动态区间的加权模糊聚类算法

doi:10.3778/j.issn.1673-9418.1907013

摘要/Abstract

摘要：

数据聚类在数据挖掘、数据分析中广泛应用，而不完整数据对数据聚类造成了很大困扰。针对不完整数据聚类中估值法填补缺失属性不准确的问题，提出动态区间的加权模糊聚类算法。首先，由属性相关度构造缺失属性的最近邻样本集，进而形成缺失属性估值区间。为进一步减小区间填补误差，使用基于最近邻样本集的离散度的区间因子来动态调节区间大小。其次，为充分挖掘属性空间的隐含信息，同时降低离群点对聚类中心的影响，对完整的区间型数据集进行基于局部密度的样本加权。最后，通过以上改进完成区间型样本的加权模糊聚类。利用多个UCI数据集和人工数据集验证提出的聚类算法，实验结果表明：动态区间的加权模糊聚类算法能有效提高聚类准确性、鲁棒性以及收敛的稳定性。

关键词: 不完整数据, 区间填补, 加权, 聚类算法

Abstract:

Clustering is widely used in data mining and data analysis, and a great many of troubles have been caused by incomplete data in clustering. Aiming at the inaccurate problem of filling missing attributes with estimation method in incomplete data clustering, a weighted fuzzy clustering algorithm is proposed based on dynamic interval. Firstly, the nearest neighbor sample sets of the missing attribute are constructed by the attribute correlation and then the missing attribute interval is formed. To further reduce the interval filling error, the interval factor which is based on the dispersion of the nearest neighbor sample set is used to adjust the interval size. Secondly, in order to fully exploit the implicit information of the attribute space and reduce the influence of the outliers on the cluster center, complete interval datasets are weighted based on local density of samples. Finally, the interval weighted fuzzy clustering is completed by the above improvement. The proposed clustering algorithm is verified by multiple UCI datasets and artificial datasets. The experimental results show that the weighted fuzzy clustering algorithm of dynamic interval can effectively improve the clustering accuracy, robustness and stability of convergence.

Key words: incomplete data, interval filling, weighting, clustering algorithm

罗浩，王彦捷，牛明航，邱存月，张利. 动态区间的加权模糊聚类算法[J]. 计算机科学与探索, 2020, 14(7): 1142-1153.

LUO Hao, WANG Yanjie, NIU Minghang, QIU Cunyue, ZHANG Li. Weighted Fuzzy Clustering Algorithm Based on Dynamic Interval[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(7): 1142-1153.

参考文献

[1] Hathaway R J, Bezdek J C. Fuzzy C-means clustering of incomplete data[J]. IEEE Transactions on Systems, Man, and Cybernetics: Part B Cybernetics, 2001, 31(5): 735-744.
[2] Gu B, Sun X M, Sheng V S. Structural minimax probability machine[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(7): 1646-1656.
[3] Song K, Feng X, Yu H Q. New fuzzy clustering based on group evolution strategies[J]. Computer Engineering and Applications, 2018, 54(4): 36-43.宋凯, 冯翔, 虞慧群. 基于群进化策略的模糊聚类算法[J].计算机工程与应用, 2018, 54(4): 36-43.
[4] Deb R, Liew A W. Missing value imputation for the analysis of incomplete traffic accident data[J]. Information Sciences, 2016, 339: 274-289.
[5] Marek ?, Lukasz S, Jacek T, et al. Generalized RBF kernel for incomplete data[J]. Knowledge-Based Systems, 2019, 173: 150-162.
[6] Tucker J, Lyndsay S, John R. Handling missing data in self-exciting point process models[J]. Spatial Statistics, 2019, 29: 160-176.
[7] Jia H N, Wang S T. Reinforced rule-based fuzzy models for noisy data and its implementation[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(11): 120-131.贾海宁, 王士同. 面向噪声整数据的强化模糊规则模型及实现[J]. 计算机科学与探索, 2018, 12(11): 120-131.
[8] Qian X D, Luo Y F. Incomplete data clustering algorithm based on mutual information attributes ranking[J]. Information and Control, 2019, 48(1): 80-87.钱晓东, 罗彦福. 基于互信息属性排序的不完整数据聚类算法[J]. 信息与控制, 2019, 48(1): 80-87.
[9] Shao X C. Research on key technique of mixed data clus-tering based on sparse representation[D]. Beijing: University of Science & Technology Beijing, 2018: 50-72.邵晓晨. 基于稀疏表示的混合属性数据聚类关键技术研究[D]. 北京: 北京科技大学, 2018: 50-72.
[10] Zhang L, Pan H, Wang B L, et al. Interval fuzzy C-means approach for incomplete data clustering based on neural networks[J]. Journal of Internet Technology, 2018, 19(4): 1089-1098.
[11] Li T H, Zhang L Y, Lu W, et al. Interval kernel fuzzy C-means clustering of incomplete data[J]. Neurocomputing, 2017, 237: 316-331.
[12] Thanh N, Trong H, Pedrycz W. Towards interval-valued fuzzy set-based collaborative fuzzy clustering algorithms[J]. Pattern Recognition, 2018, 81: 404-416.
[13] Jin H, Qian X Z. Optimized density peak clustering algorithm by natural nearest neighbor[J]. Journal of Frontiers of Com-puter Science and Technology, 2019, 13(4): 711-720.金辉, 钱雪忠. 自然最近邻优化的密度峰值聚类算法[J]. 计算机科学与探索, 2019, 13(4): 711-720.
[14] Tang Y M, Hu X H, Pedrycz W, et al. Possibilistic fuzzy clustering with high-density viewpoint[J]. Neurocomputing, 2019, 329: 407-423.
[15] Liu R H, Huang W P, Fei Z S, et al. Constraint-based clu-stering by fast search and find of density peaks[J]. Neuro-computing, 2019, 330: 223-237.
[16] Antonio I, Rosanna V, Francisco C. Fuzzy clustering of distributional data with automatic weighting of variable components[J]. Information Sciences, 2017, 406: 248-268.
[17] Zhang L Y, Pedrycz W, Lu W, et al. An interval weighted fuzzy C-means clustering by genetically guided alternating optimization[J]. Expert Systems with Applications, 2014, 41(13): 5960-5971.
[18] Kishore K R, Lokendra B, Sreenivasa R. A robust unsu-pervised pattern discovery and clustering of speech signals [J]. Pattern Recognition Letters, 2018, 116: 254- 261.
[19] Wang J, Zhao F. Multi-objective evolutionary fuzzy clustering algorithm based on semi-supervision[J]. Computer Engin-eering and Applications, 2017, 53(22): 40-44.王俊, 赵凤. 基于半监督的多目标进化模糊聚类算法[J]. 计算机工程与应用, 2017, 53(22): 40-44.
[20] Guo J, Yuan X, Han C. Sensor selection based on maximum entropy fuzzy clustering for target tracking in large-scale sensor networks[J]. IET Signal Processing, 2017, 11(5): 613-621.
[21] Liu W, Gu W, Sheng W X, et al. Virtual cluster control for active distribution system using pinning-based distributed secondary control[J]. Electrical Power and Energy Systems, 2019, 109: 710-718.
[22] Moufid B, Mouna G, Kheireddine C. Interval-valued mem-bership function estimation for fuzzy modeling[J]. Fuzzy Sets and Systems, 2019, 61: 101-113.
[23] Wang X, Yu F S, Pedryczd W, et al. Clustering of interval-valued time series of unequal length based on improved dynamic time warping[J]. Expert Systems with Applications, 2019, 125: 293-304.
[24] Bugata P, Drotar P. Weighted nearest neighbors feature selection[J]. Knowledge-Based Systems, 2019, 163: 749-761.
[25] Xia P, Zhang L, Li F. Learning similarity with cosine similarity ensemble[J]. Information Sciences, 2015, 307(1):39-52.
[26] Jiang Z, Li T, Min W. Fuzzy C-means clustering based on weights and gene expression programming[J]. Pattern Rec-ognition Letters, 2017, 90(1): 1-7.
[27] Wang L. Research of fuzzy clustering algorithm for incom-plete data based on the improved ACO with interval superv-ision[D]. Shenyang: Liaoning University, 2016.王鹭. 改进蚁群优化的区间监督模糊聚类算法研究[D]. 沈阳: 辽宁大学, 2016.
[28] Zhang L, Li B X, Zhang L Y, et al. Fuzzy clustering of incom-plete data based on missing attribute interval size[C]//Pro-ceedings of the 2015 IEEE International Conference on Anti- counterfeiting, Security, and Identification, Xiamen, Sep 25-27, 2015. Piscataway: IEEE, 2015: 101-104.
[29] Liu Y. Research of fuzzy clustering algorithm for incomplete data based on information feedback RBF network valuation[D]. Shenyang: Liaoning University, 2018.孙颖. 局部加权的不完整数据混杂聚类算法研究[D]. 沈阳: 辽宁大学, 2017.
[30] Sun Y. Research on hybird clustering algorithm for incomplete data based on local weighting[D]. Shenyang: Liaoning Uni-versity, 2017.刘洋. 信息反馈RBF网络估值的不完整数据模糊聚类算法研究[D]. 沈阳: 辽宁大学, 2018.