The identification method research for the helicopter flight based on decision-tree-based support vector machine with the parameter optimization

摘要

The accurate identification of the helicopter flight action is the basis for guiding the training of the pilot. According to the accuracy of the helicopter flight action recognition, the paper proposed a new decision-tree-based support vector machine method to realize the helicopter multi-flight action identification. Use the tree structure of the decision tree to solve the multi-class problem of support vector machine, the penalty parameters and kernel parameters of the support vector machine are optimized by genetic algorithm. In order to speed up the identification, the principal component analysis method is used to process the data samples, and the data sample dimension is reduced. Experiments show that the genetic algorithm can optimize the support vector function to improve the overall classification accuracy and the single recognition accuracy.