High Confidence Heuristic Strategy for Minimal Reduction
-
摘要: 为提高启发式算法计算最小约简的可信度,基于可辨识矩阵,研究了属性之间存在的吸收、排斥以及互斥等特征,分析其与最小约简的关联,提出了对应的最小约简属性启发策略, 建立了各个特征下属性启发策略的可信度计算模型. 在此基础上,按照可信度排序,形成了一种综合的高可信度最小约简属性启发策略,并给出了具体的约简算法. 理论和实验分析表明,本文策略具有可信度高且可信度可以估计等优点,能有效提升最小约简算法的性能.Abstract: In order to improve the confidence of minimal reducts calculated by heuristic methods, some important characters of attributes, such as absorption, repulsion, and mutex etc., are presented based on the discernibility matrix. Then the related heuristic strategies are proposed by analyzing the relation between these characters and the minimal reducts. Some confidence models of these strategies are established to order these strategies. On the basis, an integrated strategy and a related reduction algorithm are proposed to calculate a minimal redcut. Theoretic and experimental analyses show that the proposed strategies are of high confidence and effectiveness.
-
Key words:
- Attribute absorption /
- attribute repulsion /
- attribute mutex /
- minimal reduct /
- confidence
-
[1] Yao Y Y, Zhao Y. Discernibility matrix simplification for constructing attribute reducts. Information Sciences, 2009, 179(7): 867-882[2] Xie Y H. A new heuristic attribute reduction method based on boolean matrix. Applied Mechanics and Materials, 2011, 50-51: 605-609[3] Qian Y H, Liang J Y, Pedrycz W, Dang C Y. Positive approximation: an accelerator for attribute reduction in rough set theory. Artificial Intelligence, 2010, 174(9-10): 597-618[4] Xu Yi, Li Long-Shu. Variable precision rough set model based on (α, λ) connection degree tolerance relation. Acta Automatica Sinica, 2011, 37(3): 303-308 (徐怡, 李龙澍. 基于(α, λ)联系度容差关系的变精度粗糙集模型. 自动化学报, 2011, 37(3): 303-308)[5] Min F, He H P, Qian Y H, Zhu W. Test-cost-sensitive attribute reduction. Information Sciences, 2011, 181(22): 4928-4942[6] Hu B G, Wang Y. Evaluation criteria based on mutual information for classifications including rejected class. Acta Automatica Sinica, 2008, 34(11): 1396-1403[7] Liu B X, Li Y, Li L H, Yu Y P. An approximate reduction algorithm based on conditional entropy. Information Computing and Applications, 2010, 106(6): 319-325[8] Zhou L, Jiang F. A rough set approach to feature selection based on relative decision entropy. Rough Sets and Knowledge Technology, 2011, 6954: 110-119[9] Qian Y H, Liang J Y, Wang F. A new method for measuring the uncertainty in incomplete information systems. Fuzziness and Knowledge-Based Systems, 2009, 17(6): 855-880[10] Chen Y M, Miao D Q, Wang R Z. A rough set approach to feature selection based on ant colony optimization. Pattern Recognition Letters, 2010, 31(3): 226-233[11] Jensen R, Shen Q. Semantics-preserving dimensionality reduction: rough and fuzzy-rough-based approaches. IEEE Transactions on Knowledge Data Engineering, 2004, 16(12): 1457-1471[12] Lv Y J, Liu N X. Application of quantum genetic algorithm on finding minimal reduct. In: Proceedings of the 2007 IEEE International Conference on Granular Computing. Washington DC, USA: IEEE, 2007. 728[13] Wang X Y, Yang J, Teng X L, Xia W J, Jensen R. Feature selection based on rough sets and particle swarm optimization. Pattern Recognition Letters, 2007, 28(4): 459-471[14] Ke L J, Feng Z R, Ren Z G. An efficient ant colony optimization approach to attribute reduction in rough set theory. Pattern Recognition Letters, 2008, 29(9): 1351-1357[15] Zhao Y, Yao Y Y, Luo F. Data analysis based on discernibility and indiscernibility. Information Sciences, 2007, 177(22): 4959-4976
点击查看大图
计量
- 文章访问数: 1655
- HTML全文浏览量: 55
- PDF下载量: 677
- 被引次数: 0