Application of a soft competition learning method in document clustering

doi:10.19682/j.cnki.1005-8885.2018.0012

中国邮电高校学报(英文版) ›› 2018, Vol. 25 ›› Issue (3): 80-91.doi: 10.19682/j.cnki.1005-8885.2018.0012

Application of a soft competition learning method in document clustering

朱烨行,张明杰

西安邮电大学

收稿日期:2017-08-08 修回日期:2018-01-16 出版日期:2018-06-29 发布日期:2018-06-30
通讯作者: 朱烨行 E-mail:zhuyehang@126.com
基金资助:
陕西省自然科学基础研究计划项目;教育部人文社会科学研究青年基金项目

Application of a soft competition learning method in document clustering

yehang zhu ²

Received:2017-08-08 Revised:2018-01-16 Online:2018-06-29 Published:2018-06-30
Contact: yehang zhu E-mail:zhuyehang@126.com
Supported by:
The Project of Natural Science Foundation research project of Shaanxi Province of China;The humanities and social sciences research youth fund project of Ministry of Education of China

摘要/Abstract

摘要： Hard competition learning has the feature that each point modifies only one cluster centroid that wins. Correspondingly, soft competition learning has the feature that each point modifies not only the cluster centroid that wins, but also many other cluster centroids near this point. A soft competition learning method is proposed. Centroid all rank distance(CARD), CARDx, and Centroid all rank distance batch K-means(CARDBK) are three clustering algorithms that adopt the soft competition learning method proposed by us. Among them the extent to which one point affects a cluster centroid depends on the distances from this point to the other nearer cluster centroids, rather than just the rank number of the distance from this point to this cluster centroid among the distances from this point to all cluster centroids. In addition, the validation experiments are carried out in order to compare the three soft competition learning algorithms CARD, CARDx, and CARDBK with several hard competition learning algorithms as well as neural gas(NG) algorithm on five data sets from different sources. Judging from the values of five performance indexes in the clustering results, this kind of soft competition learning method has better clustering effect and efficiency, and has linear scalability.

关键词: clustering methods, text processing, document handling, competition learning method

Abstract: Hard competition learning has the feature that each point modifies only one cluster centroid that wins. Correspondingly, soft competition learning has the feature that each point modifies not only the cluster centroid that wins, but also many other cluster centroids near this point. A soft competition learning method is proposed. Centroid all rank distance(CARD), CARDx, and Centroid all rank distance batch K-means(CARDBK) are three clustering algorithms that adopt the soft competition learning method proposed by us. Among them the extent to which one point affects a cluster centroid depends on the distances from this point to the other nearer cluster centroids, rather than just the rank number of the distance from this point to this cluster centroid among the distances from this point to all cluster centroids. In addition, the validation experiments are carried out in order to compare the three soft competition learning algorithms CARD, CARDx, and CARDBK with several hard competition learning algorithms as well as neural gas(NG) algorithm on five data sets from different sources. Judging from the values of five performance indexes in the clustering results, this kind of soft competition learning method has better clustering effect and efficiency, and has linear scalability.

Key words: clustering methods, text processing, document handling, competition learning method

中图分类号:

TP391

yehang zhu. Application of a soft competition learning method in document clustering[J]. JOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOM, 2018, 25(3): 80-91.

参考文献

1. Zhu Y H. Research on document clustering algorithm. Ph D Thesis. Xi’an, China: Northwestern Polytechnical University, 2009 (in Chinese)

2. Zhu Y H, Li Y L, Yang X W. Improved clustering algorithm CARD based on Neural-Gas algorithm. Application Research of Computers, 2015, 32(5): 1309-1312 (in Chinese)

3. Zhu Y H, Li Y L, Cui M T, et al. Clustering algorithm CARDBK improved from k-means algorithm. Computer Science, 2015, 42(3): 201-205 (in Chinese).

4. Johnson T, Singh S K. Divisive hierarchical bisecting min-max clustering algorithm. Advances in Intelligent Systems and Computing: Proceedings of the International Conference on Data Engineering and Communication Technology (ICDECT’16): Vol 1, Mar 10-11, 2016, Pune, India. AISC 468. Singapore: Springer-Verlag, 2017: 579-592

5. Bishnu P S, Bhattacherjee V. Software cost estimation based on modified k-modes clustering Algorithm. Natural Computing, 2016, 15(3): 415-422

6. El Aziz M A, Selim I M, Essam A. Open cluster membership probability based on k-means clustering algorithm. Experimental Astronomy, 2016, 42(1): 49-59

7. Huang C Q, Chung F l, Wang S T. Generalized competitive agglomeration clustering algorithm. International Journal of Machine Learning and Cybernetics, 2016: 1-25

8. Li W J, Feng Y M, Li D J, et al. Micro-blog topic detection method based on BTM topic model and k-means clustering algorithm. Automatic Control and Computer Sciences, 2016, 50(4): 271-277

9. Huang Y, Zhang W Z, Zhang H Y, et al (2016) A fast clustering algorithm for massive short message. Human Centered Computing: Proceedings of the 2nd International Conference on Human Centered Computing (HCC’16), Jan 7-9, 2016, Colombo, Sri Lanka. LNCS 9567. Cham, Switzerland: Springer-Verlag, 2016: 183-192

10. Zhang B, Nie T Z, Shen D R, et al. A graph clustering algorithm for citation networks. Web Technologies and Applications: Proceedings of the 18th Asia-Pacific Web Conference (APWeb’16), Sept 23-25, 2016, Suzhou, China. LNCS 9932. Cham, Switzerland: Springer-Verlag, 2016: 414-418

11. Modha S, Joshi K. Performance analysis of clustering algorithm in sensing microblog for smart cities. Advances in Intelligent Systems and Computing: Proceedings of the International Congress on Information and Communication Technology (ICICT’15): Vol 2, Oct 9-10, 2015, Udaipur, India. AISC 439. Singapore: Springer-Verlag, 2015: 467-475

12. Zhong S. Efficient online spherical k-means clustering. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks (IJCNN’05): Vol 5, Jul 31-Aut 4, 2005, Montreal, Canada. Piscataway, NJ, USA: IEEE, 2005: 3180-3185

13. Huo J Y, Zhang H L. An improved k-means clustering algorithm based on the Voronoi diagram method. Advances in Swarm Intelligence: Proceedings of the 7th International Conference on Swarm Intelligence (ICSI’16) Vol 2, Jun 25-30, 2016, Bali, Indonesia. LNCS 9713. Cham, Switzerland: Springer-Verlag, 2016: 107-114

14. Nagaraju S, Kashyap M, Bhattachraya M. An effective density based approach to detect complex data clusters using notion of neighborhood difference. International Journal of Automation and Computing, 2017, 14(1): 57-67

15. Wang Z T, Kang P, Wu Z W, et al. A density-based clustering algorithm with educational applications. Current Developments in Web Based Learning: Proceedings of the 14th International Conference of Web Based Learning (ICWL’15), Nov 5-8, Guangzhou, China. LNCS 9584. Cham, Switzerland: Springer-Verlag, 2016: 118-127

16. Dey L, Ranjan K, Verma I, et al. Semantic overlapping clustering algorithm for analyzing short-texts. Rough Sets: Proceedings of the International Joint Conference on Rough Sets (IJCRS’16), Oct 7-11, 2016, Santiago, Chile. LNCS 9920. Cham, Switzerland: Springer-Verlag, 2016: 470-479

17. Li Y J, Luo C N, Chung S M. A parallel text document clustering algorithm based on neighbors. Cluster Computing, 2015, 18(2): 933-948

18. Xu D G, Zhao P L, Yang C H, et al. A novel Minkowski-distance-based consensus clustering algorithm. International Journal of Automation and Computing, 2017, 14(1): 33-44

19. Hilala J, Rovshan A. Applying k-means clustering algorithm using oracle data mining to banking data. Advances in Intelligent Systems and Computing: Proceedings of the 9th International Conference on Management Science and Engineering Management (ICMSEM’15), Jul 21-25, 2015, Karlsruhe, Germany. AISC 362. Berlin, Germany: Springer-Verlag, 2015: 809-816

20. Judith J E, Jayakumari J. Optimized distributed text document clustering algorithm. Advances in Intelligent Systems and Computing: Proceedings of the 2014 International Conference on Artificial Intelligence and Evolutionary Algorithms in Engineering Systems (ICAEES’14): Vol 2, Apr 22-23, 2014, Kumaracoil, India. AISC 325. New Delhi, India: Springer-Verlag, 2015: 565-574

21. Liu G L, Tan Y Q, Yu L M, et al. Application research of modified k-means clustering algorithm. Proceedings of the 19th International Conference on Industrial Engineering and Engineering Management (IE&EM’12), Oct 27-29, 2012, Changsha, China. Berlin, Germany: Springer-Verlag, 2013: 1269-1280

[1]	汪昭颖, 周军华, 廖中华, 翟翔, 张连平. Semantic segmentation of track image based on deep neural network[J]. 中国邮电高校学报(英文版), 2020, 27(5): 23-33.
[2]	陈法权樊军. Real-time prediction of the motion tendency of human lower limbs during gait [J]. 中国邮电高校学报(英文版), 2020, 27(4): 1-7.
[3]	刘永利刘燊. Meta-heuristic optimization inspired by proton-electron swarm[J]. 中国邮电高校学报(英文版), 2020, 27(3): 42-52.
[4]	Yao Wenbin, Hu Fangyi. Improvement of LDA model with time factor for collaborative filtering[J]. 中国邮电高校学报(英文版), 2019, 26(6): 54-62.
[5]	Liu Tingting, Liu Zhen, Pang Qianchao, Ouyang Menglin, Chai Yanjie. Research on virtual reality system design for body and psychological rehabilitation[J]. 中国邮电高校学报(英文版), 2019, 26(6): 73-82.
[6]	Yang Lingzhi, Ban Xiaojuan, Michele Mukeshimana, Chen Zhe. Multiple feature fusion for unimodal emotion recognition[J]. 中国邮电高校学报(英文版), 2019, 26(2): 17-29.
[7]	Guo Xiaopei, Feng Zhiquan, Sun Kaiyun, Liu Hong, Xie Wei, Bi Jianping. Research on unified recognition model and algorithm for multi-modal gestures[J]. 中国邮电高校学报(英文版), 2019, 26(2): 30-42.
[8]	苏志斌钱亚红谷雨任慧. Research on emotion space of film and television scene images based on subjective perception[J]. 中国邮电高校学报(英文版), 2019, 26(1): 75-81.
[9]	李端张洪欣 Muhammad Saad Khan 米芳. Recognition of motor imagery tasks for BCI using CSP and chaotic PSO twin SVM[J]. 中国邮电高校学报(英文版), 2017, 24(3): 83-90.
[10]	屠守中黄民烈. Mining microblog user interests based on TextRank with TF-IDF factor[J]. 中国邮电高校学报(英文版), 2016, 23(5): 40-46.
[11]	李晶陈万忠赵晓晖. Achievement of Bluetooth adaptive packet selection strategies based on SNR estimation[J]. 中国邮电高校学报(英文版), 2016, 23(1): 8-13.
[12]	徐雅静黎功福薛超罗安根宋一晢. Affinity-based Human Mobility Pattern for Improved Region Function Discovering[J]. 中国邮电高校学报(英文版), 2016, 23(1): 60-67.
[13]	张捷范旭慧班登科. Smooth support vector machine based on circular tangent function[J]. 中国邮电高校学报(英文版), 2016, 23(1): 68-72.
[14]	张小红胡应梦. RFID mutual-authentication protocol with synchronous updated-keys based on Hash function[J]. Acta Metallurgica Sinica(English letters), 2015, 22(6): 27-35.
[15]	王亮刘贵喜段红岩. Dynamic and combined gestures recognition based on multi-feature fusion in a complex environment [J]. Acta Metallurgica Sinica(English letters), 2015, 22(2): 81-88.

Application of a soft competition learning method in document clustering

Application of a soft competition learning method in document clustering

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价