Recognition of Combat Intention with Insufficient Expert Knowledge

Abstract

Aiming at the problem that the relationship between targets’ state feature and combat intention cannot be quantified under the condition of insufficient expert knowledge, a combat intention recognition model based on deep neural network is designed. By introducing the ReLU activation function and the Adam optimization algorithm, the convergence speed of the model is improved, and the local optimization is effectively prevented. The experimental results show that the proposed method can effectively recognize the target's combat intention and obtain better recognition results.