A Research On Support Vector Machines

Support Vector Machine (SVM) is a kind of novel machine learning methods based on statistic learning theory (SLT). In the 1990s, a more complete theoretical system - the achievement of statistical learning theory and neural networks, and other than because of the emerging machine learning methods of the difficulties encountered some important, such as how to determine the issue of network structure, overfitting and underfitting, the local minimum points ect, makes the rapid development and improvement of SVM in resolving the small sample, non-linear and high-dimensional pattern recognition problems in the performance of many unique advantages and can function to promote the use of fitted function and other machines learning problems. A complete theory, strong adaptability and global optimization, training time are short, good generalization performance advantages. Has become an international and domestic research hot spots. Because of its good performance, are already successfully applied in data mining, pattern recognition, aerial image recognition, and other fields.This paper presents the SVM basic concepts and methods. In the two categories of classification and multi-category classification on the basis of focus on the Huffman tree (HFMTree) method. Based on several multi-category classification algorithm research, analysis of the advantages and disadvantages of these algorithms, combined with Huffman tree, the introduction of a decision tree based on Huffman's multi-category classification algorithm. Finally in a variety of open data sets on the simulation experiments, the results show that the algorithm determine not only with high precision, but also training more efficient.As the communications, information and electronic engineering and computer technology to the rapid development of intelligent transport systems more and more extensive attention to the vehicle identification, license plate recognition technology has put forward higher requirements. This paper briefly introduced the characteristics of intelligent transportation systems and related technologies, based on the use of the above Huffman tree (HFMTree) multi-category classification of the decision tree algorithm simulation methods to deal with the problem of identification of vehicles models. Final results show that support vector machines in the transport system in the application of the feasibility and effectiveness, and has broad prospects.