Weighted Dependence of Neighborhood Rough Sets and Its Heuristic Reduction Algorithm
XU Bo1,2, ZHANG Xianyong1,2, FENG Shan1
1.School of Mathematical Sciences, Sichuan Normal University, Chengdu 610068 2.Institute of Intelligent Information and Quantum Information, Sichuan Normal University, Chengdu 610068
Abstract Neighborhood rough sets act as an effective tool for data processing of numeric attributes. According to neighborhood rough sets, the traditional dependency and its reduction rarely take the absolute structure of neighborhood covering into account. Therefore the weighted dependence and its heuristic reduction algorithm are established in this paper. Firstly, the weighted dependence is proposed to gain its measure improvement and granulation monotonicity, and its relevant attribute reduction is defined. Secondly, the self-adapting valuing of the neighborhood radius is analyzed, and the neighborhood weighted dependence reduction(NWDR algorithm) is constructed. Finally, contrast experiments on UCI datasets are implemented, and both the monotonicity of the weighted dependence and the effectiveness of NWDR are verified. The weighted dependence improves the uncertainty representation ability of the classical dependence, and the relevant NWDR exhibits higher classification accuracy and stronger application applicability.
Fund:Supported by National Natural Science Foundation of China(No.61673285,61203285), Sichuan Youth Science and Technology Foundation(No.2017JQ0046), Scientific Research Fund of Sichuan Provincial Education Department(No.15ZB0029)
Corresponding Authors:
ZHANG Xianyong, Ph.D., professor. His research interests include rough sets, granular computing and data mining.
About author:: XU Bo, master student. His research inte-rests include rough sets, data mining and intelligence algorithms.FENG Shan, Ph.D., professor. His research interests include artificial intelligence algorithm, intelligent software platform deve-lopment and data mining.)
[1] PAWLAK Z. Rough Sets. International Journal of Computer & Information Sciences, 1982, 11(5): 341-356. [2] MAGRO M C, PINCETI P. A Confirmation Technique for Predictive Maintenance Using the Rough Set Theory.Computers & Industrial Engineering, 2009, 56(4): 1319-1327. [3] DENG T Q, YANG C D, WANG X F.A Reduct Derived from Feature Selection. Pattern Recognition Letters, 2012, 33(12): 1638-1646. [4] WONG S K M, ZIARKO W. On Optimal Decision Rules in Decision Tables. Bulletin of Polish Academy of Sciences, 1985, 33(11/12): 693-696. [5] YAO Y Y, ZHAO Y. Discernibility Matrix Simplification for Constructing Attribute Reducts. Information Sciences, 2009, 179(7): 867-882. [6] ZHANG X Y, MIAO D Q. Three-Layer Granular Structures and Three-Way Informational Measures of a Decision Table. Information Sciences, 2017, 412/413: 67-86. [7] ZHANG X Y, MIAO D Q. Three-Way Attribute Reducts. International Journal of Approximate Reasoning, 2017, 88: 401-434. [8] KWAK N, CHOI C H. Input Feature Selection for Classification Problems. IEEE Transactions on Neural Networks, 2002, 13(1): 143-159. [9] 苗夺谦,胡桂荣.知识约简的一种启发式算法.计算机研究与发展, 1999, 36(6): 681-684. (MIAO D Q, HU G R. A Heuristic Algorithm for Reduction of Knowledge. Journal of Computer Research & Development, 1999, 36(6): 681-684.) [10] LIANG J Y, SHI Z Z, LI D Y. Information Entropy, Rough Entropy and Knowledge Granulation in Incomplete Information Systems. International Journal of General Systems, 2006, 35(6): 641-654. [11] 江 峰,王莎莎,杜军威,等.基于近似决策熵的属性约简.控制与决策, 2015, 30(1): 65-70. (JIANG F, WANG S S, DU J W, et al. Attribute Reduction Based on Approximation Decision Entropy. Control and Decision, 2015, 30(1): 65-70.) [12] 王国胤,于 洪,杨大春.基于条件信息熵的决策表约简.计算机学报, 2002, 25(7): 759-766. (WANG G Y, YU H, YANG D C. Decision Table Reduction Based on Conditional Information Entropy. Chinese Journal of Computers, 2002, 25(7): 759-766.) [13] LI C L, ZHANG H, ZHAO R Y, et al. Discretization Algorithm for Continuous Attribute in Rough Set Theory Based on Heuristic SOM. Journal of Guangxi Normal University(Natural Science Edition), 2006, 24(4): 46-49. [14] HU Q H, YU D R, LIU J F, et al. Neighborhood Rough Set Based Heterogeneous Feature Subset Selection.Information Sciences, 2008, 178(18): 3577-3594. [15] 胡清华,于达仁,谢宗霞.基于邻域粒化和粗糙逼近的数值属性约简.软件学报, 2008, 19(3): 640-649. (HU Q H, YU D R, XIE Z X. Numerical Attribute Reduction Based on Neighborhood Granulation and Rough Approximation. Journal of Software, 2008, 19(3): 640-649.) [16] CHEN Y M, XUE Y, MA Y, et al. Measures of Uncertainty for Neighborhood Rough Sets. Knowledge-Based Systems, 2017, 120: 226-235. [17] CHEN Y M, ZENG Z Q, LU J W. Neighborhood Rough Set Redu- ction with Fish Swarm Algorithm.Soft Computing, 2017, 21(23): 6907-6918. [18] 叶东毅,廖建坤.基于二进制粒子群优化的一个最小属性约简算法.模式识别与人工智能, 2007, 20(3): 295-300. (YE D Y, LIAO J K. Minimum Attribute Reduction Algorithm Based on Binary Particle Swarm Optimization. Pattern Recognition and Artificial Intelligence, 2007, 20(3): 295-300.) [19] 娄 畅,刘遵仁,郭功振.一种多阈值邻域粗糙集的属性约简算法.青岛大学学报(自然科学版), 2014, 27(4): 44-48. (LOU C, LIU Z R, GUO G Z. An Attribute Reduct Algorithm for Multi-threshold Neighborhood Rough Set. Journal of Qingdao University(Natural Science Edition), 2014, 27(4): 44-48.)
2018, Vol. 31 
