基于仿生算法优化的镜像极限学习机的应用

doi:10.13438/j.cnki.jdzk.2022.06.004

吉首大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (6): 14-19.DOI: 10.13438/j.cnki.jdzk.2022.06.004

基于仿生算法优化的镜像极限学习机的应用

印煜民，廖柏林

(吉首大学计算机科学与工程学院,湖南吉首 416000)

出版日期:2022-11-25 发布日期:2023-01-10
通讯作者: 廖柏林(1981—)，男，湖南常宁人，吉首大学计算机科学与工程学院教授，博士，主要从事人工智能和神经网络研究.
作者简介:印煜民（1993—），男，湖南张家界人，吉首大学计算机科学与工程学院助理实验师，硕士,主要从事人工智能和神经网络研究
基金资助:
国家自然科学基金资助项目（62066015）；湖南省教育厅科学研究项目（20A396）；吉首大学校级理工科研究项目（JD20004）

Application of Mirror ELM Based on Bio-Inspired Algorithm Optimization

YIN Yumin,LIAO Bolin

(College of Computer Science and Engineering,Jishou University,Jishou 416000,Hunan China)

Online:2022-11-25 Published:2023-01-10

摘要/Abstract

摘要：提出了一种改进的极限学习机（ELM）的权值确定方法，该方法的权值确定过程与传统的ELM权值确定过程互为镜像，因此称其为镜像ELM（MELM）.结合一种新的仿生算法天牛须搜索算法（BAS）来优化神经网络的权值选取，并将其应用于模式分类实验.实验结果表明，与其他神经网络模型相比，BAS-MELM在模式分类方面具有更简单的神经网络结构和更好的泛化性能.

关键词： 极限学习机, 仿生算法, 优化算法, 模式分类, 镜像, 天牛须搜索算法

Abstract: This study proposes a method to determine the weights of an improved ELM.The weight determination process of this method and the traditional ELM weight determination process mirror each other,so it is termed Mirror ELM (MELM).At the same time,a novel bio-inspired algorithm named Beetle Antennae Search (BAS) is used to optimize the selection of neural network weights and is applied in pattern classification.Experimental results show that the proposed BAS-MELM has more simple neural network structure and superior generalization performance in terms of pattern classification.

Key words: extreme learning machine, bio-inspired algorithm, optimization solution, pattern classification, mirror, beetle antennae search algorithm

印煜民, 廖柏林. 基于仿生算法优化的镜像极限学习机的应用[J]. 吉首大学学报（自然科学版）, 2022, 43(6): 14-19.

YIN Yumin, LIAO Bolin. Application of Mirror ELM Based on Bio-Inspired Algorithm Optimization[J]. Journal of Jishou University(Natural Sciences Edition), 2022, 43(6): 14-19.

参考文献

[1] YE Yunfei,WANG Ping,WU Ning,et al.Optimisation for Accuracy Improving of MSB Signal Detection[J].Electronics Letters,2017,53(24):1578-1580.
[2] HUANG Guangbin,ZHU Qinyu,SIEW C KHEONG.Extreme Learning Machine:Theory and Applications[J].Neurocomputing,2006,70(1/2/3):489-501.
[3] FENG Guorui,HUANG Guangbin,LIN Qingping,et al.Error Minimized Extreme Learning Machine with Growth of Hidden Nodes and Incremental Learning[J].IEEE Transactions on Neural Networks,2009,20(8):1352-1357.
[4] ZHANG Yunong,YIN Yonghua,GUO Dongsheng,et al.Cross-Validation Based Weights and Structure Determination of Chebyshev-Polynomial Neural Networks for Pattern Classification[J].Pattern Recognition,2014,47(10):3414-3428.
[5] SARAS SARASWATHI,SURESH SUNDARAM,NARASIHAN SUNDARARAJAN,et al.ICGA-PSO-ELM Approach for Accurate Multiclass Cancer Classification resulting in Reduced Gene Sets in Which Genes Encoding Secreted Proteins are Highly Represented[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2010,8(2):452-463.
[6] YANG Hongming,YI Jun,ZHAO Junhua,et al.Extreme Learning Machine Based Genetic Algorithm and Its Application in Power System Economic Dispatch[J].Neurocomputing,2013,102:154-162.
[7] JIN Bo,JING Zhongliang,ZHAO Haitao.Incremental and Decremental Extreme Learning Machine Based on Generalized inverse[J].IEEE Access,2017,5:20852-20865.
[8] HUANG Fang,LU Jun,TAO Jian,et al.Research on Optimization Methods of ELM Classification Algorithm for Hyperspectral Remote Sensing Images[J].IEEE Access,2019,7:108070-108089.
[9] ZHANG Sen,LIU Zheng,HUANG Xuejiao,et al.A Modified Residual Extreme Learning Machine Algorithm and Its Application[J].IEEE Access,2018,6:62215-62223.
[10] CHEN Liangming,HUANG Zhigua,LI Yuhe,et al.Weight and Structure Determination Neural Network Aided with Double Pseudoinversion for Diagnosis of Flat Foot[J].IEEE Access,2019,7:33001-33008.
[11] ZHANG Weibin,JI Hongbing.Fuzzy Extreme Learning Machine for Classification[J].Electronics Letters,2013,49(7):448-450.
[12] XU Yan,WANG Quanwei,WEI Zhenyu,et al.Traffic Sign Recognition Based on Weighted ELM and AdaBoost[J].Electronics Letters,2016,52(24):1988-1990.
[13] LI Hongwei,HUANG Zhiguan,FU Jinshan,et al.Modified Weights-and-Structure-Determination Neural Network for Pattern Classification of Flatfoot[J].IEEE Access,2019,7:63146-63154.
[14] JIN Long,HUANG Zhiguan,LI Yuhe,et al.On Modified Multi-Output Chebyshev-Polynomial Feed-Forward Neural Network for Pattern Classification of Wine Regions[J].IEEE Access,2018,7:1973-1980.
[15] WEN Hui,FAN Hongguang,XIE Weixin,et al.Hybrid Structure-Adaptive RBF-ELM Network Classifier[J].IEEE Access,2017,5:16539-16554.
[16] JIANG Xiangyuan,LI Shuai.BAS:Beetle Antennae Search Algorithm for Optimization Problems[EB/OL].(2018-09-22)[2022-03-14] .http:∥www.doc88.com/p-8002524552909.html.
[17] ZHANG Yunong,YIN Yonghua,GUO Dongsheng,et al.Cross-Validation Based Weights and Structure Determination of Chebyshev-Polynomial Neural Networks for Pattern Classification[J].Pattern Recognition,2014,47(10):3414-3428.
[18] PAVEL B BRAZDIL,CARLOS SOARES.A Comparison of Ranking Methods for Classification Algorithm Selection[C]∥LPEZ DE MNTARAS R,PLAZA ENRIC.Machine Learning:ECML 2000.Berlin,Heidelberg:Springer,2000:63-75.

基于仿生算法优化的镜像极限学习机的应用

Application of Mirror ELM Based on Bio-Inspired Algorithm Optimization

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	李苗. 基于IPv6的通信网络多信道协作路由跨层控制系统[J]. 吉首大学学报（自然科学版）, 2023, 44(5): 35-41.
[2]	于存威, 莫礼平, 万润泽. 基于莱维飞行和布朗运动的鲸鱼优化算法[J]. 吉首大学学报（自然科学版）, 2023, 44(2): 24-32.
[3]	龙求青, 廖柏林, 印煜民. 基于去噪自编码器的镜像极限学习机设计[J]. 吉首大学学报（自然科学版）, 2020, 41(5): 19-25.
[4]	蒋一锄. 基于灰狼优化聚类算法的读者行为分析[J]. 吉首大学学报（自然科学版）, 2020, 41(4): 38-43.
[5]	王琳. 基于PPSO算法的电力系统无功优化[J]. 吉首大学学报（自然科学版）, 2020, 41(4): 33-37.
[6]	余大为，周海鹏，孙敏，李旸，张恩宝，李倩倩. 基于正态云模型的自适应量子粒子群优化算法[J]. 吉首大学学报（自然科学版）, 2019, 40(6): 29-39.
[7]	印煜民,李帅,马川，廖柏林. 一种新型仿生算法在优化问题中的应用[J]. 吉首大学学报（自然科学版）, 2018, 39(6): 26-29.
[8]	王国军, 曹建农, 陈振冲. 一种新型的多OROLAP模型及其优化算法[J]. journal6, 2004, 25(3): 29-35.