基于决策倾向度的样本过滤与主动选择
|
摘要
该文提出了基于过滤函数的粗糙集样本决策倾向度动态调节与主动选择方法。首先定义样本过滤函数,从而确定样本选择或丢弃的依据;然后依次添加新增样本,根据过滤函数决定样本的去留,同时根据阈值指标调节已有样本的决策倾向度;最终建立有效的决策样本库,并在此基础上进行属性约简。本方法克服了传统变精度方法实现过程复杂、计算量大的问题,可有效地去除噪声数据,提高系统的鲁棒性。数据实验结果表明,该方法可以有效地压缩数据,提高样本分析质量。
A dynamic adjustment and active selection method for rough set decision making based on filtering function is proposed. Firstly, a sample filtering function is defined to determine the basis for sample selection or discarding; then, new samples are added in turn to determine the retention of samples according to the filtering function, and the decision-making tendency of existing samples is adjusted according to the threshold;finally, new sample library is established and attribute reduction is carried out. This method overcomes the problems of complex implementation process and large amount of calculation in traditional variable precision methods, and can effectively remove noise data and improve the robustness of the system. Experimental results show that this method can effectively compress data and improve the quality of sample analysis.
A dynamic adjustment and active selection method for rough set decision making based on filtering function is proposed. Firstly, a sample filtering function is defined to determine the basis for sample selection or discarding; then, new samples are added in turn to determine the retention of samples according to the filtering function, and the decision-making tendency of existing samples is adjusted according to the threshold;finally, new sample library is established and attribute reduction is carried out. This method overcomes the problems of complex implementation process and large amount of calculation in traditional variable precision methods, and can effectively remove noise data and improve the robustness of the system. Experimental results show that this method can effectively compress data and improve the quality of sample analysis.
引文
[1]PAWLAK Z.Rough sets[J].International Journal of Computer and Information Science,1982,11(5):341-356.
[2]张文修,吴伟志,梁吉业.粗糙集理论与方法[M].北京:科学出版社,2001:19-23.ZHANG Wen-xiu,WU Wei-zhi,LIANG Ji-ye.Rough set theory and method[M].Beijing:Science Press,2001:19-23.
[3]胡清华,于达仁.应用粗糙计算[M].北京:科学出版社,2012:56-60.HU Qing-hua,YU Da-ren,Application of rough computing[M].Beijing:Science Press,2012:56-60.
[4]刘清.Rough集及Rough推理[M].北京:科学出版社,2001:12-18.LIU Qing,Rough sets and Rough reasoning[M].Beijing:Science Press,2001:12-18.
[5]廖启明,龙鹏飞.基于属性重要性的粗糙集属性约简方法[J].计算机工程与应用,2013,49(15):130-132.LIAO Qi-ming,LONG Peng-fei.Rough set reduction method of attribute based on importance of attribute[J].Computer Engineering and Applications,2013,49(15):130-132.
[6]SKOWRON A,RAUSZER C.The discernibility matrices and functions in information systems[M].Theory&Decision Library,1992,11:331-362.
[7]杨明.一种基于改进差别矩阵的属性约简增量式更新算法[J].计算机学报,2007,30(5):815-822.YANG Ming.An incremental updating algorithm for attribute reduction based on improved discernibility matrix[J].Chinese Journal of Computers,2007,30(5):815-822.
[8]GUAN Li-he.An incremental updating algorithm of attribute reduction set in decision tables[C]//2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.Tianjin,China:IEEE,2009:421-425.
[9]FENG S R,ZHANG D Z.Increment algorithm for attribute reduction based on improvement of discernibility matrix[J].Journal of Shenzhen University Science and Engineering,2012,29(5):405-411.
[10]ZIARKO W.Variable precision rough set model[J].Journal of Computer and System Sciences,1993,46(1):39-59.
[11]ZIARKO W.Analysis of uncertain information in the framework of variable precision rough sets[J].Foundations of Computing&Decision Sciences,1993,18(3):381-396.
[12]YANG Y,CHEN D,WANG H.Active sample selection based incremental algorithm for attribute reduction with rough sets[J].IEEE Transactions on Fuzzy Systems,2017,25(4):825-838.
[13]YANG Y,CHEN D,WANG H,et al.Fuzzy rough set based incremental attribute reduction from dynamic data with sample arriving[J].Fuzzy Sets and Systems,2017,312:66-86.
[14]DONG Z,SUN M,YANG Y.Fast algorithms of attribute reduction for covering decision systems with minimal elements in discernibility matrix[J].International Journal of Machine Learning and Cybernetics,2016,7(2):297-310.
[15]CHEN D,YANG Y,DONG Z.An incremental algorithm for attribute reduction with variable precision rough sets[J].Applied Soft Computing,2016,45:129-149.
[16]杨燕燕.基于粗糙集的增量属性约简机理与算法研究[D].北京:华北电力大学,2017.YANG Yan-yan.Rough set based mechanisms and algorithms for incremental attribute reduction[D].Beijing:North China Electric Power University,2017.
[17]BACHE K,LICHMAN M.UCI machine learning repository[EB/OL].[2017-08-13]:http://archive.ics.uci.edu/ml/datasets.html.
[18]YAO Y,ZHAO Y.Discernibility matrix simplification for constructing attribute reducts[J].Information Sciences,2009,179(7):867-882.
[19]CHEN D G,ZHAO S Y,ZHANG L.Sample pair selection for attribute reduction with rough set[J].IEEE Transactions on Knowledge and Data Engineering,2012,24(11):2080-2093.
[2]张文修,吴伟志,梁吉业.粗糙集理论与方法[M].北京:科学出版社,2001:19-23.ZHANG Wen-xiu,WU Wei-zhi,LIANG Ji-ye.Rough set theory and method[M].Beijing:Science Press,2001:19-23.
[3]胡清华,于达仁.应用粗糙计算[M].北京:科学出版社,2012:56-60.HU Qing-hua,YU Da-ren,Application of rough computing[M].Beijing:Science Press,2012:56-60.
[4]刘清.Rough集及Rough推理[M].北京:科学出版社,2001:12-18.LIU Qing,Rough sets and Rough reasoning[M].Beijing:Science Press,2001:12-18.
[5]廖启明,龙鹏飞.基于属性重要性的粗糙集属性约简方法[J].计算机工程与应用,2013,49(15):130-132.LIAO Qi-ming,LONG Peng-fei.Rough set reduction method of attribute based on importance of attribute[J].Computer Engineering and Applications,2013,49(15):130-132.
[6]SKOWRON A,RAUSZER C.The discernibility matrices and functions in information systems[M].Theory&Decision Library,1992,11:331-362.
[7]杨明.一种基于改进差别矩阵的属性约简增量式更新算法[J].计算机学报,2007,30(5):815-822.YANG Ming.An incremental updating algorithm for attribute reduction based on improved discernibility matrix[J].Chinese Journal of Computers,2007,30(5):815-822.
[8]GUAN Li-he.An incremental updating algorithm of attribute reduction set in decision tables[C]//2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.Tianjin,China:IEEE,2009:421-425.
[9]FENG S R,ZHANG D Z.Increment algorithm for attribute reduction based on improvement of discernibility matrix[J].Journal of Shenzhen University Science and Engineering,2012,29(5):405-411.
[10]ZIARKO W.Variable precision rough set model[J].Journal of Computer and System Sciences,1993,46(1):39-59.
[11]ZIARKO W.Analysis of uncertain information in the framework of variable precision rough sets[J].Foundations of Computing&Decision Sciences,1993,18(3):381-396.
[12]YANG Y,CHEN D,WANG H.Active sample selection based incremental algorithm for attribute reduction with rough sets[J].IEEE Transactions on Fuzzy Systems,2017,25(4):825-838.
[13]YANG Y,CHEN D,WANG H,et al.Fuzzy rough set based incremental attribute reduction from dynamic data with sample arriving[J].Fuzzy Sets and Systems,2017,312:66-86.
[14]DONG Z,SUN M,YANG Y.Fast algorithms of attribute reduction for covering decision systems with minimal elements in discernibility matrix[J].International Journal of Machine Learning and Cybernetics,2016,7(2):297-310.
[15]CHEN D,YANG Y,DONG Z.An incremental algorithm for attribute reduction with variable precision rough sets[J].Applied Soft Computing,2016,45:129-149.
[16]杨燕燕.基于粗糙集的增量属性约简机理与算法研究[D].北京:华北电力大学,2017.YANG Yan-yan.Rough set based mechanisms and algorithms for incremental attribute reduction[D].Beijing:North China Electric Power University,2017.
[17]BACHE K,LICHMAN M.UCI machine learning repository[EB/OL].[2017-08-13]:http://archive.ics.uci.edu/ml/datasets.html.
[18]YAO Y,ZHAO Y.Discernibility matrix simplification for constructing attribute reducts[J].Information Sciences,2009,179(7):867-882.
[19]CHEN D G,ZHAO S Y,ZHANG L.Sample pair selection for attribute reduction with rough set[J].IEEE Transactions on Knowledge and Data Engineering,2012,24(11):2080-2093.