Computer Engineering and Applications ›› 2018, Vol. 54 ›› Issue (7): 226-231.DOI: 10.3778/j.issn.1002-8331.1611-0045

Previous Articles     Next Articles

Target threat assessment using Elman neural network optimized by adaptive krill herd algorithm

LI Zhipeng, LI Weizhong, DU Ruichao   

  1. Air and Missile Defense College of Air Force Engineering University, Xi’an 710051, China
  • Online:2018-04-01 Published:2018-04-16



  1. 空军工程大学 防空反导学院,西安 710051

Abstract: Adaptive krill herd algorithm is proposed on the basis of the basic krill herd algorithm, by establishing genetic breeding mechanism and adding an adaptive link which is made of genetic and optimization operators. This new algorithm not only improves the global optimization performance, but also obtains robust result with good quality. The method employing adaptive evolutionary krill herd algorithm to simultaneously optimize the initial weights and thresholds of the Elman neural network is presented. And on the basis of it, a target threat assessment model is established to seek global excellent result. Through simulation and analysis of experimental data, the feasibility and efficiency of the algorithm in the application of target threat assessment are verified.

Key words: adaptive krill herd algorithm, genetic breeding mechanism, Elman neural network, target threat assessment, threat value

摘要: 提出一种自适应磷虾群算法,在基本磷虾群算法中引入遗传繁殖机制,并加入进化算子和优化算子构成自适应环节,提高了算法的全局搜索能力和预测精度;通过自适应磷虾群算法对Elman神经网络的初始权值和阈值进行寻优,并在此基础上建立目标威胁评估模型。仿真实验表明,自适应磷虾群优化Elman神经网络既保证了一定的收敛速度,又能够使寻优精度得到明显提升,其对测试集的预测结果优于传统Elman神经网络和基本磷虾群优化Elman神经网络,从而验证了算法模型在目标威胁评估中的可行性、有效性。

关键词: 自适应磷虾群算法, 遗传繁殖机制, Elman神经网络, 目标威胁评估, 威胁值