[1]胡志强,李文静,乔俊飞.带扰动的变频正弦混沌神经网络研究[J].智能系统学报,2018,13(04):493-499.[doi:10.11992/tis.201703003]
 HU Zhiqiang,LI Wenjing,QIAO Junfei.Frequency-conversion sinusoidal chaotic neural network with disturbance feature[J].CAAI Transactions on Intelligent Systems,2018,13(04):493-499.[doi:10.11992/tis.201703003]
点击复制

带扰动的变频正弦混沌神经网络研究(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年04期
页码:
493-499
栏目:
出版日期:
2018-07-05

文章信息/Info

Title:
Frequency-conversion sinusoidal chaotic neural network with disturbance feature
作者:
胡志强12 李文静12 乔俊飞12
1. 北京工业大学 信息学部, 北京 100124;
2. 计算智能与智能系统北京市重点实验室, 北京 100124
Author(s):
HU Zhiqiang12 LI Wenjing12 QIAO Junfei12
1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
2. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China
关键词:
扰动三角函数小波函数混沌神经网络变频正弦组合优化
Keywords:
disturbancetrigonometric functionwavelet functionchaotic neural networkfrequency conversion sinusoidalcombination optimization
分类号:
TP18
DOI:
10.11992/tis.201703003
摘要:
为了研究变频正弦混沌神经网络(FCSCNN)的抗扰动能力,在该混沌神经元的内部状态中分别引入三角函数和小波函数扰动项,提出了带扰动的变频正弦混沌神经元模型。给出了该混沌神经元的倒分岔图及Lyapunov指数的时间演化图,分析了其动力学特性。利用该模型构建了新型暂态混沌神经网络,通过选择不同的扰动系数,将其应用于函数优化和组合优化问题上。仿真实验表明,在适当的扰动系数下,变频正弦混沌神经网络能够有效地解决函数优化和组合优化问题,体现了该模型具有较强的鲁棒性和抗扰动能力。
Abstract:
In this paper, we propose a novel frequency-conversion sinusoidal chaotic neuron model with a disturbance feature to study the anti-disturbance ability of the frequency-conversion sinusoidal chaotic neural network (FCSCNN). To do so, we introduce trigonometric function and wavelet function disturbances into the internal state of the chaotic neuron model. We present a reversed bifurcation diagram of the chaotic neuron and a time evolution diagram of the Lyapunov exponent and then analyze the dynamic properties. We constructed a new transient chaotic neural network (TCNN) using the novel chaotic neuron model. By selecting different disturbance coefficients, we performed network function optimization and combinational optimization. Simulation results show that the FCSCNN can effectively solve function optimization and combinational optimization problems with appropriate disturbance coefficients, which demonstrate the strong robustness and anti-disturbance ability of the model.

参考文献/References:

[1] HOPFIELD J J, TANK D W. "Neural" computation of decisions in optimization problems[J]. Biological cybernetics, 1985, 52(3):141-152.
[2] WANG Jiahai, CAI Yiqiao, YIN Jian. Multi-start stochastic competitive Hopfield neural network for frequency assignment problem in satellite communications[J]. Expert systems with applications, 2011, 38(1):131-145.
[3] CHEN Luonan, AIHARA K. Chaotic simulated annealing by a neural network model with transient chaos[J]. Neural networks, 1997, 8(6):915-930.
[4] ZHANG Jiahai, XU Yaoqun. Wavelet chaotic neural networks and their application to continuous function optimization[J]. Natural science, 2009, 1(3):204-209.
[5] LIU Xiangdong, XIU Chunbo. A novel hysteretic chaotic neural network and its applications[J]. Neurocomputing, 2007, 70(13/14/15):2561-2565.
[6] ZHAO Lin, SUN Ming, CHENG Jianhua, et al. A novel chaotic neural network with the ability to characterize local features and its application[J]. IEEE transactions on neural networks, 2009, 20(4):735-742.
[7] 胡志强, 李文静, 乔俊飞. 变频正弦混沌神经网络及其应用[J]. 物理学报, 2017, 66(9):090502. HU Zhiqiang, LI Wenjing, QIAO Junfei. Frequency conversion sinusoidal chaotic neural network and its application[J]. Acta physica sinica, 2017, 66(9):090502.
[8] HSU C C, GOBOVIC D, ZAGHLOUL M E, et al. Chaotic neuron models and their VLSI circuit implementations[J]. IEEE transactions on neural networks, 1996, 7(6):1339-1350.
[9] SHUAI Jianwei, CHEN Zhenxiang, LIU Riutang, et al. Self-evolution neural model[J]. Physics letters A, 1996, 221(5):311-316.
[10] POTAPOV A, ALI M K. Robust chaos in neural networks[J]. Physics letters A, 2000, 277(6):310-322.
[11] SIH G C, TANG K K. Sustainable reliability of brain rhythms modeled as sinusoidal waves with frequency-amplitude trade-off[J]. Theoretical and applied fracture mechanics, 2012, 61:21-32.
[12] 韩广, 乔俊飞, 韩红桂, 等. 基于Hopfield神经网络的污水处理过程优化控制[J]. 控制与决策, 2014, 29(11):2085-2088. HAN Guang, QIAO Junfei, HAN Honggui, et al. Optimal control for waste-water treatment process based on Hopfield neural network[J]. Control and decision, 2014, 29(11):2085-2088.
[13] CHEN S S. Chaotic simulated annealing by a neural network with a variable delay:design and application[J]. IEEE transactions on neural networks, 2011, 22(10):1557-1565.
[14] GARCÍA L, TALAVÁN P M, YÁÑEZ J. Improving the Hopfield model performance when applied to the traveling salesman problem[J]. Soft computing, 2017, 21(14):3891-3905.

相似文献/References:

[1]许楠,刘桂阳,徐耀群.带有高斯扰动的混沌神经网络及应用[J].智能系统学报,2014,9(04):444.[doi:10.3969/j.issn.1673-4785.201308013]
 XU Nan,LIU Guiyang,XU Yaoqun.A novel chaotic neural network with Gaussian disturbance and its application[J].CAAI Transactions on Intelligent Systems,2014,9(04):444.[doi:10.3969/j.issn.1673-4785.201308013]

备注/Memo

备注/Memo:
收稿日期:2017-03-02。
基金项目:国家自然科学基金重点项目(61533002);国家杰出青年科学基金项目(61225016);国家自然科学基金青年科学基金项目(61603009);中国博士后科学基金项目(2015M570910);朝阳区博士后研究基金项目(2015ZZ-6);北京工业大学基础研究基金项目(002000514315501).
作者简介:胡志强,男,1988年生,博士研究生,主要研究方向为混沌动力学、混沌神经网络、污水处理建模与仿真、智能优化算法。发表学术论文6篇,其中被SCI收录2篇,EI收录2篇;李文静,女,1985年生,讲师,博士。主要研究方向为神经计算、人工神经网络、模式识别。申请美国发明专利1项。作为项目负责人先后获得国家自然科学基金青年项目、中国博士后第57批面上资助、北京市博士后科研活动经费资助。近五年来,发表学术论文10余篇,其中SCI收录8篇;乔俊飞,男,1968年生,教授,博士生导师。教育部长江学者特聘教授,国家杰出青年基金获得者,国家级百千万人才工程入选者,教育部新世纪优秀人才,享受国务院特殊津贴专家。中国人工智能学会科普工作委员会主任,中国自动化学会理事,主要研究方向为智能信息处理、智能控制理论与应用。获教育部科技进步奖一等奖和北京市科学技术奖三等奖各1项。获得发明专利20余项。发表学术论文100余篇,其中被SCI收录20余篇,EI收录60余篇。
通讯作者:胡志强.E-mail:zacharyhu33@163.com.
更新日期/Last Update: 2018-08-25