Optimization of Urban Mass Transit System Based on Support Vector Machine and Ant Colony Algorithm

Abstract

Due to the rapid growth of economy, the acceleration of urbanization, the rapid expansion of city scale and the rapid increase of urban population, the existing urban transportation can no longer meet the requirements of urban growth. The immature urban mass transit (UMT) system is the root of traffic congestion, so it is urgent to build an efficient and intelligent UMT system to solve the city transportation congestion problem. Based on the research of SVM (Support Vector Machines) algorithm and CAD theory, this article puts forward a traffic stream forecasting model according to the characteristics of UMT, thus providing support for the optimization of UMT system. The algorithm model is applied to the optimization of UMT system. This method optimizes the training parameters in SVM through GA to get the optimized SVM prediction model. Compared with traditional ant colony algorithm (ACA), this model has better fitting degree and higher accuracy with real data, and is suitable for UMT system optimization. In order to provide theoretical guidance and decision support for UMT related work.