusions of this article and explored possible directions for future work: firstly, conducted in-depth research on multi-source data fusion technology and interpretability of models.