ABSTRACT
The intelligent vehicle road system can effectively improve the safety and traffic efficiency of road traffic. Fully comprehensive testing is an important prerequisite to ensure its large-scale application. To find the limits and typical traffic scenarios is the key to carrying out this type of testing. In response to the call of the national transportation power policy, this paper makes full use of data mining methods to study the identification and classification of the intelligent vehicle road system test set. With the support of real data, after repeated attempts and deductions, the proposed PCA-based intelligent identification and classification method for isolated forest test sets is obtained. Moreover, under the comparative experimental verification of isolation forest, PCA-logistic regression, and PCA-neural network, the method still possesses superiority and progress. This method can be applied to classify the natural driving data set, and extract the driving behavior data set of extreme and typical scenes.
