Abstract: |
Aiming at the traditional air target threat assessment method has large computational energy, poor real time performance, and is difficult to apply to the situation of lack of data, this paper proposes a method of using K nearest neighbor algorithm (KNN) to achieve threat assessment of any incoming target. In this method, the state information features of air targets are extracted as input data, the data set is constructed by using the dispersion maximization method, the target threat degree level is used as the output data, and the target threat evaluation model is constructed by using the K nearest neighbor algorithm. Simulation results show that this method can achieve high accuracy and real time target threat assessment, and compare with TOPSIS method and dispersion maximization method, which proves that this method has higher decision making efficiency for air target anomalous feature values and is more suitable for the high complexity of modern battlefields, which further reflects the superiority and feasibility of this method. |