基于反时限混沌郊狼优化算法的BP神经网络参数优化
作者:
作者单位:

1.辽宁工程技术大学;2.成都数联铭品科技有限公司

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

基于时空序列反演的露天矿物料流量流向动态优化研究;基于大数据的煤与瓦斯突出的预测方法与应用研究;露天煤矿顺倾软岩边坡失稳时空演化机制与稳定性计算方法


Parameter optimization of BP neural network based on coyote optimization algorithm with inverse time chaotic
Author:
Affiliation:

1.Liaoning Technical University;2.BusinessBigData TECH. CO., LTD

Fund Project:

Study on dynamic optimization of material flow direction of open-pit mine based on spatiotemporal sequence inversion ;Prediction method and application research of coal and gas outburst based on big data;Spatial-temporal evolution mechanism and stability calculation method of downdip soft rock slope in opencast coal mine

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对郊狼优化(Coyote Optimization Algorithm,COA)算法优化性能弱及多样性低等问题,提出了一种基于反时限衰减算子的混沌郊狼优化算法(COA with Inverse time chaotic,ICCOA).首先,在个体迭代更新过程中加入反时限衰减权重因子,使得全局搜索与局部开发能力保持平衡的同时提高算法的搜索速度;其次,加入基于Tent混沌映射的混沌干扰机制,将种群中部分较差个体经过映射产生新个体,进而增大种群多样性.为了验证ICCOA 算法的优化能力,分别在10、30和 100 维度下进行函数优化测试,并与5种优化算法进行比较,其实验结果表明 ICCOA 算法具有良好的优化性能.最后,将ICCOA算法应用于BP神经网络参数优化,提出新的神经网络模型(BP neural network with ICCOA,简称ICCOABP),并与标准神经网络、基于遗传算法的BP神经网络参数优化方法一同应用于机器学习的分类任务,进行性能比较,实验结果表明ICCOABP算法具有高效性.

    Abstract:

    A chaotic coyote optimization algorithm based on inverse time-decay operator(ICCOA) is proposed to solve the coyote optimization algorithm(COA),such as the poor performance and low diversity. Firstly, the inverse time decay weight factor is added in the process of individual iterative updating, so as to maintain the balance between global search and local development ability and improve the search speed of the algorithm. Secondly, add the chaotic interference mechanism based on Tent chaotic map,some poor individuals in the population were mapped to produce new individuals, thus increasing the diversity of the population. In order to verify the optimization ability of ICCOA algorithm, functional optimization tests were carried out in 10, 30 and 100 dimensions respectively, and compared with five optimization algorithms. The experimental results show that ICCOA algorithm has good optimization performance.Finally, the ICCOA algorithm is applied to the parameter optimization of BP neural network, and a new neural network model (ICCOABP) is proposed. Compared with the standard neural network and the BP neural network parameter optimization method based on genetic algorithm, the experimental results show that the ICCOABP algorithm is efficient.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-04-11
  • 最后修改日期:2020-06-03
  • 录用日期:2020-06-12
  • 在线发布日期:
  • 出版日期: