Air Target Route Rule Mining Based on Clustering

Abstract

The air target activity is frequent, how to better study and judge the target is an important problem facing at present. The route rule of target is an important feature of judge and recognition. In order to improve the intelligence degree of air target routing rule mining and get rid of the interference of artificial experience and subjective factors, this paper proposes a method of air target route rule mining based on clustering. Firstly, the distance between any two routes is defined based on Hausdorff distance. Secondly, the K-means algorithm was improved, a distance threshold was set to ensure that the clustering centers would not be completely randomly selected, and the optimal number of clustering was selected by elbow method. Finally, routes in a certain airspace were obtained by simulation, and the rules of routes were obtained by clustering mining. Through the simulation experiment, 21 airlines were simulated. The optimal clustering number was determined to be 4 by elbow method, and the SSE of clustering by K-means algorithm was 1.03.