首页 | 本学科首页   官方微博 | 高级检索  
     

基于萤火虫算法优化BP神经网络的目标威胁估计
引用本文:王改革,郭立红,段红,刘逻,王鹤淇. 基于萤火虫算法优化BP神经网络的目标威胁估计[J]. 吉林大学学报(工学版), 2013, 43(4): 1064-1069
作者姓名:王改革  郭立红  段红  刘逻  王鹤淇
作者单位:1. 中国科学院长春光学精密机械与物理研究所,长春130033;中国科学院研究生大学,北京100039
2. 中国科学院长春光学精密机械与物理研究所,长春,130033
3. 东北师范大学计算机科学与信息技术学院,长春,130117
基金项目:中国科学院知识创新项目
摘    要:在萤火虫优化算法和BP神经网络的基础上,建立了萤火虫算法优化BP神经网络的目标威胁估计模型,并提出了基于该模型的算法。该模型和算法采用萤火虫算法优化BP神经网络的初始权值和阈值,优化后的BP神经网络能对测试集进行更好的预测。实验结果表明,萤火虫算法优化BP神经网络的预测误差明显小于BP和PSO_SVM。该模型和算法具有很好的预测能力,可以快速、准确地完成目标威胁估计。

关 键 词:计算机应用  BP神经网络  目标威胁估计  萤火虫算法

Target threat assessment using glowworm swarm optimization and BP neural network
WANG Gai-ge,GUO Li-hong,DUAN Hong,LIU Luo,WANG He-qi. Target threat assessment using glowworm swarm optimization and BP neural network[J]. Journal of Jilin University:Eng and Technol Ed, 2013, 43(4): 1064-1069
Authors:WANG Gai-ge  GUO Li-hong  DUAN Hong  LIU Luo  WANG He-qi
Affiliation:1(1.Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;2.Graduate University of Chinese Academy of Sciences,Beijing 100039,China;3.School of Computer Science and Information Technology,Northeast Normal University,Changchun 130117,China)
Abstract:Based on the introduction of Glowworm Swarm Optimization(GSO) and Back-Propagation(BP) neural network,a target threat assessment model is proposed and its algorithm is developed.This model is based on GSO optimized BP network(GSOBP).In GSOBP,GSO is employed to simultaneously optimize the initial weights and thresholds of the BP neural network.Target threat database is adopted to test the performance of GSOBP in target threat prediction.The performance of GSOBP is compared with that of normal BP neural network and Particle Swarm Optimization and Support Vector Machines(PSO_SVM).Experiment results show that target threat prediction accuracy by GSOBP is higher than that by normal BP or by PSO_SVM.
Keywords:computer application  back propagation neural network  target threat assessment  glowworm swarm optimization
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号