半监督聚类目标下粒子群算法的分析与改进

doi:10.13190/j.jbupt.2020-017

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (5): 21-26.doi: 10.13190/j.jbupt.2020-017

半监督聚类目标下粒子群算法的分析与改进

孙艺¹, 夏启钊²

1. 北京邮电大学计算机学院(国家示范性软件学院), 北京 100876;
2. 北京邮电大学国际学院, 北京 100876

收稿日期:2020-02-16 发布日期:2021-03-11
作者简介:孙艺(1979-),男,高级工程师,E-mail:sunyisse@bupt.edu.cn.
基金资助:
河北省重点研发计划项目（20313701D）；河北省重点研发计划项目（19210404D）；国家自然科学基金项目（U1536112）；国家社会科学基金重点项目（17AJL014）

Analysis and Improvement of Semi-Supervised K-means Clustering Based on Particle Swarm Optimization Algorithm

SUN Yi¹, XIA Qi-zhao²

1. School of Computer Science(National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. International School, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-02-16 Published:2021-03-11

摘要/Abstract

摘要： 传统粒子群算法的优点较为明显，但是随着环境复杂度的增高，传统算法的聚类中心敏感度升高，空聚类过多，类标号对聚类结果的影响不足等问题日趋严重.为此，提出了一种改进算法，以半监督K均值聚类为目标，以自适应K值的方式，随机地计算初始化聚类中心，并根据均值聚类算法的需要编码成粒子，同时引入软性约束概念重新构造目标函数；最后使用改进后的算法进行寻优.所提出的粒子群算法改进了自适应参数，引入了免疫扰动和混沌扰动2种扰动方式，同时应用了退火策略和动态聚类策略.实验结果表明，该算法在很大程度上解决了上述问题.

关键词: 半监督, K均值, 信息熵, 扰动, 退火策略

Abstract: Traditional particle swarm optimization has obvious advantages, but with increased complexity of the environment. When the traditional algorithm is used, the sensitivity of the clustering center is increased, there are too many empty clusters, and the performance of the class label has insufficient influence on the clustering results. An improved algorithm is proposed, which aims at semi-supervised K-means clustering; first, the clustering center is initialized by random calculation in an adaptive K-value method, and the particles are encoded according to the needs of the mean clustering algorithm. At the same time, the objective function is reconstructed with the concept of soft constraints, and finally the improved algorithm is used for optimization. The adaptive parameters in the improved particle swarm optimization algorithm is improved, two disturbance methods of immune disturbance and chaos disturbance is introduced, and the annealing strategy and dynamic clustering strategy at the same time is applied. Experiments show that the algorithm has solved the above problem.

Key words: semi-supervised, K-means clustering, information entropy, perturbation, annealing strategy

中图分类号:

TP301.6

孙艺, 夏启钊. 半监督聚类目标下粒子群算法的分析与改进[J]. 北京邮电大学学报, 2020, 43(5): 21-26.

SUN Yi, XIA Qi-zhao. Analysis and Improvement of Semi-Supervised K-means Clustering Based on Particle Swarm Optimization Algorithm[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 21-26.

参考文献

[1] Han Jiawei, Kamber Micheline. Data mining:concepts and techniques[J]. Data Mining Concepts Models Methods & Algorithms Second Edition, 2006, 5(4):1-18.
[2] 刘佳鸣, 况立群, 尹洪红, 等. 灰狼优化的K均值聚类算法[J]. 中国科技论文, 2019, 14(7):778-782, 807. Liu Jiaming, Kuang Liqun, Yin Honghong, et al. K-means clustering algorithm based on grey wolf optimization[J]. China Sciencepaper, 2019, 14(7):778-782, 807.
[3] 马俊宏, 武丽芬. 一种改进的加速K均值聚类算法[J]. 太赫兹科学与电子信息学报, 2019, 17(5):885-891, 897. Ma Junhong, Wu Lifen. An improved accelerated K-means clustering algorithm[J]. Journal of Terahertz Science and Electronic Information Technology, 2019, 17(5):885-891, 897.
[4] Fu Mandi, Jian Yiheng, Yu Xiao, et al. Cross-company defect prediction via semi-supervised clustering-based data filtering and MSTrA-based transfer learning[J]. Soft Computing:A Fusion of Foundations, Methodologies and Applications, 2018, 22(10):3461-3472.
[5] Yu Zhiwen, Luo Peinan, Liu Jiming, et al. Semi-supervised ensemble clustering based on selected constraint projection[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(12):2394-2407.
[6] Yu Zhiwen, Chen Hongsheng, You Jane, et al. Double selection based semi-supervised clustering ensemble for tumor clustering from gene expression profiles[J]. Computational Biology & Bioinformatics IEEE/ACM Transactions on, 2014, 11(4):727-740.
[7] 李文锋, 梁晓磊, 张煜, 等. 具有异构分簇的粒子群优化算法研究[J]. 电子学报, 2012, 40(11):2194-2199. Li Wenfeng, Liang Xiaolei, Zhang Yu, et al. Research on PSO with clusters and heterogeneity[J]. Acta Electronica Sinica, 2012, 40(11):2194-2199.
[8] Doctor S, Venayagamoorthy G K, Gudise V G. Optimal PSO for collective robotic search applications[C]//Congress on Evolutionary Computation. Portland:IEEE, 2004.
[9] Sierra M R, Coello Coello C A. Improving PSO-based multi-objective optimization using crowding, mutation and E-Dominance[J]. Lecture Notes in Computer Science, 2005, 3410:505-519.
[10] Liu Bo, Wang Ling, Jin Yihui, et al. Improved particle swarm optimization combined with chaos[J]. Chaos, Solitons and Fractals, 2005, 25(5):1261-1271.

半监督聚类目标下粒子群算法的分析与改进

Analysis and Improvement of Semi-Supervised K-means Clustering Based on Particle Swarm Optimization Algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	谢攀, 彭才静, 何志慧, 张远. 一种融合分组卷积和半监督的睡眠分期方法[J]. 北京邮电大学学报, 2022, 45(4): 7-12.
[2]	田智予, 刘晓平, 王刚, 赵云龙, 黎星华. 考虑万向轮扭转角扰动轮式移动机器人轨迹跟踪[J]. 北京邮电大学学报, 2022, 45(1): 94-101.
[3]	霍纬纲, 王星, 梁锐. 融合互信息估计和对抗自编码器的异常检测[J]. 北京邮电大学学报, 2021, 44(5): 28-34.
[4]	曹志义, 牛少彰, 张继威. 基于生成对抗网络的遮挡图像修复算法[J]. 北京邮电大学学报, 2018, 41(3): 81-86.
[5]	晁浩, 鲁保云, 刘永利, 刘志中, 宋成. 基于谱信息熵和互补模型的声效模式检测[J]. 北京邮电大学学报, 2018, 41(2): 56-61.
[6]	赵健, 张婉如, 张顺利, 雷敏, 徐文胜, 范帅帅. 一种新的结合SVD的非下采样Shearlet数字水印[J]. 北京邮电大学学报, 2017, 40(s1): 34-38.
[7]	李忠涛, 赵帅, 郎立萌, 史俊, 万波. 论内容可寻址网络中节点扰动引起的结构变化[J]. 北京邮电大学学报, 2016, 39(s1): 67-71.
[8]	刘珍, 王若愚, 刘琼. 基于Bootstrapping的因特网流量分类方法[J]. 北京邮电大学学报, 2014, 37(5): 66-70,79.
[9]	张韬政,王小捷,仝辉. 交互结构最优化算法中辅助问题的相关性[J]. 北京邮电大学学报, 2011, 34(4): 14-18.