SVM (Support Vector Machine)-based road vehicle running speed prediction method

Abstract

The invention belongs to the intelligent traffic field, and relates to a SVM(Support Vector Machine)-based road vehicle running speed prediction method. The method comprises the following steps of: acquiring actual measured road speed data of a to-be-predicted road; normalizing the acquired actual measured road speed data, and grouping to get a data set; selecting a radial basis function as a kernel function of the SVM, and obtaining an optimal parameter of quadratic programming by a dynamic regulation method; solving a prediction function; predicting the road vehicle running speed according to the prediction function generated in the previous step, comparing the prediction result with the data in a test sample set, and evaluating the prediction error; and if the error is large, predicting after regulating the SVM parameter. With the prediction method of the invention, the generalization ability of a learning machine is improved, the local minimum problem is avoided; and in unsteady short-time traffic flow information prediction, even if the input signals are mixed with noise, the prediction precision also can be very high.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and can be directly applied to predict the running speed of a vehicle within a certain period of time on a certain section of road. Background technique [0002] In recent years, my country's economy has continued to maintain rapid growth, people's living standards have greatly improved, the degree of urbanization has increased significantly, and automobile consumption has also increased day by day. The problem of urban traffic congestion has become more prominent and difficult, which has had a great impact on people's work and life. . These impacts are mainly manifested in the following aspects: first, time wasting; second, resource wasting; third, reducing the response speed of emergency handling. Therefore, it is very important to judge road congestion by predicting the speed of road vehicles. At the same time, with the development of intelligent transportation systems, intelligent t...

AI Technical Summary

Problems solved by technology

However, the neural network is a heuristic technology that relies on experience, and the learning process adopts the principle of empirical risk minimization. In the case of small samples, it is prone to over-learning and lead to low generalization ability; in addition, for non-stationary short-term Traffic flow information, when the input signal is mixed with noise, the accuracy of neural network prediction is relatively low

Images