Vehicle Classification Method Based on Single-Point Magnetic Sensor

In this paper a novel and scientific vehicle classification method is proposed, which is used on a new single-point magnetic sensor. The original waveform is transformed into numerical format by the data fusion technology for feature extraction. The extracted feature subsets are evaluated by Filter-Filter-Wrapper model, and then the nonredundant feature subset which fully reflects the difference of various vehicle types and is adaptable to the vehicle classifier is determined. On the basis of the optimal feature subset, this paper provides a novel vehicle classification algorithm based on Clustering Support Vector Machines(C-SVM). Particle Swarm Optimization (PSO) is used to search the optimal kernel parameter and slack penalty parameter. The cross-validation result of 460 samples shows that the classification rate of proposed vehicle classification method is better than 99%. It demonstrates that the vehicle classification method would be able to enhance efficiency of data mining, capability of machine learning and accuracy of vehicle classification.