[1]王静红,等.混合模型下的雅可比矩阵退火算法优化[J].深圳大学学报理工版,2021,38(2):188-193.[doi:10.3724/SP.J.1249.2021.02188]
 WANG Jinghong,FENG Chan,et al.Optimization of Jacobian matrix annealing algorithm based on hybrid model[J].Journal of Shenzhen University Science and Engineering,2021,38(2):188-193.[doi:10.3724/SP.J.1249.2021.02188]
点击复制

混合模型下的雅可比矩阵退火算法优化()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第38卷
期数:
2021年第2期
页码:
188-193
栏目:
电子与信息科学
出版日期:
2021-03-12

文章信息/Info

Title:
Optimization of Jacobian matrix annealing algorithm based on hybrid model
文章编号:
202102011
作者:
王静红1 2冯婵3柴变芳4
1) 河北师范大学计算机与网络空间安全学院, 人工智能研究中心, 河北石家庄 050024
2)伊利诺伊大学香槟分校信息科学学院,厄巴纳-香槟市 61801,美国
3)河北工程技术学院人工智能与大数据学院,河北石家庄 050091;4)河北地质大学信息工程学院,河北石家庄 050031
Author(s):
WANG Jinghong1 2 FENG Chan3 and CHAI Bianfang4
1) Artificial Intelligence Research Center, College of Computer and cyber Sceurity, Hebei Normal University, Shijiazhuang 050024, Hebei Province, P.R.China
2) School of Information Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
3) College of Artificial Intelligence Big Data, Hebei Institute of Engineering Technology, Shijiazhuang 050091, Hebei Province, P.R.China
4) College of Information Engineering, Hebei GEO University, Shijiazhuang 050031, Hebei Province, P.R.China
关键词:
人工智能理论复杂网络混合模型退火算法收敛速度雅可比矩阵半监督学习
Keywords:
artificial intelligence theory complex network hybrid model annealing algorithm convergence rate Jacobian matrix semi-supervised learning
分类号:
TP181
DOI:
10.3724/SP.J.1249.2021.02188
文献标志码:
A
摘要:
退火算法可有效发现网络结构的聚类分布情况,但在不同的网络中算法处理结果的准确性有待提高.为更精确地识别混合模型网络结构中的数据分布,解决混合模型易陷入局部最大值和收敛等问题,提出混合模型下雅可比矩阵退火算法.首先利用逆温度参数β对模型进行初始化,然后迭代执行计算期望步骤和最大化步骤2个任务;采用雅可比矩阵计算模型的后验概率,直至算法达到设定的准确性或收敛.将建立的雅可比矩阵退火算法与半监督高斯混合模型下的逆模拟退火聚类算法在真实网络上进行对比分析,实验结果表明,基于雅可比矩阵的算法在混合网络模型中的准确性更优.该算法不仅能防止陷入局部最优,而且能提高分析网络聚类分布的准确性.
Abstract:
The annealing algorithm can effectively find the clustering distribution of network structure, but the algorithm accuracy of handling different networks needs to be further improved. In order to identify the data distribution in network structure of mixed model more accurately and solve the problems of local maximum value and convergence of mixed model, the Jacobian matrix annealing algorithm is studied. First, the model is initialized by using the inverse temperature parameter, and then the two tasks of expectation step and maximization step are performed iteratively. The posterior probability of model is calculated based on the Jacobian matrix until the algorithm reaches the set accuracy or meets the convergence condition. The Jacobian matrix annealing algorithm is compared with the inverse simulated annealing clustering algorithm under semi-supervised Gaussian mixture model on the real network, and the experimental results show that the accuracy of Jacobian matrix algorithm in the hybrid network model is better. The proposed algorithm can not only prevent the network from falling into the local optimum, but also improve the accuracy of analyzing network clustering distribution.

参考文献/References:

[1] YIN Nan. A big data analysis method based on modified collaborative filtering recommendation algorithms[J]. Open Physics, 2019, 17(1):966-974.
[2] LIAO C H, CHEN M Y. Building social computing system in big data: from the perspective of social network analysis[J]. Computers in Human Behavior, 2019, 101: 457-465.
[3] FORTUNATO S. Community detection in graphs[J]. Physics Reports, 2010, 486(3/4/5): 75-174.
[4] 赵学华,杨博,陈贺昌.一种高效的随机块模型学习算法[J].软件学报,2016,27(9):2248-2264.
ZHAO Xuehua, YANG Bo, CHEN Hechang. Fast learning algorithm for stochastic block model[J]. Journal of Software, 2016, 27(9): 2248-2264.(in Chinese).
[5] LATOUCHE P, BIRMELE E, AMBROISE C. Variational Bayesian inference and complexity control for stochastic block models[J]. Statistical Modelling, 2012, 12(1): 93-115.
[6] YANG Bo, HE He, HU Xiaoming. Detecting community structure in networks via consensus dynamics and spatial[J]. Physica A: Statistical Mechanics and Its Applications, 2017, 483(1): 156-170.
[7] 王垚,柴变芳,李文斌,等.一种基于逆模拟退火和高斯混合模型的半监督聚类算法[J].南京师大学报自然科学版,2017,40(3):67-73.
WANG Yao, CHAI Bianfang, LI Wenbin, et al. A semi-supervised clustering algorithm based on anti-annealing and Gaussian mixture model[J]. Journal of Nanjing Normal University Natural Science Edition, 2017, 40(3): 67-73.(in Chinese).
[8] NAIM I,GILDEA D. Convergence of the EM algorithm for Gaussian mixtures with unbalanced mixing coefficients[C]// Proceedings of the 29th International Conferences on Machine Learning. Edinburgh,UK: Omnipress,2012:1427-1431.
[9] KANG S B, PARK J W, Lee I. Accuracy improvement of the most probable point-based dimension reduction method using the hessian matrix[J]. International Journal for Numerical Methods in Engineering, 2017, 111(3):203-217.
[10] RUTKEVICH S B, KURASOV P. A formula for eigenvalues of Jacobi matrices with a reflection symmetry[J]. Advances in Mathematical Physics, 2018, 2018: 9784091.
[11] XIONG Hui, SHANG Pengjian. Weighted multifractal cross-correlation analysis based on Shannon entropy[J]. Communications in Nonlinear Science and Numerical Simulation, 2016, 30(1/2/3): 268-283.
[12] CHAOMURILIGE, YU Jian, YANG M S. Analysis of parameter selection for Gustafson-Kessel fuzzy clustering using Jacobian matrix[J]. IEEE Transactions on Fuzzy Systems, 2015, 23(6): 2329-2342.
[13] OLVER P J. Lecture notes on numerical analysis[EB/OL].(2008-05-18)[2021-01-05].http://fourier.eng.hmc.edu/e176/lectures/peter/lno.pdf.
[14] NAIM I, GILDEA D. EM algorithm for Gaussian mixtures with unbalanced mixing coefficient[C]// Proceedings of the 29th International Conference on Machine Learning. Edinburgh, UK: ACM Press, 2012: 1427-1431.

相似文献/References:

[1]吴雪飞,徐晨.基于牵制控制的一类线性耦合复杂网络同步[J].深圳大学学报理工版,2011,28(No.5(377-470)):460.
 WU Xue-fei and XU Chen.The synchronization of a dynamic complex network with linear coupling[J].Journal of Shenzhen University Science and Engineering,2011,28(2):460.
[2]吴维扬,丰建文,赵毅.基于随机牵制控制的复杂网络均方簇同步[J].深圳大学学报理工版,2015,32(5):538.[doi:10.3724/SP.J.1249.2015.05538]
 Wu Weiyang,Feng Jianwen,and Zhao Yi.Mean square cluster synchronization of complex networks via random pinning control[J].Journal of Shenzhen University Science and Engineering,2015,32(2):538.[doi:10.3724/SP.J.1249.2015.05538]
[3]毛北行,王战伟.一类分数阶复杂网络系统的有限时间同步控制[J].深圳大学学报理工版,2016,33(1):96.[doi:10.3724/SP.J.1249.2016.01096]
 Mao Beixing and Wang Zhanwei.Finite-time synchronization control of a class of fractional-order complex network systems[J].Journal of Shenzhen University Science and Engineering,2016,33(2):96.[doi:10.3724/SP.J.1249.2016.01096]
[4]李娜,丰建文,赵毅.具有马氏跳拓扑复杂网络的有限时间同步[J].深圳大学学报理工版,2016,33(4):359.[doi:10.3724/SP.J.1249.2016.04359]
 Li Na,Feng Jianwen,and Zhao Yi.Finite-time synchronization of Markovian jump complex networks[J].Journal of Shenzhen University Science and Engineering,2016,33(2):359.[doi:10.3724/SP.J.1249.2016.04359]
[5]潘静静,王晓峰.复杂网络视角下的港口连通性建模及应用[J].深圳大学学报理工版,2017,34(5):544.[doi:10.3724/SP.J.1249.2017.05544]
 Pan Jingjing,and Wang Xiaofeng.Port connectivity model based on complex network and its application[J].Journal of Shenzhen University Science and Engineering,2017,34(2):544.[doi:10.3724/SP.J.1249.2017.05544]

备注/Memo

备注/Memo:
Received:2019-09-18;Accepted:2019-11-11
Foundation:National Science and Technology Major Project of China (2016ZX05046-004); Natural Science Foundation of Hebei Province(F2019205303); Science and Technology Project of Education Department of Hebei Province (ZD2018023)
Corresponding author:Professor WANG Jinghong. E-mail: wangjinghong6301@163.com
Citation:WANG Jinghong, FENG Chan, CHAI Bianfang. Optimization of Jacobian matrix annealing algorithm based on hybrid model[J]. Journal of Shenzhen University Science and Engineering, 2021, 38(2): 188-193.(in Chinese)
基金项目:国家科技重大专项资助项目(2016ZX05046-004);河北省自然科学基金项目资助项目(F2019205303);河北省教育厅科学技术研究资助项目(ZD2018023)
作者简介:王静红(1967—),河北师范大学教授.研究方向:机器学习与数据挖掘、复杂网络.
E-mail:wangjinghong6301@163.com
引文:王静红,冯婵,柴变芳.混合模型下的雅可比矩阵退火算法优化[J]. 深圳大学学报理工版,2021,38(2):188-193.
更新日期/Last Update: 2021-03-30