数据流集成分类器算法研究
|
摘要
随着信息技术的不断发展与应用,人们每天可以收集到大量高速、动态和连续到达的信息,如传感器网络数据、电话记录、金融数据和商业交易数据等。传统静态数据集作为信息的载体已无法有效表达该类信息,因此,数据流作为一种新的数据类型被提出并广泛应用于上述领域。数据流作为一种连续到达的、潜在无限输入的数据有序序列,与传统静态数据集相比,具有以下几个特征：(1)数据高速到达；(2)数据规模宏大；(3)数据流是有序数据；(4)数据流具有动态变化性；(5)数据流往往伴随高维特性。上述特征使数据流无法被传统数据挖掘分类算法有效处理,因此对数据流挖掘算法的研究成为数据挖掘领域的热点之一。
本文聚焦于数据流集成分类问题,围绕个体分类器生成与结论融合两个方面,对噪音数据流、高速数据流以及类标签不完整数据流的集成分类问题展开研究,主要研究工作如下：
首先,针对利用噪音数据流训练集成分类器,集成分类器的分类准确率受噪音数据影响严重的问题,提出一种交叉验证容噪数据流集成分类器算法。交叉验证容噪分类算法是一种典型的噪音消除算法,可以在建立分类模型之前有效去除数据集中的噪音数据,使分类模型的分类准确率明显提高。由于目前并没有学者对其有效性进行理论证明,因此本文通过有噪音数据集的样本复杂度理论,对其有效性进行了严格的理论推导,并根据推导结果提出了一种新的交叉验证容噪分类算法,应用在数据流环境里,进一步提高了集成分类模型对噪音数据流的分类能力。
其次,针对高速数据流数据到达速度远远超过处理器的处理能力,处理器无法利用全部数据训练个体分类器的问题,提出一种基于偏倚抽样的高速数据流集成分类器算法。抽样技术可以有效缩减待处理的数据规模,减少集成分类器的训练和更新时间,由于不同的抽样策略产生的训练数据集,建立集成分类器,其分类准确率具有明显区别。因此本文通过集成分类器期望错误的偏差方差分解,计算各个待抽样数据的期望错误贡献度,并通过集成分类器分类性能的几何分析,说明抽取期望错误贡献度大的数据作为训练数据更新集成分类器模型,可以有效提高集成分类器的分类准确率,并依此提出了基于偏倚抽样的高速数据流集成分类器算法。
再次,针对数据流中数据类标签难以全部获得的问题,提出一种基于聚类假设的半监督数据流集成分类器算法。传统半监督分类算法虽然能够解决类标签不完整数据集的分类问题,但如何将其引入数据流环境,利用数据流特性提高半监督分类算法的分类准确率仍是一个有待解决的问题。本文通过基于聚类假设的半监督分类算法分类误差分析,表明在训练个体分类器时增加有标签数据集的规模可以有效减少分类算法的分类误差,并利用此结论,提出了基于聚类假设的半监督数据流集成分类器算法。
最后,针对选择性集成分类算法训练一旦结束,被选择的个体分类器组合就以确定,无法针对具体数据进行动态调整的问题,提出一种两阶段数据流选择性集成分类器算法。本文首先通过分析说明,选择性集成分类算法获得的个体分类器集合,虽然在整体数据集上具有最优的分类性能,但对某具体数据分类时,并不一定是最优的个体分类器组合。因此,利用支持向量数据描述算法,动态自适应选择数据分类时的个体分类器集合,可以有效避免上述情况的发生,提高选择性集成分类器的分类性能。
With the development and application of information technology, people can collect lots of high-speed, dynamic and continuous information, such as sensors network data, telephone records, financial data and commercial transaction data etc. Traditional static data set s the information carrier has already been unable to efficiently express such information a. Therefore data stream as a kind of new data type is put forward and widely used in the above fields. Data stream is a kind of orderly data sequences which can continuously arrive in and potentially infinitely be input in. Compared with the traditional static data set, data stream has the following features:(1) Data reach with rapid speed. (2) Large-scale data. (3) Data stream is orderly sequences. (4) Data stream can dynamic change. (5) Data stream often is high-dimensional. The above features let data stream cannot be delt with effectively by the traditional data mining classification algorithm.So the research of data stream mining algorithm become one of the hot spots in the data mining area.
We focused on classifying data stream using ensemble classifiers in this paper. From two aspects of training individual classifier and integrating classified outcome, we studied noisy data stream, high speeding data stream and data stream without complete label. Main job is as follows:
First of all, aiming at the promble of ensemble classifiers classification accuracy is influenced seriously by noise which is trained by noisy data set, a cross validation noise-tolerance data stream ensemble classifiers algorithm was proposed. Cross validation noise-tolerance classification algorithm is an important method which eliminates noise of data set. That can eliminates noise of training data set before training classifier, So classifier classification accuracy be able to increased significantly. However, there have been not scholars to prove it validity in theory. According to sample complexity theory of noisy data set, algorithm validity was proved in this paper. And according to outcome of proving, a new Cross validation noise-tolerance classification algorithm which deal with data stream was proposed. It can further increase classification accuracy of classifier which deal with noisy data set.
Secondly, aiming at high speed data stream existing the phenomenon that the data rate is higher relative to the ensemble classifiers'computational power, so ensemble classifiers can't train all data to update themselves. An ensemble classifiers based on biased sample was proposed. Sampling technique can effectively reduce to data scale, so it can decrease time of training and updating ensemble classifiers. However, training differnet ensemble classifiers using data set produced by different sampling strategy, their classification performance has obvious difference. Therefore, by means of expectation error bias variance decomposition method, computing all data's expectation error contribution degree which waited for being sampled. And through geometric analysis of ensemble classifiers classification performance, it be proved that using data which have bigger expectation error contribution degree to train ensemble classifiers, the ensemble classifiers have more classification accuracy. According to that an ensemble classifiers algorithm based on biased sample was proposed in this paper.
Further, aiming at the promble that it is hardly to label all data in data stream, a semi-supervised data stream ensemble classifiers algorithm based on cluster assumption was proposed. Although traditional semi-supervised classification algorithm can solve incomplete label data sets classification problem, but it is an unsolved problem that how to use it in data stream environment and how to improve semi-supervised classification algorithm accuracy by using data stream characters. According to analyzing generalization of semi-supervised classifier based on cluster assumption, it indicates that increasing labeled data during training moment can improve semi-supervised classifier accuracy. Making use of this conclusion, a semi-supervised data stream ensemble classifiers algorithm based on cluster assumption was proposed.
Finally, aiming at the promble that after training in selective ensemble classifiers, it is determined which individual classifier be selected and be unable to dynamicly adjust with specific data. Two-phase selective ensemble classifiers algorithm of data sreams was presented. Through the analysis it is indicated that individual classifiers be selected by selective ensemble algorithm can have best Classification performance in whole data set, but they may be not optimal combination of individual classifiers to classify specific data. Hence, Dynamic adaptive choosing individual classifiers by Using support vector data description algorithm can Effectively prevent this situations and Improving selective ensemble classifiers classification performance.
本文聚焦于数据流集成分类问题,围绕个体分类器生成与结论融合两个方面,对噪音数据流、高速数据流以及类标签不完整数据流的集成分类问题展开研究,主要研究工作如下：
首先,针对利用噪音数据流训练集成分类器,集成分类器的分类准确率受噪音数据影响严重的问题,提出一种交叉验证容噪数据流集成分类器算法。交叉验证容噪分类算法是一种典型的噪音消除算法,可以在建立分类模型之前有效去除数据集中的噪音数据,使分类模型的分类准确率明显提高。由于目前并没有学者对其有效性进行理论证明,因此本文通过有噪音数据集的样本复杂度理论,对其有效性进行了严格的理论推导,并根据推导结果提出了一种新的交叉验证容噪分类算法,应用在数据流环境里,进一步提高了集成分类模型对噪音数据流的分类能力。
其次,针对高速数据流数据到达速度远远超过处理器的处理能力,处理器无法利用全部数据训练个体分类器的问题,提出一种基于偏倚抽样的高速数据流集成分类器算法。抽样技术可以有效缩减待处理的数据规模,减少集成分类器的训练和更新时间,由于不同的抽样策略产生的训练数据集,建立集成分类器,其分类准确率具有明显区别。因此本文通过集成分类器期望错误的偏差方差分解,计算各个待抽样数据的期望错误贡献度,并通过集成分类器分类性能的几何分析,说明抽取期望错误贡献度大的数据作为训练数据更新集成分类器模型,可以有效提高集成分类器的分类准确率,并依此提出了基于偏倚抽样的高速数据流集成分类器算法。
再次,针对数据流中数据类标签难以全部获得的问题,提出一种基于聚类假设的半监督数据流集成分类器算法。传统半监督分类算法虽然能够解决类标签不完整数据集的分类问题,但如何将其引入数据流环境,利用数据流特性提高半监督分类算法的分类准确率仍是一个有待解决的问题。本文通过基于聚类假设的半监督分类算法分类误差分析,表明在训练个体分类器时增加有标签数据集的规模可以有效减少分类算法的分类误差,并利用此结论,提出了基于聚类假设的半监督数据流集成分类器算法。
最后,针对选择性集成分类算法训练一旦结束,被选择的个体分类器组合就以确定,无法针对具体数据进行动态调整的问题,提出一种两阶段数据流选择性集成分类器算法。本文首先通过分析说明,选择性集成分类算法获得的个体分类器集合,虽然在整体数据集上具有最优的分类性能,但对某具体数据分类时,并不一定是最优的个体分类器组合。因此,利用支持向量数据描述算法,动态自适应选择数据分类时的个体分类器集合,可以有效避免上述情况的发生,提高选择性集成分类器的分类性能。
With the development and application of information technology, people can collect lots of high-speed, dynamic and continuous information, such as sensors network data, telephone records, financial data and commercial transaction data etc. Traditional static data set s the information carrier has already been unable to efficiently express such information a. Therefore data stream as a kind of new data type is put forward and widely used in the above fields. Data stream is a kind of orderly data sequences which can continuously arrive in and potentially infinitely be input in. Compared with the traditional static data set, data stream has the following features:(1) Data reach with rapid speed. (2) Large-scale data. (3) Data stream is orderly sequences. (4) Data stream can dynamic change. (5) Data stream often is high-dimensional. The above features let data stream cannot be delt with effectively by the traditional data mining classification algorithm.So the research of data stream mining algorithm become one of the hot spots in the data mining area.
We focused on classifying data stream using ensemble classifiers in this paper. From two aspects of training individual classifier and integrating classified outcome, we studied noisy data stream, high speeding data stream and data stream without complete label. Main job is as follows:
First of all, aiming at the promble of ensemble classifiers classification accuracy is influenced seriously by noise which is trained by noisy data set, a cross validation noise-tolerance data stream ensemble classifiers algorithm was proposed. Cross validation noise-tolerance classification algorithm is an important method which eliminates noise of data set. That can eliminates noise of training data set before training classifier, So classifier classification accuracy be able to increased significantly. However, there have been not scholars to prove it validity in theory. According to sample complexity theory of noisy data set, algorithm validity was proved in this paper. And according to outcome of proving, a new Cross validation noise-tolerance classification algorithm which deal with data stream was proposed. It can further increase classification accuracy of classifier which deal with noisy data set.
Secondly, aiming at high speed data stream existing the phenomenon that the data rate is higher relative to the ensemble classifiers'computational power, so ensemble classifiers can't train all data to update themselves. An ensemble classifiers based on biased sample was proposed. Sampling technique can effectively reduce to data scale, so it can decrease time of training and updating ensemble classifiers. However, training differnet ensemble classifiers using data set produced by different sampling strategy, their classification performance has obvious difference. Therefore, by means of expectation error bias variance decomposition method, computing all data's expectation error contribution degree which waited for being sampled. And through geometric analysis of ensemble classifiers classification performance, it be proved that using data which have bigger expectation error contribution degree to train ensemble classifiers, the ensemble classifiers have more classification accuracy. According to that an ensemble classifiers algorithm based on biased sample was proposed in this paper.
Further, aiming at the promble that it is hardly to label all data in data stream, a semi-supervised data stream ensemble classifiers algorithm based on cluster assumption was proposed. Although traditional semi-supervised classification algorithm can solve incomplete label data sets classification problem, but it is an unsolved problem that how to use it in data stream environment and how to improve semi-supervised classification algorithm accuracy by using data stream characters. According to analyzing generalization of semi-supervised classifier based on cluster assumption, it indicates that increasing labeled data during training moment can improve semi-supervised classifier accuracy. Making use of this conclusion, a semi-supervised data stream ensemble classifiers algorithm based on cluster assumption was proposed.
Finally, aiming at the promble that after training in selective ensemble classifiers, it is determined which individual classifier be selected and be unable to dynamicly adjust with specific data. Two-phase selective ensemble classifiers algorithm of data sreams was presented. Through the analysis it is indicated that individual classifiers be selected by selective ensemble algorithm can have best Classification performance in whole data set, but they may be not optimal combination of individual classifiers to classify specific data. Hence, Dynamic adaptive choosing individual classifiers by Using support vector data description algorithm can Effectively prevent this situations and Improving selective ensemble classifiers classification performance.
引文
[1]Fayyad U, Piatetsky S, Smyth P, et al. Advances in knowledge discovery and data mining, MIT Press,1996.
[2]Quinlan J R. Induction of decision trees. Machine Learning,1986,1(1):81-106P.
[3]Quinlan J R. C4.5:Programs for machine learning. San Mateo, California:Morgan Kaufmann,1993.
[4]Kuncheva L I. Editing for the k-nearest neighbors rule by a genetic. Pattern Recognition Letters,1995,16(8):809-814P.
[5]Shafer J C, Agrawal R, Mehta M. SPRINT:A scalable parallel classifier for data mining. In Proceeding of the 22nd International conference on very large databases. USA:San Francisco,1996.
[6]Friedman N, Geiger D, Goldszmidt M. Bayesian network classifier. Machine Learning,1997,29(1):131-163P.
[7]Michie D, Spiegelhalter D J. Machine learning, neural and stastical classification. Ellis Horwood Upper Saddle River, NJ, USA Press,1994.
[8]Scholkopf B, Burges C J C, Smola A J, et al. Advances in kernel methods:support vector learning. MIT Press, Cambridge, MA,1999.
[9]HALL P. On projection pursuit regression. Annals of statistics,1989,17(2): 573-588P.
[10]付强,赵小勇.投影寻踪模型原理及其应用.北京：科学出版社,2006.
[11]Kaufman L, Rousseeuw P J. Finding groups in data:an introduction to cluster analysis. Applied Probability and Statistics,1990.
[12]Wei Wang, Jiong Yang, Richard Muntz. STING:A statistical information grid approach to spatial data mining. In Proceeding of the 23 th international conference on very large data bases,1997.
[13]Sheikholeslami G, Chatterjee S, Zhang A. Wavecluster:a multiresolution clustering approach for very large spatial databases.In Proceedings of the 24th conference on very large data bases. NY,1998:428-439P.
[14]孙吉贵,刘杰,赵连宇.聚类算法研究.软件学报,2008,19(1)：48-61页.
[15]W Li, K. NG Wee, H. D. Xuan, et al. Density-based clustering of data streams at multiple resolutions. ACM Transactions on Knowledge Discovery from Data,2009, 3(3):14-42P.
[16]Verikas A, Baeauskiene M. Feature Selection with Neural Networks. Pattern Reeognition Letters,2002,3(11):1323-1335P.
[17]Sindhwani V, Rakshit S, Deodhare D, et al. Feature Seleetion in MLPs and SVMs Based on maximum output information. IEEE Trans on Neural Networks,2004, 15(4):937-948P.
[18]孙平,徐宗本,申建中.基于核化原理的非线性典型相关判别分析.计算机学报,2004,27(6)：789-795页.
[19]孙权森,曾生根,王平安等.典型相关分析的理论及其在特征融合中的应用.计算机学报,2005,28(9)：1524-1533页.
[20]Agrawal R, Srikant R. Fast algorithm for mining association rules in large databases. Proceedings of the 21th International Conference on Very Large Data Bases. San Francisco, CA,1994.
[21]Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation:A frequent-pattern tree approach. Data mining and knowledge discovery,2004, 8(1):53-87P.
[22]沙宗尧,李晓雷.异质环境下的空间关联规则挖掘.武汉大学学报,2009,34(12)：1481-1484页.
[23]吕志军,王照飞,谢福鼎等.基于F C M聚类的时间序列模糊关联规则挖掘.大连理工大学学报,2010,50(5)：806-810页.
[24]张玉芳,熊忠阳,王灿等.含正负项目的基于位串频繁项集挖掘算法究.控制与决策,2010,25(1)：37-42页.
[25]Knorr E M, NgR T. Algorithms for Mining Distance-based Outliers in Large Datasets. NewYork:Proceeding of the International conference on very large databases,1998:392-403P.
[26]Amidan B G, Ferryman T A, Cooley S K. Data outlier detection using the Chebyshev theorem. Aerospace,2005 IEEE Conference,2005:3814-3819P.
[27]Pei Y L, Zaiane O R, Gao Y. An efficient reference-based approach to outlier detection in large datasets.In Proceedings of the Sixth International Conference on Data Mining. IEEE Computer Society Washington, DC,2006:478-487P.
[28]江峰,杜军威,眭跃飞等.基于边界和距离的离群点检测.电子学报,2010,38(3)：700-705页.
[29]胡彩平,秦小麟.一种基于密度的局部离群点检测算法DLOF.计算机研究与发展,2010,47(12)：2110-2116页.
[30]Bonnet P. Towards sensor database systems. Proceeding of the 2nd International Conference on Mobile Data Management. HongKong,2001:3-14P.
[31]Chen J, Dewitt D.Niagara C Q. A scalable continuousquery system for intemet datahases. Proceeding of the ACM International Conference on Management of Data. New York:ACM Press,2000:379-390P.
[32]Lilian H. Detection of complex temporal Patterns over data streams. Information Systems,2004,29(6):439-59P.
[33]Zhu Y, Shasha D. Statstream:Statistical monitoring of thousands of data streams in real time. Proceeding of the International conference on very large databases,2002.
[34]Guha S, Mishra N, Motwani R, et al. Clustering data streams. In Proceeding of IEEE Symposium on Foundations of ComPuter Science,2000:359-366 P.
[35]Domingos P, Hulten G. A general method for scaling up machine learning algorithms and its application to clustering. Proceedings of the 18th International Conference on Machine Learning,2001:106-113 P.
[36]Aggarwal C C, Han J, Wang J, et al. A framework for projected clustering of high dimensional data streams. In Proceeding of the 30th VLDB Conference. Toronto, Canada,2004:852-863P.
[37]Park N H, Lee W S. Statistical Grid-based clustering over data streams. ACM SIGMOD Record,2004,33(1):32-37P.
[38]Cao F, Ester M, Qian W, et al. A density-based clustering over an evolving data stream with noise. Proceedings of the 6th International Conference on data minging, 2006:326-337P.
[39]Chen Y X, Tu L. Density-based clustering for real-time stream data.In Proceedings of the 13th ACM SIGKDD international conference on Knowledge Discovery and Data Mining.California, ACM,2007:133-142.
[40]于翔,印桂生.数据流的不规则网格增量聚类算法.哈尔滨工程大学学报,2008,29(8)：846-850页.
[41]陈华辉,施伯.基于随机投影的并行数据流聚类方法.模式识别与人工智能,2009,22(1)：113-121页.
[42]杨宁,唐常杰,王悦等.一种基于时态密度的倾斜分布数据流聚类算法.软件学报,2010,21(5)：1031-1041页.
[43]Manku G, Motwani R. Approximate frequency counts over data streams. In: Proceeding of the 28th International Conference on very large data bases. Hong Kong, China:Morgan Kanfmann,2002:346-357P.
[44]Giannella C, HAN Jiawei, JIAN Pei, et al. Mining frequent patterns in data streams at multiple time granularities. Proceeding of the NSF Workshop on next generation data mining,2003.
[45]刘旭,毛国君,孙岳.数据流中频繁闭项集的近似挖掘算法.电子学报,2007,35(5)：900-905页.
[46]刘春,郑征,蔡开元等.数据流频繁闭集的在线挖掘.北京航空航天大学学报,2008,34(8)：969-972页.
[47]敖富江,颜跃进,刘宝宏等.在线挖掘数据流滑动窗口中最大频繁项集.系统仿真学报,2009,21(4)：1134-1139页.
[48]张蕊.基于数据流的top-k频繁项集挖掘.武汉理工大学学报,2009,31(3)：87-90页.
[49]杨蓓,黄厚宽.挖掘数据流界标窗口Top-K频繁项集.计算机研究与发展,2010,47(3)：463-473页.
[50]Kenji Yamanishi, Jun-ichi Takeuchi. A unifying framework for detecting outliers and change points from non-stationary time series data. Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. Edmonton, Alberta, Canada,2002.
[51]Muthukrishnan S, Shah R, Vitter J S. Mining deviants in time series data streams. Proceedings of the 16th International Conference on Scientific and Statistical Database Management. Rutgers Univ., Piscataway, NJ, USA,2004.
[52]Feng Han, Yan Ming Wang, Hua Peng Wang. Odabk:An Effective Approach to Detecting Outlier in Data Stream.2006 International Conference on Machine Learning and Cybernetics. DaLian,2006.
[53]周晓云,孙志挥,张柏礼等.高维类别属性数据流离群点快速检测算法.软件 学报,2007,18(4)：933-942页.
[54]张忠平,梁永欣.基于反k近邻的流数据离群点挖掘算法.计算机工程,2009,35(12)：11-13页.
[55]唐向红,李国徽,杨观赐.快速挖掘数据流中离群点.小型微型计算机系统,2011,32(1)：9-16页.
[56]Domingos P, Hulten G Mining high-speed data streams. The Assoiciation for Computing Machinery 6th Int'l Conf on Knowledge Discovery and Data Minings. Boston,2000.
[57]Gama J, Rocha R, Medas P. Accurate decision trees for mining high-speed data streams. Proceeding of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, ACM Press,2003.
[58]Jin R, Agrawal G Efficient decision tree construction on streaming data. The ACM SIGKDD 9th International Conference on Knowledge Discovery and Data Mining. Washington,2003.
[59]Widmer G, Kubat M. Learning in the presence of concept drift and hidden contexts. Machine Learning,1996,23(1):69-101P.
[60]Hulten G, Spencer L, Domingos P. Mining time-changing data strems. The ACM International Conference on Knowledge Discovery and Data Mining, San Francisco,2001.
[61]王鹏,吴晓晨,王晨等CAPE——数据流上的基于频繁模式的分类算法.计算机研究与发展,2004,41(10)：1677-1683页.
[62]吴俊杰,陈剑SCBA基于演变的规则知识库的数据流分类模型.清华大学学报(自然科学版),2006,46(s1)：1078-1084页.
[63]Valiant L. A theory of learnability. Communication ACM,1984,27:1134-1142P.
[64]Kearns M, Vazirani U. An introduction to computational learning theory. Cambridge, MA:The MIT Press,1994.
[65]Street W N, Kim Y S. A streaming ensemble algorithm for large-scale classification. Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining. San Francisco, ACM,2001:377-382P.
[66]Wang H, Fan W, Yu P S, et al. Mining concept-drifting data stream using ensemble classifiers Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. Washington, D.C, ACM,2003:226-235P.
[67]Wei Fan. Systematic data selection to mine concept-drifting data streams. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. NY, ACM,2004.
[68]Chu F, Zaniolo C. Fast and light boosting for adaptive mining of data streams. Pacific-Asia conference on advances in knowledge discovery and data mining. Sydney:Springer Verlag,2004:282-292P.
[69]王勇,李战怀,张阳等.基于相反分类器的数据流分类方法.计算机科学,2006,33(8)：206-209页.
[70]王勇,李战怀,张阳等.一种对噪音健壮的数据流分类算法.西北工业大学学报,2007,25(4)：603-607页.
[71]孙岳,毛国君,刘旭等.基于多分类器的数据流中的概念漂移挖掘.电子学报,2008,34(1)：93-97页.
[72]Zhang Peng, Zhu Xingquan, Shi Yong. Categorizing and Mining Concept Drifting Data Streams. Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. NY, ACM,2008.
[73]欧阳震诤,罗建书,胡东敏等.一种不平衡数据流集成分类模型.电子学报,2010,38(1)：184-189页.
[74]Aggarwal C C, Han J, Wang J, et al. A framework for Projceted clustering of high dimensional data streams. Proceeding.of the 30th Conference.on Very Large DataBases (VLDB'04),2004:852-863P.
[75]Vitter J S. Random sampling with a reservoir. ACMTrans. On Mathematical Software,1985,11(1):37-57P.
[76]Gibbons P B, Matias Y. New sampling-based summary statistics for improving approximate query answers. Proceeding.of SIGMOD,1998:331-342P.
[77]Greenwald M, Khanna S. Space-efficient online computation of Quantile summaries. Proceeding of SIGMOD,2001:58-66P.
[78]Ioannidis Y, Poosala V. Balancing histogram optimality Practicality for query result size estimation. Proceeding.of SIGMOD,1995:233-244P.
[79]Poosala V, Ioannidis Y, Haas P, et al. Improved histograms for selectivity estimation of range Predieates. Proceeding of the 1996 ACM-SIGMOD international conference,1996:294-30P.
[80]Cao F, Ester M, Qian W, et al. Density-based clustering over an evolving data stream with noise. Proceeding.of the SIAM conference on DataMing,2006: 326-337P.
[81]Han J, Kamber M. Data Mining:Concepts and Techniques (Seeond Edition). Morgan Kaufmann, Elsevier Inc,2006:467-589P.
[82]Gilbert A, Kotidis Y, Muthukrishnan S, et al. Surfind wavelets on streams:one Pass summaries for approximate aggregate queries. VLDB Journal,2001,79(8):79-88P
[83]Jawerth B, Sweldens W. An overview of Waveletbased multiresolution analysis. SIAM Reve,1994,36(3):377-412P.
[84]Vitter J S, Wang M, Lyer B. Data cube approximation and Histograms via wavelets. Proceeding of CIKM,1998.
[85]Vitter J S, Wang M. Approxlinate computation of multidimensional aggregates of sparse data using wavelets. Proceeding of the 2002 ACM-SIGMOD international conference Management of Data,1999.
[86]Dietterich T D. Ensemble Methods in Machine Learning. In Proceedings of MCS, LNCS, Springer,2000:1-15P.
[87]Schapire R E. The strength of weak learnability. Machine Learning,1990,5(2): 197-227P.
[88]Freund Y. Boosting a Weak Algorithm by Majority. Information and Computation, 1995,121(2):256-285P.
[89]Freund Y, Schapire R E. A decision-the oretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences,1997, 55(1):119-139P.
[90]Schapire R, Freund Y, Bartlett P, et al. Boosting the margin:A new explanation for the effectivness of voting methods. The Annals of Statistics,1998,26:1651-1686P
[91]Breiman L. Prediction games and arcing algorithms. Neural computation,1999,11: 1493-1517P.
[92]Wang L, Sugiyama M, Yang C, et al. On the margin explanation of boosting algorithms. In:21st Annual Conference on Learning Theory (COLT),2008.
[93]Schapire R E, Singer Y. Boostexter:a boosting-based system for text categorization, Machine Learning,2000,39(2/3):135-68P.
[94]NikunjChandrakant Oza. Online Ensemble Learning. Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence,2000.
[95]F d'Alche Buc, Grandvalet Y, Ambroise C. Semi-supervised marginboost, in Advances in Neural Information Processing Systems,2002,14:553-560P.
[96]Breiman L. Bagging Predictors. Machine Learning,1996,24(2):123-140P.
[97]Friedman J H, Hall P. On bagging and non-linear estimation. Technical Report, Stanford University, Stanford, CA,2000.
[98]Buhlmann P, Yu B. Explaining Bagging. Technical Report 92, Seminar fur Statistik, ETH, Zurich,2000.
[99]BUHLMANN Peter, Bin Yu. Analyzing bagging. Annals of statistics,2002,30(4): 927-961P.
[100]付忠良.关于AdaBoost有效性分析.计算机研究与发展,2008,45(10)：1747-1755页.
[101]Opitz D W. Feature selection for ensembles. Proceedings of the sixteenth international conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence,1999:379-384P.
[102]Bryll R, Gutierrez-Osuna R, Quek F. Attribute bagging:improving accuracy of classifier ensembles by using random feature subsets. Pattern Recognition 2003, 36(6):1291-1302P.
[103]Grigorios Tsoumakas, Ioannis Vlahavas. Random k-Labelsets:An Ensemble Method for Multilabel Classication. ECML'07 Proceedings of the 18th European conference on Machine Learning,2007:406-417P.
[104]Zhou Z H, Wu J, Tang W. Ensembling neural networks:Many could be better than all. Artificial Intelligence,2002,137(1-2):239-263P.
[105]李凯,黄厚宽.一种基于聚类技术的选择性神经网络集成方法.计算机研究与发展,2005,42(4)：594-598页.
[106]赵胜颖,高广春.基于蚁群算法的选择性神经网络集成方法.浙江大学学报(工学版),2009,43(9)：1568-1573页.
[107]李文斌,刘椿年,钟宁.基于两阶段集成学习的分类器集成.北京工业大学学报,2010,36(3)：410-419页.
[108]Shen D, Yang Q, Chen Z. Noise reduction through summarization for web-page classification. Information processing and management,2007,43(6):173-174P.
[109]Wu X D, Zhu X Q. Mining with noise knowledge:error aware data mining. IEEE Transactions on Systems Man and Cybernetics,2008,38(4):917-932P.
[110]Angluinand D, Laird P. Learning from noisy examples. Machine Learning.1988, 2(4):343-370P.
[111]John G. H. Robust Decision Trees:Removing Outliers from Databases. Proceedings of the First International Conference on Knowledge Discovery and Data Mining, Menlo Park, CA,1995:174-179P.
[112]Gamgerber D, Lavrac N, Groselj C. Experiments with noise filtering in a medical domain. Proceedings of the Sixteenth International Conference on Machine Learning, San Francisco,1999:143-151P.
[113]Zhu X Q, Wu X D, Chen Q J. Eliminating class noise in large datasets. Proceedings of the Twentieth International Conference on Machine Learning, Washington DC, 2003:920-927P.
[114]Sofie V, Anneleen V A. Ensemble methods for noise elimination in classification problems. Fourth Workshop on Multiple Classifier Systems, United Kingdom,2003: 317-325P.
[115]Tumer K, Ghosh J. Analysis of decision boundaries in linearly combined neural classifiers. Pattern Recognition,1996,29(2).
[116]Tumer K, Ghosh J. Error correlation and error reduction in ensemble classifiers. Connection Science,1996,8(3-4):385-403P.
[117]Shahshahan B, Landgrebe D. The effect of unlabeled samples in reducing the small sample size problem and mitigating the hughes phenomenon. IEEE Transactions on Geoscience and Remote Sensing,1994,32(5):1087-1095P.
[118]黄树成,朱宇光,董逸生.基于半监督学习的数据流分类方法.计算机研究与发展,2007,44：225--229页.
[119]Miller D J, Uyar H S. A minture of experts classifier with learning based on both labelled and unlabelled data. Advances in Neural Information Processing Systems9, Cambridge, MA:MIT press,1997:571-577P.
[120]Rigollet P. Generalization error bounds in semi-supervised classification under the cluster assumption. The Journal of Machine Learning Research,2007,8: 1369-1392P.
[121]Devroye L. A probabilistic theory of pattern recognition. Springer-Verlag, New York, 1996.
[122]周志华,王珏.机器学习及其应用2007.北京：清华大学出版社,2007.
[123]Chapelle O, Zien A. Semi-supervised classification by low density separation. Proceedings of the tenth international workshop on artificial intelligence and statistics,2005.
[124]谢元澄,杨静宇.删除最差基学习器来层次修剪Bagging集成.计算机研究与发展,2009,46(2)：261-267页.
[125]Tax D, Duin R. Support vector domain description. Pattern Recognition Letters, 1999,20(11-13):1191-1199P
[2]Quinlan J R. Induction of decision trees. Machine Learning,1986,1(1):81-106P.
[3]Quinlan J R. C4.5:Programs for machine learning. San Mateo, California:Morgan Kaufmann,1993.
[4]Kuncheva L I. Editing for the k-nearest neighbors rule by a genetic. Pattern Recognition Letters,1995,16(8):809-814P.
[5]Shafer J C, Agrawal R, Mehta M. SPRINT:A scalable parallel classifier for data mining. In Proceeding of the 22nd International conference on very large databases. USA:San Francisco,1996.
[6]Friedman N, Geiger D, Goldszmidt M. Bayesian network classifier. Machine Learning,1997,29(1):131-163P.
[7]Michie D, Spiegelhalter D J. Machine learning, neural and stastical classification. Ellis Horwood Upper Saddle River, NJ, USA Press,1994.
[8]Scholkopf B, Burges C J C, Smola A J, et al. Advances in kernel methods:support vector learning. MIT Press, Cambridge, MA,1999.
[9]HALL P. On projection pursuit regression. Annals of statistics,1989,17(2): 573-588P.
[10]付强,赵小勇.投影寻踪模型原理及其应用.北京：科学出版社,2006.
[11]Kaufman L, Rousseeuw P J. Finding groups in data:an introduction to cluster analysis. Applied Probability and Statistics,1990.
[12]Wei Wang, Jiong Yang, Richard Muntz. STING:A statistical information grid approach to spatial data mining. In Proceeding of the 23 th international conference on very large data bases,1997.
[13]Sheikholeslami G, Chatterjee S, Zhang A. Wavecluster:a multiresolution clustering approach for very large spatial databases.In Proceedings of the 24th conference on very large data bases. NY,1998:428-439P.
[14]孙吉贵,刘杰,赵连宇.聚类算法研究.软件学报,2008,19(1)：48-61页.
[15]W Li, K. NG Wee, H. D. Xuan, et al. Density-based clustering of data streams at multiple resolutions. ACM Transactions on Knowledge Discovery from Data,2009, 3(3):14-42P.
[16]Verikas A, Baeauskiene M. Feature Selection with Neural Networks. Pattern Reeognition Letters,2002,3(11):1323-1335P.
[17]Sindhwani V, Rakshit S, Deodhare D, et al. Feature Seleetion in MLPs and SVMs Based on maximum output information. IEEE Trans on Neural Networks,2004, 15(4):937-948P.
[18]孙平,徐宗本,申建中.基于核化原理的非线性典型相关判别分析.计算机学报,2004,27(6)：789-795页.
[19]孙权森,曾生根,王平安等.典型相关分析的理论及其在特征融合中的应用.计算机学报,2005,28(9)：1524-1533页.
[20]Agrawal R, Srikant R. Fast algorithm for mining association rules in large databases. Proceedings of the 21th International Conference on Very Large Data Bases. San Francisco, CA,1994.
[21]Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation:A frequent-pattern tree approach. Data mining and knowledge discovery,2004, 8(1):53-87P.
[22]沙宗尧,李晓雷.异质环境下的空间关联规则挖掘.武汉大学学报,2009,34(12)：1481-1484页.
[23]吕志军,王照飞,谢福鼎等.基于F C M聚类的时间序列模糊关联规则挖掘.大连理工大学学报,2010,50(5)：806-810页.
[24]张玉芳,熊忠阳,王灿等.含正负项目的基于位串频繁项集挖掘算法究.控制与决策,2010,25(1)：37-42页.
[25]Knorr E M, NgR T. Algorithms for Mining Distance-based Outliers in Large Datasets. NewYork:Proceeding of the International conference on very large databases,1998:392-403P.
[26]Amidan B G, Ferryman T A, Cooley S K. Data outlier detection using the Chebyshev theorem. Aerospace,2005 IEEE Conference,2005:3814-3819P.
[27]Pei Y L, Zaiane O R, Gao Y. An efficient reference-based approach to outlier detection in large datasets.In Proceedings of the Sixth International Conference on Data Mining. IEEE Computer Society Washington, DC,2006:478-487P.
[28]江峰,杜军威,眭跃飞等.基于边界和距离的离群点检测.电子学报,2010,38(3)：700-705页.
[29]胡彩平,秦小麟.一种基于密度的局部离群点检测算法DLOF.计算机研究与发展,2010,47(12)：2110-2116页.
[30]Bonnet P. Towards sensor database systems. Proceeding of the 2nd International Conference on Mobile Data Management. HongKong,2001:3-14P.
[31]Chen J, Dewitt D.Niagara C Q. A scalable continuousquery system for intemet datahases. Proceeding of the ACM International Conference on Management of Data. New York:ACM Press,2000:379-390P.
[32]Lilian H. Detection of complex temporal Patterns over data streams. Information Systems,2004,29(6):439-59P.
[33]Zhu Y, Shasha D. Statstream:Statistical monitoring of thousands of data streams in real time. Proceeding of the International conference on very large databases,2002.
[34]Guha S, Mishra N, Motwani R, et al. Clustering data streams. In Proceeding of IEEE Symposium on Foundations of ComPuter Science,2000:359-366 P.
[35]Domingos P, Hulten G. A general method for scaling up machine learning algorithms and its application to clustering. Proceedings of the 18th International Conference on Machine Learning,2001:106-113 P.
[36]Aggarwal C C, Han J, Wang J, et al. A framework for projected clustering of high dimensional data streams. In Proceeding of the 30th VLDB Conference. Toronto, Canada,2004:852-863P.
[37]Park N H, Lee W S. Statistical Grid-based clustering over data streams. ACM SIGMOD Record,2004,33(1):32-37P.
[38]Cao F, Ester M, Qian W, et al. A density-based clustering over an evolving data stream with noise. Proceedings of the 6th International Conference on data minging, 2006:326-337P.
[39]Chen Y X, Tu L. Density-based clustering for real-time stream data.In Proceedings of the 13th ACM SIGKDD international conference on Knowledge Discovery and Data Mining.California, ACM,2007:133-142.
[40]于翔,印桂生.数据流的不规则网格增量聚类算法.哈尔滨工程大学学报,2008,29(8)：846-850页.
[41]陈华辉,施伯.基于随机投影的并行数据流聚类方法.模式识别与人工智能,2009,22(1)：113-121页.
[42]杨宁,唐常杰,王悦等.一种基于时态密度的倾斜分布数据流聚类算法.软件学报,2010,21(5)：1031-1041页.
[43]Manku G, Motwani R. Approximate frequency counts over data streams. In: Proceeding of the 28th International Conference on very large data bases. Hong Kong, China:Morgan Kanfmann,2002:346-357P.
[44]Giannella C, HAN Jiawei, JIAN Pei, et al. Mining frequent patterns in data streams at multiple time granularities. Proceeding of the NSF Workshop on next generation data mining,2003.
[45]刘旭,毛国君,孙岳.数据流中频繁闭项集的近似挖掘算法.电子学报,2007,35(5)：900-905页.
[46]刘春,郑征,蔡开元等.数据流频繁闭集的在线挖掘.北京航空航天大学学报,2008,34(8)：969-972页.
[47]敖富江,颜跃进,刘宝宏等.在线挖掘数据流滑动窗口中最大频繁项集.系统仿真学报,2009,21(4)：1134-1139页.
[48]张蕊.基于数据流的top-k频繁项集挖掘.武汉理工大学学报,2009,31(3)：87-90页.
[49]杨蓓,黄厚宽.挖掘数据流界标窗口Top-K频繁项集.计算机研究与发展,2010,47(3)：463-473页.
[50]Kenji Yamanishi, Jun-ichi Takeuchi. A unifying framework for detecting outliers and change points from non-stationary time series data. Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. Edmonton, Alberta, Canada,2002.
[51]Muthukrishnan S, Shah R, Vitter J S. Mining deviants in time series data streams. Proceedings of the 16th International Conference on Scientific and Statistical Database Management. Rutgers Univ., Piscataway, NJ, USA,2004.
[52]Feng Han, Yan Ming Wang, Hua Peng Wang. Odabk:An Effective Approach to Detecting Outlier in Data Stream.2006 International Conference on Machine Learning and Cybernetics. DaLian,2006.
[53]周晓云,孙志挥,张柏礼等.高维类别属性数据流离群点快速检测算法.软件 学报,2007,18(4)：933-942页.
[54]张忠平,梁永欣.基于反k近邻的流数据离群点挖掘算法.计算机工程,2009,35(12)：11-13页.
[55]唐向红,李国徽,杨观赐.快速挖掘数据流中离群点.小型微型计算机系统,2011,32(1)：9-16页.
[56]Domingos P, Hulten G Mining high-speed data streams. The Assoiciation for Computing Machinery 6th Int'l Conf on Knowledge Discovery and Data Minings. Boston,2000.
[57]Gama J, Rocha R, Medas P. Accurate decision trees for mining high-speed data streams. Proceeding of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, ACM Press,2003.
[58]Jin R, Agrawal G Efficient decision tree construction on streaming data. The ACM SIGKDD 9th International Conference on Knowledge Discovery and Data Mining. Washington,2003.
[59]Widmer G, Kubat M. Learning in the presence of concept drift and hidden contexts. Machine Learning,1996,23(1):69-101P.
[60]Hulten G, Spencer L, Domingos P. Mining time-changing data strems. The ACM International Conference on Knowledge Discovery and Data Mining, San Francisco,2001.
[61]王鹏,吴晓晨,王晨等CAPE——数据流上的基于频繁模式的分类算法.计算机研究与发展,2004,41(10)：1677-1683页.
[62]吴俊杰,陈剑SCBA基于演变的规则知识库的数据流分类模型.清华大学学报(自然科学版),2006,46(s1)：1078-1084页.
[63]Valiant L. A theory of learnability. Communication ACM,1984,27:1134-1142P.
[64]Kearns M, Vazirani U. An introduction to computational learning theory. Cambridge, MA:The MIT Press,1994.
[65]Street W N, Kim Y S. A streaming ensemble algorithm for large-scale classification. Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining. San Francisco, ACM,2001:377-382P.
[66]Wang H, Fan W, Yu P S, et al. Mining concept-drifting data stream using ensemble classifiers Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. Washington, D.C, ACM,2003:226-235P.
[67]Wei Fan. Systematic data selection to mine concept-drifting data streams. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. NY, ACM,2004.
[68]Chu F, Zaniolo C. Fast and light boosting for adaptive mining of data streams. Pacific-Asia conference on advances in knowledge discovery and data mining. Sydney:Springer Verlag,2004:282-292P.
[69]王勇,李战怀,张阳等.基于相反分类器的数据流分类方法.计算机科学,2006,33(8)：206-209页.
[70]王勇,李战怀,张阳等.一种对噪音健壮的数据流分类算法.西北工业大学学报,2007,25(4)：603-607页.
[71]孙岳,毛国君,刘旭等.基于多分类器的数据流中的概念漂移挖掘.电子学报,2008,34(1)：93-97页.
[72]Zhang Peng, Zhu Xingquan, Shi Yong. Categorizing and Mining Concept Drifting Data Streams. Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. NY, ACM,2008.
[73]欧阳震诤,罗建书,胡东敏等.一种不平衡数据流集成分类模型.电子学报,2010,38(1)：184-189页.
[74]Aggarwal C C, Han J, Wang J, et al. A framework for Projceted clustering of high dimensional data streams. Proceeding.of the 30th Conference.on Very Large DataBases (VLDB'04),2004:852-863P.
[75]Vitter J S. Random sampling with a reservoir. ACMTrans. On Mathematical Software,1985,11(1):37-57P.
[76]Gibbons P B, Matias Y. New sampling-based summary statistics for improving approximate query answers. Proceeding.of SIGMOD,1998:331-342P.
[77]Greenwald M, Khanna S. Space-efficient online computation of Quantile summaries. Proceeding of SIGMOD,2001:58-66P.
[78]Ioannidis Y, Poosala V. Balancing histogram optimality Practicality for query result size estimation. Proceeding.of SIGMOD,1995:233-244P.
[79]Poosala V, Ioannidis Y, Haas P, et al. Improved histograms for selectivity estimation of range Predieates. Proceeding of the 1996 ACM-SIGMOD international conference,1996:294-30P.
[80]Cao F, Ester M, Qian W, et al. Density-based clustering over an evolving data stream with noise. Proceeding.of the SIAM conference on DataMing,2006: 326-337P.
[81]Han J, Kamber M. Data Mining:Concepts and Techniques (Seeond Edition). Morgan Kaufmann, Elsevier Inc,2006:467-589P.
[82]Gilbert A, Kotidis Y, Muthukrishnan S, et al. Surfind wavelets on streams:one Pass summaries for approximate aggregate queries. VLDB Journal,2001,79(8):79-88P
[83]Jawerth B, Sweldens W. An overview of Waveletbased multiresolution analysis. SIAM Reve,1994,36(3):377-412P.
[84]Vitter J S, Wang M, Lyer B. Data cube approximation and Histograms via wavelets. Proceeding of CIKM,1998.
[85]Vitter J S, Wang M. Approxlinate computation of multidimensional aggregates of sparse data using wavelets. Proceeding of the 2002 ACM-SIGMOD international conference Management of Data,1999.
[86]Dietterich T D. Ensemble Methods in Machine Learning. In Proceedings of MCS, LNCS, Springer,2000:1-15P.
[87]Schapire R E. The strength of weak learnability. Machine Learning,1990,5(2): 197-227P.
[88]Freund Y. Boosting a Weak Algorithm by Majority. Information and Computation, 1995,121(2):256-285P.
[89]Freund Y, Schapire R E. A decision-the oretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences,1997, 55(1):119-139P.
[90]Schapire R, Freund Y, Bartlett P, et al. Boosting the margin:A new explanation for the effectivness of voting methods. The Annals of Statistics,1998,26:1651-1686P
[91]Breiman L. Prediction games and arcing algorithms. Neural computation,1999,11: 1493-1517P.
[92]Wang L, Sugiyama M, Yang C, et al. On the margin explanation of boosting algorithms. In:21st Annual Conference on Learning Theory (COLT),2008.
[93]Schapire R E, Singer Y. Boostexter:a boosting-based system for text categorization, Machine Learning,2000,39(2/3):135-68P.
[94]NikunjChandrakant Oza. Online Ensemble Learning. Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence,2000.
[95]F d'Alche Buc, Grandvalet Y, Ambroise C. Semi-supervised marginboost, in Advances in Neural Information Processing Systems,2002,14:553-560P.
[96]Breiman L. Bagging Predictors. Machine Learning,1996,24(2):123-140P.
[97]Friedman J H, Hall P. On bagging and non-linear estimation. Technical Report, Stanford University, Stanford, CA,2000.
[98]Buhlmann P, Yu B. Explaining Bagging. Technical Report 92, Seminar fur Statistik, ETH, Zurich,2000.
[99]BUHLMANN Peter, Bin Yu. Analyzing bagging. Annals of statistics,2002,30(4): 927-961P.
[100]付忠良.关于AdaBoost有效性分析.计算机研究与发展,2008,45(10)：1747-1755页.
[101]Opitz D W. Feature selection for ensembles. Proceedings of the sixteenth international conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence,1999:379-384P.
[102]Bryll R, Gutierrez-Osuna R, Quek F. Attribute bagging:improving accuracy of classifier ensembles by using random feature subsets. Pattern Recognition 2003, 36(6):1291-1302P.
[103]Grigorios Tsoumakas, Ioannis Vlahavas. Random k-Labelsets:An Ensemble Method for Multilabel Classication. ECML'07 Proceedings of the 18th European conference on Machine Learning,2007:406-417P.
[104]Zhou Z H, Wu J, Tang W. Ensembling neural networks:Many could be better than all. Artificial Intelligence,2002,137(1-2):239-263P.
[105]李凯,黄厚宽.一种基于聚类技术的选择性神经网络集成方法.计算机研究与发展,2005,42(4)：594-598页.
[106]赵胜颖,高广春.基于蚁群算法的选择性神经网络集成方法.浙江大学学报(工学版),2009,43(9)：1568-1573页.
[107]李文斌,刘椿年,钟宁.基于两阶段集成学习的分类器集成.北京工业大学学报,2010,36(3)：410-419页.
[108]Shen D, Yang Q, Chen Z. Noise reduction through summarization for web-page classification. Information processing and management,2007,43(6):173-174P.
[109]Wu X D, Zhu X Q. Mining with noise knowledge:error aware data mining. IEEE Transactions on Systems Man and Cybernetics,2008,38(4):917-932P.
[110]Angluinand D, Laird P. Learning from noisy examples. Machine Learning.1988, 2(4):343-370P.
[111]John G. H. Robust Decision Trees:Removing Outliers from Databases. Proceedings of the First International Conference on Knowledge Discovery and Data Mining, Menlo Park, CA,1995:174-179P.
[112]Gamgerber D, Lavrac N, Groselj C. Experiments with noise filtering in a medical domain. Proceedings of the Sixteenth International Conference on Machine Learning, San Francisco,1999:143-151P.
[113]Zhu X Q, Wu X D, Chen Q J. Eliminating class noise in large datasets. Proceedings of the Twentieth International Conference on Machine Learning, Washington DC, 2003:920-927P.
[114]Sofie V, Anneleen V A. Ensemble methods for noise elimination in classification problems. Fourth Workshop on Multiple Classifier Systems, United Kingdom,2003: 317-325P.
[115]Tumer K, Ghosh J. Analysis of decision boundaries in linearly combined neural classifiers. Pattern Recognition,1996,29(2).
[116]Tumer K, Ghosh J. Error correlation and error reduction in ensemble classifiers. Connection Science,1996,8(3-4):385-403P.
[117]Shahshahan B, Landgrebe D. The effect of unlabeled samples in reducing the small sample size problem and mitigating the hughes phenomenon. IEEE Transactions on Geoscience and Remote Sensing,1994,32(5):1087-1095P.
[118]黄树成,朱宇光,董逸生.基于半监督学习的数据流分类方法.计算机研究与发展,2007,44：225--229页.
[119]Miller D J, Uyar H S. A minture of experts classifier with learning based on both labelled and unlabelled data. Advances in Neural Information Processing Systems9, Cambridge, MA:MIT press,1997:571-577P.
[120]Rigollet P. Generalization error bounds in semi-supervised classification under the cluster assumption. The Journal of Machine Learning Research,2007,8: 1369-1392P.
[121]Devroye L. A probabilistic theory of pattern recognition. Springer-Verlag, New York, 1996.
[122]周志华,王珏.机器学习及其应用2007.北京：清华大学出版社,2007.
[123]Chapelle O, Zien A. Semi-supervised classification by low density separation. Proceedings of the tenth international workshop on artificial intelligence and statistics,2005.
[124]谢元澄,杨静宇.删除最差基学习器来层次修剪Bagging集成.计算机研究与发展,2009,46(2)：261-267页.
[125]Tax D, Duin R. Support vector domain description. Pattern Recognition Letters, 1999,20(11-13):1191-1199P
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |