An Economic Analysis Method of Weapon System Based on Weighted Feature Selection

In the traditional feature selection, only a simple feature selection can be made, which will lead to the loss of information. In this paper, the requirement of weapon system economic analysis on the cost forecasting and the importance analysis of tactical and technical indicators were taken into account, moreover, considering the shortcomings of the traditional method of feature selection. A weighted feature selection with the supervised wrapper mode was used in the economic analysis of weapon system, which can effectively distinguish the influence of different features on the cost. In view of the good application effects of support vector machine (SVM), as well as a good performance of the mixture of kernels, the relationship model among the features and the cost was established based on SVM with the mixture of kernels. In addition, considering the consistency of feature selection and the establishment of cost forecasting model, a joint optimization method based on hybrid particle swarm optimization (PSO) was adopted, which can achieve the influence analysis of features and the optimization of cost forecasting model, that is, the economic analysis and cost forecasting can be done synchronically. Experiments show that the proposed method is effective.