粗糙集属性约简判别分析方法及其应用
|
摘要
为了解决统计逐步判别分析法存在的问题,提出了一种基于粗糙集属性约简的统计判别分析方法.首先采用粗糙集属性约简进行变量筛选,这样可充分利用粗糙集属性约简不需要属性分布的先验信息这一特点,再对所选择的变量进行Bayes判别分析训练,建立判别函数或相应的后验概率函数,以解决选择变量过程中存储量较大且检验变量的重要性总体服从正态分布这一主观性假设等问题.通过对油气储层数据的实际分析表明,所提方法不仅易于实施,而且检验数据集的判别准确率高于统计逐步判别分析法,同时可节省预测成本,提高预测速度.
In order to overcome some shortcomings of the statistical stepwise discrimination method,a new discrimination method based on rough set attribute reduction is proposed,in which the attribute reduction of rough set is used to select important discriminating variables by sufficiently taking advantage of the feature that the attribute reduction of rough set needs no prior information on the distribution.Then,with the selected variables,Bayesian discrimination procedure is used to build the discrimination function or compute the posterior probability so as to solve the problems that the storage size is much bigger and the importance of discriminating variables wholly obey the normal distribution from the subjective assumption in the statistical stepwise discrimination method.Through applying the proposed method to the real-world dataset of reservoir of oil and gas,it is demonstrated that the proposed method not only is easy to be implemented with higher correct discrimination rate,but also can decrease the computational cost and increase the prediction speed.
In order to overcome some shortcomings of the statistical stepwise discrimination method,a new discrimination method based on rough set attribute reduction is proposed,in which the attribute reduction of rough set is used to select important discriminating variables by sufficiently taking advantage of the feature that the attribute reduction of rough set needs no prior information on the distribution.Then,with the selected variables,Bayesian discrimination procedure is used to build the discrimination function or compute the posterior probability so as to solve the problems that the storage size is much bigger and the importance of discriminating variables wholly obey the normal distribution from the subjective assumption in the statistical stepwise discrimination method.Through applying the proposed method to the real-world dataset of reservoir of oil and gas,it is demonstrated that the proposed method not only is easy to be implemented with higher correct discrimination rate,but also can decrease the computational cost and increase the prediction speed.
引文
[1]范金城,梅长林.数据分析[M].北京:科学出版社,2002.
[2]梅长林,周家良.实用统计分析方法[M].北京:科学出版社,2002.
[3]Lingras P J,Yao Y Y.Data mining using extensionsof the rough set model[J].Journal of the AmericanSociety for Information Sciences,1998,49(5):415-422.
[4]张文修,吴伟志,梁吉业,等.粗糙集理论与方法[M].北京:科学出版社,2003.
[5]Greco S,Matarazzo B,Slowinski R.Rough sets theo-ry for multicriteria decision analysis[J].EuropeanJournal of Operational Research,2001,129(1):1-47.
[6]Pawlak Z.Rough sets:theoretical aspects of reasoningabout data[M].Dordrecht,Netherlands:Klumer Aca-demic Publishers,1991:1-53.
[7]夏克文,沈钧毅,李昌彪.样本信息处理中一种属性约简方法的研究[J].西安交通大学学报,2005,39(6):558-561.Xia Kewen,Shen Junyi,Li Changbiao.Study on at-tribute reduction method in sample information pro-cessing[J].Journal of Xi′an Jiaotong University,2005,39(6):558-561.
[8]史忠植.知识发现[M].2版.北京:清华大学出版社,2004.
[9]高惠璇.应用多元统计分析[M].北京:北京大学出版社,2005.
[10]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社.1998.
[11]郭同翠,刘明新,郑晓东,等.地震数据识别孔隙流体和孔隙度[J].天然气勘探与开发,2004,27(3):18-20.Guo Tongcui,Liu Mingxin,Zhang Xiaodong,et al.Recognition of pore-fluid and porosity by seismic data[J].Natural Gas Exploration and Development,2004,27(3):18-20.
[12]陈遵德,陈富贵.地震数据油气预测中的属性优化方法[J].石油物探,1998,37(4):32-40.Chen Zunde,Chen Fugui.An attribute optimizationmethod in oil and gas prediction with seismic data[J].Geophysical Prospecting for Petroleum,1998,37(4):32-40.
[2]梅长林,周家良.实用统计分析方法[M].北京:科学出版社,2002.
[3]Lingras P J,Yao Y Y.Data mining using extensionsof the rough set model[J].Journal of the AmericanSociety for Information Sciences,1998,49(5):415-422.
[4]张文修,吴伟志,梁吉业,等.粗糙集理论与方法[M].北京:科学出版社,2003.
[5]Greco S,Matarazzo B,Slowinski R.Rough sets theo-ry for multicriteria decision analysis[J].EuropeanJournal of Operational Research,2001,129(1):1-47.
[6]Pawlak Z.Rough sets:theoretical aspects of reasoningabout data[M].Dordrecht,Netherlands:Klumer Aca-demic Publishers,1991:1-53.
[7]夏克文,沈钧毅,李昌彪.样本信息处理中一种属性约简方法的研究[J].西安交通大学学报,2005,39(6):558-561.Xia Kewen,Shen Junyi,Li Changbiao.Study on at-tribute reduction method in sample information pro-cessing[J].Journal of Xi′an Jiaotong University,2005,39(6):558-561.
[8]史忠植.知识发现[M].2版.北京:清华大学出版社,2004.
[9]高惠璇.应用多元统计分析[M].北京:北京大学出版社,2005.
[10]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社.1998.
[11]郭同翠,刘明新,郑晓东,等.地震数据识别孔隙流体和孔隙度[J].天然气勘探与开发,2004,27(3):18-20.Guo Tongcui,Liu Mingxin,Zhang Xiaodong,et al.Recognition of pore-fluid and porosity by seismic data[J].Natural Gas Exploration and Development,2004,27(3):18-20.
[12]陈遵德,陈富贵.地震数据油气预测中的属性优化方法[J].石油物探,1998,37(4):32-40.Chen Zunde,Chen Fugui.An attribute optimizationmethod in oil and gas prediction with seismic data[J].Geophysical Prospecting for Petroleum,1998,37(4):32-40.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心