一种基于麻雀搜索算法的空中目标意图预测方法

An Air Target Intention Prediction Method Based on Sparrow Search Algorithm

针对BP神经网络(BPNN)的分类性能和遗传算法(GA)的参数寻优能力难以满足空中目标意图预测需求的问题,提出了一种基于麻雀搜索算法(SSA)优化支持向量机(SVM)的空中目标意图预测方法。利用SVM和SSA分别取代BPNN和GA,构建了SSA-SVM空中目标意图预测模型,并对模型的预测性能进行了仿真检验。结果表明,SSA-SVM比GA-SVM具有更快的收敛速度和更高的适应度值,比BPNN具有更高的预测准确性和更稳定的预测结果。因此,SSA-SVM可以准确、稳定地预测空中目标意图,能够满足意图预测在准确性和稳定性上的需求,提升了预测性能。

Aiming at the problem that the classification performance of BP neural network(BPNN)and parameter optimization capability of genetic algorithm(GA)cannot meet the requirements of air target intention prediction.An air target intention prediction method based on support vector machine(SVM)optimized by sparrow search algorithm(SSA)is proposed,SVM and SSA are used to replace BPNN and GA respectively.Then,the air target intention prediction model based on SSA-SVM is established,the prediction performance of the model is verified by simulation experiments.The results show that compared with GA-SVM,SSA-SVM has a faster convergence speed and a higher fitness value.Compared with BPNN,SSA-SVM has the higher prediction accuracy and the more stable prediction results.Therefore,SSA-SVM could predict air target intention accurately and stably and can meet the requirements for intention prediction in accuracy and stability,the prediction performance is improved.