Application of ant colony algorithm in feature extraction

In mode identification, the characteristic selection affects identification results directly. In order to select effective characteristics, a characteristic selection method based on an improved ant colony algorithm is proposed in this paper. Firstly, an improved ant colony algorithm based on information Shannon and the principles of characteristic selection in mode identification are introduced. And then the improved ant colony algorithm was used to select characteristics. It is proved by experiments that the proposed method can increase the identification rate greatly and has practical applications in mode identification