Air Target Intention Recognition Based on Further Clustering and Sample Expansion

Abstract

Concerning the first problem, the further clustering algorithm, which is established based on Euclidean Distance, provides a new method of clustering which can make full use of the intrinsic information of sample; Concerning the second problem, the sample expansion algorithm is put forward to increase the number of sample and promote the prediction accuracy. Then, by using Neural Network, an instance of ATIR is studied. The result shows that the combination of further clustering algorithm and the sample expansion method algorithm is effective.