基于服务的森林资源调查数据挖掘系统的研究
|
摘要
森林资源调查是林业工作的重要方面,而随着数字化林业的发展,林业基础调查数据的积累呈现快速增长的趋势,如何从海量数据中提取有价值的信息正是林业资源调查数据挖掘所应对的主要问题。在Internet的全球发展战略的影响下,基于WEB服务的应用集成已成为当前及未来信息系统的一个主要趋势,本研究探讨了WEB服务下森林资源调查数据挖掘系统的设计及实现。
首先对近年来常用的数据挖掘算法在森林资源调查中的应用进行了归纳总结,概括了不同的挖掘算法在相关领域的应用特点及场景要求,随后对相关技术进行了介绍,在分析了基于WEB服务的数据挖掘模式及其特点的基础上,依据.Net平台分别在不同的模式下开发了数据挖掘的WEB服务：实现属性相关分析的本地数据挖掘和改进的Aprior算法对远程数据的频繁项集的查找,着重研究了针对大数据集的访问、网络资源占用、代码的可伸缩性等方面的系统设计。
在此基础上,针对九曲水林场实验区构建了基于小班林分因子调查数据的决策树判定系统,并提出了特征数据集的品质这一概念,在属性约简过程中依此进行了约简阈值的设定,并基于.Net和WSBPEL进行了系统设计；针对决策树构建过程中易于出现数据碎片、子树重复等问题,进一步提出了基于分形维构建特征数据集的方法,分析了依据分形维数和信息增益对冗余属性的删除以及特征集的信息损失对决策树构建的影响；本部分的最后,依据实验数据比较分析了两种决策树归纳的特点。
作为服务于大面积区域调查的一个重要数据来源,遥感数据在森林资源调查中的应用占据着越来越重要的位置,为此,基于WCS标准,分别研究了面向服务的遥感数据挖掘模式及其基于工作流的分布式系统架构,并采用.Net体系及WSBPEL流程建模语言,具体设计了一个遥感影像纹理关联规则的挖掘系统。
基于此,提出了基于频繁项集的遥感图像特征抽取,该方法首先依据项集的频繁度及空间分布筛选候选频繁项集,再定义每一个频繁项集的空间表达能力值构建特征集。仿真在遥感图像上进行测试检验,针对EM算法对初始设置比较敏感的特点,采用了对同一特征集指定不同聚类数目并比较对数似然值确定最终聚类结果的方法。试验结果表明,本文提出的频繁集对研究区的林区具有较好的判别
之后,在分析了支持向量算法的特点及协同训练理论的基础上,依据遥感影像的纹理特征,提出了基于纹理特征值及像素灰度值构建的两个训练集上协同训练支持向量机的算法CTSVMTRS,并具体设计了分布式CTSVMTRS系统。
论文主要分析了如何针对一般森林资源调查的事务数据和遥感数据构建基于WEB服务上的数据挖掘系统,从对一些经典算法的系统设计过程中探讨了具体实现过程中的关键技术及算法改进策略,并对相关的设计进行了实验分析,仿真主要从两个方面进行：WEB系统的可行性及改进算法的有效性,实验结果证明了相关的观念,也表明了本研究在林业信息化应用集成方面具有一定的参考价值。
Forest resource survey plays an important role in forest aspect. As digital forestry widely applicated, the accumulation of fundation data on forest survey increases quickly. Therefore, how to distill valuable information from the mass data become the main issue of forest data mining. Besides, under the impact of global developing strategic of Internet, the application integration based WEB Service has been a major trend in information system. This paper studies the design and development in forest investigate data mining system based on WEB Service.
Firstly,the paper summarized the recent actuality on data mining application in forest resource survey, and drew out characteristics and scene requirement for different algorithms employed in the field of forest resource survey. After analyzing the data mining models and characteristics based on WEB Service, data mining WEB Service were developed with.Net Framework in different models, which includes an attributes relation analyzing running in the local server and an improved Aprior algorithm for searching the frequent item sets from route datasets. Besides, this development primarily studied on system designment on aspects of accessing to a large data source, occupying the network resources, process scalability and etc.. In the third part, to examine the each WEB Services architecture with study area data is the main work. A decision-tree system was constructed based on subcompartment inventory data which directed toward JiuQu Forestry that is located in FuJian province. After defining the quality of characteristic data set, Threshold value was decided in the process of attribute reduction, with this reserach, a distributed system was designed by using the.Net framework and WSBPEL. For issuses of how to reduce the data fragmentation and sub-tree repeat on training the decision-tree, the paper presented a method of constructing characteristic data set based on fractal dimension, and analysed the influence of using fractal dimension and information gain to droping the redundancy attributes, as well as information loss of characteristic data set to constructing the decision-tree. In this part, the paper summarized the characteristics of this two kinds of decision-tree by the experimental results.
As a vital data source for large area researching, remote sensing data plays a more and more important role in forest resource survey. In the next part of the paper, the model of data mining in the WEB Services architecture and integrating by work flow was investigated. On this foundation, a remote sensing image data mining basing on the value of feature texture system was designed by the.Net framework and WSBPEL
In the next chapter, extracting the feature from image basing on frequent itemsets is proposed, this method first selects out the candidate frequent itemsets founding on the degree of frequency and the locality distributing, then constructs the feature set by defining the value of spatial control for every frequent itemset. The simulation is done with remote sensor image, because of the EM clustering algorithm maybe be dominated by its initializing, the experimentation is designed with specifying the different number of clusters for every feature set and determines by the log likelihood. Experiment results show that frequent feature set can provide satisfactory expression for distinguzing the forestr proportion in image.
Since Tri-training applied in semi-supervised learning can improve the classification precision, and how to construct two redundance data sets is the key for Tri-training, the system running in WEB Services named CTSVMTRS was worked out in the research, with analysing on SVM algorithm and texture property of remote sensing image, which is for Tri-training SVMS in remote sensing image based on two data sets that one is from pixel value and another from calculating texture property is presented.
This paper mainly analyses how to design a data mining system based on WEB Services directed toward common forest resource survey affair data and remote sensing data. After designing some classical data mining algorithms in this system, the key technic and algorithm ameliorating strategy were researched in the concrete implementing process. By analysing the related designments, two tests were carried out for ensuring the design's effective, one is for WEB service architecture and another is for improving of algorithms and appling to the forest resources survey, the result of experiment not only proves that these methods are effective, but also shows this research has reference value in the aspect of forest information system integration to a certain extent.
首先对近年来常用的数据挖掘算法在森林资源调查中的应用进行了归纳总结,概括了不同的挖掘算法在相关领域的应用特点及场景要求,随后对相关技术进行了介绍,在分析了基于WEB服务的数据挖掘模式及其特点的基础上,依据.Net平台分别在不同的模式下开发了数据挖掘的WEB服务：实现属性相关分析的本地数据挖掘和改进的Aprior算法对远程数据的频繁项集的查找,着重研究了针对大数据集的访问、网络资源占用、代码的可伸缩性等方面的系统设计。
在此基础上,针对九曲水林场实验区构建了基于小班林分因子调查数据的决策树判定系统,并提出了特征数据集的品质这一概念,在属性约简过程中依此进行了约简阈值的设定,并基于.Net和WSBPEL进行了系统设计；针对决策树构建过程中易于出现数据碎片、子树重复等问题,进一步提出了基于分形维构建特征数据集的方法,分析了依据分形维数和信息增益对冗余属性的删除以及特征集的信息损失对决策树构建的影响；本部分的最后,依据实验数据比较分析了两种决策树归纳的特点。
作为服务于大面积区域调查的一个重要数据来源,遥感数据在森林资源调查中的应用占据着越来越重要的位置,为此,基于WCS标准,分别研究了面向服务的遥感数据挖掘模式及其基于工作流的分布式系统架构,并采用.Net体系及WSBPEL流程建模语言,具体设计了一个遥感影像纹理关联规则的挖掘系统。
基于此,提出了基于频繁项集的遥感图像特征抽取,该方法首先依据项集的频繁度及空间分布筛选候选频繁项集,再定义每一个频繁项集的空间表达能力值构建特征集。仿真在遥感图像上进行测试检验,针对EM算法对初始设置比较敏感的特点,采用了对同一特征集指定不同聚类数目并比较对数似然值确定最终聚类结果的方法。试验结果表明,本文提出的频繁集对研究区的林区具有较好的判别
之后,在分析了支持向量算法的特点及协同训练理论的基础上,依据遥感影像的纹理特征,提出了基于纹理特征值及像素灰度值构建的两个训练集上协同训练支持向量机的算法CTSVMTRS,并具体设计了分布式CTSVMTRS系统。
论文主要分析了如何针对一般森林资源调查的事务数据和遥感数据构建基于WEB服务上的数据挖掘系统,从对一些经典算法的系统设计过程中探讨了具体实现过程中的关键技术及算法改进策略,并对相关的设计进行了实验分析,仿真主要从两个方面进行：WEB系统的可行性及改进算法的有效性,实验结果证明了相关的观念,也表明了本研究在林业信息化应用集成方面具有一定的参考价值。
Forest resource survey plays an important role in forest aspect. As digital forestry widely applicated, the accumulation of fundation data on forest survey increases quickly. Therefore, how to distill valuable information from the mass data become the main issue of forest data mining. Besides, under the impact of global developing strategic of Internet, the application integration based WEB Service has been a major trend in information system. This paper studies the design and development in forest investigate data mining system based on WEB Service.
Firstly,the paper summarized the recent actuality on data mining application in forest resource survey, and drew out characteristics and scene requirement for different algorithms employed in the field of forest resource survey. After analyzing the data mining models and characteristics based on WEB Service, data mining WEB Service were developed with.Net Framework in different models, which includes an attributes relation analyzing running in the local server and an improved Aprior algorithm for searching the frequent item sets from route datasets. Besides, this development primarily studied on system designment on aspects of accessing to a large data source, occupying the network resources, process scalability and etc.. In the third part, to examine the each WEB Services architecture with study area data is the main work. A decision-tree system was constructed based on subcompartment inventory data which directed toward JiuQu Forestry that is located in FuJian province. After defining the quality of characteristic data set, Threshold value was decided in the process of attribute reduction, with this reserach, a distributed system was designed by using the.Net framework and WSBPEL. For issuses of how to reduce the data fragmentation and sub-tree repeat on training the decision-tree, the paper presented a method of constructing characteristic data set based on fractal dimension, and analysed the influence of using fractal dimension and information gain to droping the redundancy attributes, as well as information loss of characteristic data set to constructing the decision-tree. In this part, the paper summarized the characteristics of this two kinds of decision-tree by the experimental results.
As a vital data source for large area researching, remote sensing data plays a more and more important role in forest resource survey. In the next part of the paper, the model of data mining in the WEB Services architecture and integrating by work flow was investigated. On this foundation, a remote sensing image data mining basing on the value of feature texture system was designed by the.Net framework and WSBPEL
In the next chapter, extracting the feature from image basing on frequent itemsets is proposed, this method first selects out the candidate frequent itemsets founding on the degree of frequency and the locality distributing, then constructs the feature set by defining the value of spatial control for every frequent itemset. The simulation is done with remote sensor image, because of the EM clustering algorithm maybe be dominated by its initializing, the experimentation is designed with specifying the different number of clusters for every feature set and determines by the log likelihood. Experiment results show that frequent feature set can provide satisfactory expression for distinguzing the forestr proportion in image.
Since Tri-training applied in semi-supervised learning can improve the classification precision, and how to construct two redundance data sets is the key for Tri-training, the system running in WEB Services named CTSVMTRS was worked out in the research, with analysing on SVM algorithm and texture property of remote sensing image, which is for Tri-training SVMS in remote sensing image based on two data sets that one is from pixel value and another from calculating texture property is presented.
This paper mainly analyses how to design a data mining system based on WEB Services directed toward common forest resource survey affair data and remote sensing data. After designing some classical data mining algorithms in this system, the key technic and algorithm ameliorating strategy were researched in the concrete implementing process. By analysing the related designments, two tests were carried out for ensuring the design's effective, one is for WEB service architecture and another is for improving of algorithms and appling to the forest resources survey, the result of experiment not only proves that these methods are effective, but also shows this research has reference value in the aspect of forest information system integration to a certain extent.
引文
[1]A.Blum,T.Mitchell.Combinging labeled and unlabeled data with co-trining.Proceeding of the 11th Annual Conference on Computational Learning Theory,Wisconsin,Mi,1998,92-100
[2]Anantha M. Prasad,Louis R.Iverson, Andy Liaw. Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction[J]. Ecosystems,2006,9:181-199
[3]B.B.Mandelbrot.The Fractal Geometry of Nature[M].New York:W.H.Freemanand Company,1982:1-3
[4]B.Mandelbrot,文志英译.分形对象：形、机遇和维数[M].北京：世界图书出版社,1999,3：3-7
[5]BEASystems, IBM, MicroSoft, et al.Business process execution lan-guage for WEB services version1.1[EB/OL](2005-02).http://www-106.ibm.comdeveloperworksWEBserviceslibraryws-bpel.
[6]Bill Evjen, Billy Hollis. Professional VB.Net 2003[M],清华大学出版社.2005,6：297-303,671-676
[7]Brandon M.Collins,et al.Spatial patterns of large natural fires in Sierra Nevada wilderness areas[J]. Landscape Ecol,2007,22:545-557
[8]Chun yu Zhao,Ling kui Meng,Chang qing Huang.The study of relevant techniques for intellectual integra-tion of GIS and RS[C]. Proc.ACRS2001-22 Asian Conference on Remote Sensing,2001(2):1285-1290.
[9]Christian Nagel,Bill Evjen,Jay Glynn,李铭译C#2005&.Net3.0高级编程(第五版),北京,清华大学出版社,2007,12:32-76,121-201,660-693,921-978,1175-1198,1501-1558
[10]David Sceppa. Programming Microsoft ADO.Net 2.0 Core Reference[M],清华大学出版社.2007,6: 9,301-336,607,621
[11]D. J. KING, I. OLTHOF1, et al. Modelling and Mapping Damage to Forests from an Ice Storm Using Remote Sensing and Environmental Data[J], Natural Hazards,2005,35:321-342
[12]D.J.Miller,H.S.Uyar,Amixture of experts classfier with learning based on both labeled and unlabeled data.In:M.Mozer, M.I.Jordon,T.Petsche,eds. Advances in Neural Information Processing System 9,Cambridge,Ma:MIT Press,1997,571-577
[13]Fu X, Bultan T, Su J.Analysis of interacting BPEL WEB services[C]//The 13th International World Wide WEB Conference,2004.
[14]Franklin SE, Peddle DR..Classification of SPOTHRV Imagery and Texture Features[J].International Journal of Remote Sensing,1990,11 (3):551-556.
[15]HAO H.What is service-oriented architecture [EB/OL]. [2003-8-1]. http://WEBservices.xml.com/pub/a/ ws/2003/09/30/soa.html
[16]Hisashi Hasegawa,Tetsuhiko Yoshimura.Estimation of GPS positional accuracy under different forest conditions using signal interruption probability[J], Journal Forest Research,2007,12:1-7
[17]Hisatomo Taki, Peter G. Kevan,John S.Ascher. Landscape effects of forest loss in a pollination system[J],Landscape Ecol,2007,22:1575-1587
[18]HSU C W, LIN C J.A comparison of methods for multi-class support vector machines[J].IEEE Transaction on Neural Network,2002,13 (2):415-425.
[19]JIA HU, NING AHONG,.Organizing Multiple Data Source For Developing Intelligent e-Business Ports[J], Data Mining and Knowledge Discovery,12,127-150,2006
[20]Jiawei Han, Micheline Kamber.范明,孟小峰译Data Mining:Concepts and Techniques[M],机械工业出版社,2005,8：130,152
[21]Kazuhiro Aruga.Tabu search optimization of horizontal and vertical alignments of forest roads[J], Journal Forest Research,2005,10:275-284
[22]Lee J,Philpot W.Spectral Textures Pattern Matching:Aclassifier for Digit Imagery[J].IEEE Transactions on Geosciences and Remote Sensing,1991,19:545-548
[23]Li Z Y, Tang S W, Yan S C.Multi-class SVM classifier based on pair wise coupling [C]//Lecture Notes in Computer Science 2388.Berlin:Springer-Verlag,2002:321-333.
[24]Masato Katoh.Classifying tree species in a northern mixed forest using high-resolution IKONOS data[J],Journal Forest Research,2004,9:7-14
[25]Mike Gunderloy, Joseph L.Jorden, David W.Tschanz. Mastering Microsoft SQL Server 2005[M],人民邮电出版社,2008,4：221-252,312-332
[26]OASIA UDDI Specification[EB/OL].http://www.oasia-open.org/committees/tc_home.php?wg_abbrev= uddi-spec[2008-8-10]
[27]OASIA WEB Services Business Process Execution Language Version 2.0[EB/OL],[2007-5-9].http:// www.oasis-open.org/wsbpel/2.0/OS/wsbpel-v2.0-OS.html
[28]OASIA WEB Service Transaction1.1[EB/OL].http://www.oasia-open.org/committees/tc_home.php?wg_abbrev=ws_tx[2008-8-10]
[29]Peddle DR and Franklin SE.Multisourse Evidential Classification of Surface and Frozen Ground[J].International Journal of Remote Sensing,1992,13(17):3375-3380.
[30]Peddle DR.An Empirical Comparison of Evidential Reasoning,Linear Discriminant Analysis,and Maximum Likelihood Algorithms for Alpine Land Cover Classification[J]. Canadian Journal of Remote Sensing,1993,19(1):13-44.
[31]Pang-Ning,Tan Michael,Steinbach Vipin Kumar著,范明,范宏建等译.数据挖掘导论[M],人民邮电出版社2006,5：105-116
[32]Raul Romero-Calcerrada,C.J.Novillo,et al.GIS analysis of spatial patterns of human-caused wildfire ignition risk in the SW of Madrid (Central Spain)[J], Landscape Ecol,2008,23:341-354
[33]Risto Seppala.The future of forest research in a changing world[J], Journal Forest Research,2004, 9:313-316
[34]Roger Jennings.Expert one-on-one Visual Basic 2005 Database Programming [M],清华大学出版社,2006,11：22-33,335-338
[35]RUSHINGJA., RANGANATHH etal. Image segmentation using association rule feature[J]. IEEE Transactions on Image Processing,2002,11(5):558-567
[36]Sambasivam S,Theodosopoulos N.Advanced data clustering methods of mining WEB document[J]. Issues in Information Science and Information Technology,2006,3:563-579
[37]Sedat Keles, Fatih Sivrikaya,et al. Urbanization and forest cover change in regional directorate of Trabzon forestry from 1975 to 2000 using landsat data[J], Environ Monit Assess,2008,140:1-14
[38]S.Goldman,Y.Zhou.Enhancing supervised learning with unlabeled data. Proceedings of the 17th International Conference on Machine Learning,San Francisco,CA,2000,327-334.
[39]Srinivasan A Konowledge-based Techniques for Multi-source Classification[J].InternationalJournal of Remote Sensing,1990,11(3):505-522.
[40]Steve Cumming, Pierre Vernier.Statistical models of landscape pattern metrics with applications to regional scale dynamic forest simulations[J], Landscape Ecology,2002,17:433-444
[41]Tapan Kamdar, Anupam Joshi. Using incremental WEB log mining to create adaptive WEB servers[J], Int J Digit Libr (2005)5:133-150
[42]Thomas Eri著,王满红,陈荣华译.SOA概念、技术与设计[M],北京：机械工业出版社,2007：16-28,105-133
[43]Tomohiro,Nishizono,et al.Effects of thinning and site productivity on culmination of stand growth:results from long-term monitoring experiments in Japanese cedar (Cryptomeria japonica D. Don) forests in northeastern Japan[J],2008,13:264-274
[44]Townsend PA, Walsh SJ.Remote sensing of for ested wetlands:application of multitemporal and multispectral satellite imagery to determine plant community composition and structure in southeastern USA[J].PlantEcology,2001,157:129-149.
[45]Traina Jr c, Traina A et al. Fast fetures selection using fractal dimension[C]//Proc of XV Brazilian Database Symposium on Database. Berlin:Springer,2000:158-171
[46]Tsuyoshi,Kajisa,Takuhiko, et al.Estimation of stand volumes using the k-nearest neighbors method in Kyushu, Japan[J], Journal Forest Research,2008,13:249-254
[47]Vapnik V N. Statistical Learning Theory. Wiley-Interscience Publication, John Wiley&Sons, Inc,1998,6
[48]Vapnik V N. The Nature of Statistical Learning Theory. Springer-Verlag, New York 1995.5
[49]WEB Coverage Service (WCS)Implementation Standard[EB/OL],[2008-3-19]. http://www.openg eospatial.org/legal/
[50]WEB服务：SOAP专题[EB/OL].http//www.ibm.com/developerworks/cn/WEBservices/ws-theme/ ws-soap.html[2008-8-10]
[51]WEB服务：WSDL专题[EB/OL]. http//www.ibm.com/developerworks/cn/WEBservices/ws-theme/ ws-wsdl.html[2008-8-10]
[52]White Paper:Microsoft.Net framework 3.0 [EB/OL][2008-08-10] http://www.microsoft.com/.net framework/2008/en/us/white-papers.aspx
[53]White Paper:Microsoft SQL Server 2008 [EB/OL][2008-08-10] http://www.microsoft.com/sqlserver /2008/en/us/white-papers.aspx
[54]Yasushi Minowa. Classification rules discovery from selected trees for thinning with the C4.5 machine learning system[J], Journal Forest Research,2005,10:221-231
[55]yunsong Wang, Evan F,Bollig.Benjamin J,Kadlec Zachary A,Garbow. Gardon Erlebacher, David A yuen, Maxwell Rudolph, Lilli X.Yang, Erik.O.D.Sevre.WEB-IS(integrated system):an overall view[J],Vis Geosci,2006,10:27-42
[56]Z.-H.Zhou, M.Li. Tri-training:Exploiting unlabeled data using three classifiers.Ieee Transactions on Knowledge and data Engineering,2005,17(11):1529-1541
[57]Zhu Gu Bing, Dan G Blumberg. Classification Using ASTER Data and SVM Algorithms:The Case Study of Beer Sheva,Israel[J]. Remote Sensing of Environment,2002,80(2):233-240·
[58]鲍玉斌,王琢,孙怀良,于戈.一种基于分形维的快速属性选择算法[J],东北大学学报,2003,24(6)：527-530
[59]毕晓丽,洪伟,吴承祯,闫淑君,蓝斌.黄山松林不同树种树冠分形特征研究.福建林学院学报,2001,21(4)：347-350
[60]邓书斌,武红敢,江涛.GIS辅助下的基于数据挖掘的林型遥感分类方法研究[J],测绘科学,2008,5,33(3)：121-123
[61]丁海勇,卞正富.支持向量机理论及其在遥感图像处理中的应用[J],计算机工程与设计,2008,29(5)：1231-1234
[62]陈冰,张化祥.集成学习的多分类器动态组合方法[J],计算机工程,2008,24(12)：218-220
[63]陈昌鹏,吴保国.数据挖掘技术在森林资源信息管理系统中的应用[J],河北林果研究,2004,19(2)：149-153
[64]陈薇,李健.数据挖掘在农村林业中的应用[J],森林工程,2007,23(4)：82-84
[65]冯仲科,姚山,刘永霞,臧淑英.从林业信息数据采集到森林知识获取[J].北京林业大学学报,2007,29(8)：1-7
[66]高峻,张劲松,孟平.分形理论及其在林业科学中的应用[J].世界林业研究,2004,11(6)：11-15
[67]郭平,陈其鑫,王燕霞.基于分形维数的属性约减[J],计算机科学,2007,34(9)：189-190,239
[68]郭艳卿,孔祥维,尤新刚,何德全.基于Tri-training半监督学习的JPEG隐密分析方法[J],通信学报,2008,10：205-209,214
[69]贾萍,李海涛,林卉,顾海燕,韩颜顺.基于SVM的多源遥感影像分类研究[J],测绘科学,2008,33(4)：21-22.7
[70]蒋礼,阳柳.林火初期蔓延的分形模型[J].火灾科学,1994,3(1)：1-8
[71]李崇贵,赵宪文.聚类分析在监测区域样地分类中的应用研究[J],遥感学报,2006,10(3)：256-261
[72]李德仁,王树良,李德毅.空间数据挖掘理论与应用[M].科学出版社2006：9：269-275
[73]李广水,宋丁全,郑滔.分布式服务下的遥感影像挖掘的设计与实现[J],计算机工程,2009,11
[74]李金铭,刘荣其,宁正元.基于贝叶斯算法的森林成熟预测研究[J],厦门大学学报(自然科学版),2009,48(3)：342-346
[75]李金萍.分形理论的发展及其研究前景[J],英才高职论坛,2008,4(4)：55-59
[76]李明诗,谭莹,彭世揆.基于ASTER遥感数据的杨树林分因子建模及制图研究[J],南京林业大学学报,2006,30(5)：123-126
[77]李明诗,彭世揆等.基于ASTER数据的决策树自动构建及分类研究[J],国土资源遥感,2006,69(3)：33-36,42
[78]李慧,陈健飞,余明.线性光谱混合模型的ASTER影像植被应用分析[J],地球信息科学,2005,7(1)：103-106,115
[79]李星敏,郑有飞,刘安麟.遥感植被分类方法的概述及发展[J].陕西气象,2002(3)：20-23.
[80]廖明生,江利明,林珲,杨立民.基于CART集成学习的城市不透水层百分比遥感估算[J],武汉大学学报(信息科学版),2007,32(12)：1099-1102,1106
[81]刘剑平,陈松岭,胡晓娟.林业基础空间数据挖掘系统设计[J],西北林学院学报,2007,22(1)：157-160
[82]刘军志,宋现锋,汪超亮,胡勇.基于OGCWPS的遥感图像分布式检索系统研究[J],地理与地理信息科学,2008,24(4)：1-5
[83]刘庆连,宁正元.基于数据仓库的林业信息数据模型的设计[J],福建电脑,2006(2)：3,2
[84]刘龙飞,陈云浩,李京.遥感影像纹理分析方法综述与展望[J],遥感技术与应用,2003,18(6)：441-44
[85]刘小平,黎夏,何晋强,艾彬,彭晓鹃.基于蚁群智能的遥感影像分类新方法[J],遥感学报2008,12(2)：253-260
[86]刘雪华,张爽,靳强.贝叶斯专家系统分类器中专家知识的自动提取[J],地理与地理信息科学,2008,24(4)：20-24
[87]毛新生.SOA原理.方法.实践[M],北京：电子工业出版社,2007：16-18,36-102
[88]明德廷,李娟,尹怡欣.基于WEB Service的数据挖掘系统的研究与应用[J],计算机工程与设计2007,9(28)：1995-1997,2065
[89]倪志伟,胡正华.基于工作流和WEB服务技术的MIS研究[J],微计算机信息,2008,24(7)：20-22
[90]牛丽敏Apriori算法分析与改进综述[J],桂林电子科技大学学报,2007,27(1)：27-30
[91]彭光雄,李京,何宇华等.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J],遥感技术与应用,2007,22(1)：8-13
[92]彭岩,张道强.半监督典型相关分析算法[J],软件学报,2008,19(11)：2814-2821
[93]普雷斯.软件工程：实践者的研究方法[M],第5版,北京：机械工业出版社,2004：470-476.
[94]祁亨年,杨建刚,方陆明.基于多类支持向量机的遥感图像分类及其半监督式改进策略[J],复旦学报(自然科学版)2004,43(5)：781-785
[95]库向阳,薛惠锋,雷学武,汤国安.基于分类规则挖掘的遥感影像分类研究[J],遥感学报,2006,10(3)：332-338
[96]盛庆红,张剑清,肖晖.基于颜色和纹理的森林影像分割方法[J],武汉大学学报·信息科学版,2008,33(3)：306-309
[97]申文明,王文杰,罗海江等.基于决策树分类技术的遥感影像分类方法研究[J],遥感技术与应用,2007,22(3)：333-337
[98]史忠植.高级人工智能[M],北京,科学出版社,2006,9：216-223,242-256
[99]宋丽萍,佘光辉.深圳绿化树种选择智能决策支持系统的构建[J],南京林业大学学报,2005,29(2)：87-91
[100]宋波,李妙妍.面向WEB服务的BPEL的研究与实现[J],计算机工程与设计,2007,28(9)：2213-2219
[101]孙吉贵,刘杰,赵连宇.聚类算法研究[J],软件学报,2008,19(1)：48-61
[102]谭三清.聚类分析法在森林火险区划中的应用[J],中南林业科技大学学报,2008,28(1)：127-129,133
[103]谈冉,陆正球,严新平.分布式环境基于相似度的关联规则挖掘模型的研究[J],计算机应用研究,2008,3(25)：695-697,701
[104]汤井田,胡丹,龚智敏.基于SVM的图像纹理特征分类研究[J],计算机工程与科学,2008,30(8)：44-45,48
[105]唐耀华,高静怀,包乾宗.一种新的选择性支持向量机集成学习算法[J],西安交通大学学报,2008,42(10):1221-1225
[106]王阗,佘光辉.决策树C4.5算法在森林资源二类调查中的应用[J].南京林业大学学报,2007,31(3)：115-118
[107]王阗,彭世揆,佘光辉Apriori算法在森林资源二类调查数据分析中的应用[J],南京林业大学学报,2006,30(3)：63-66
[108]王占刚,庄大方,邱冬生,明涛.林业数据挖掘与可视化的应用分析[J],地球信息科学,2007,9(4)：19-22
[109]王涛,李舟军等.数据挖掘分类技术综述[J],计算机研究与发展,2007,44(11)：1809-1815
[110]汪杭军,方陆明,张广群.粗糙集在林业信息管理中的应用[J],森林资源管理,2006,1：85-87,94
[111]万幼川,刘良明,张永军.我国摄影测量与遥感发展探讨[J],测绘通报,2007,1：1-4
[112]王路,卓晴,王文渊.基于Co-Training的协同目标跟踪[J],计算机工程,2009,35(3)：202-204
[113]王佐成,薛丽霞,凌聪.遥感图像纹理关联规则挖掘[J].重庆邮电大学学报(自然科学版),2007,19(4)：438-441,449
[114]韦佳,彭宏.基于局部与全局保持的半监督维数约减方法[J],软件学报,2008,19(11)：2833-2842
[115]吴达胜,范雪华,应志辉.空间数据挖掘技术在森林资源管理信息系统中的应用研究[J],浙江林业研究,2004,24(3)：78-81
[116]吴柯,舒华忠.应用Krawtchouk矩和支持向量机的图像纹理分割[J],应用科学学报,2008,26(5)：521-525
[117]吴涛,秦昆,肖启芝,尹宁.图像纹理特征数据挖掘不确定性分析[J],计算机工程与设计,2007,28(12)：2905-2908
[118]吴小竹,陈崇成.利用WEB Services技术构建开放式数据挖掘系统[J],计算机工程与设计,2007,15(28)：2563-2565,3620
[119]肖红生,罗富和.基于小班取证推理的林业遥感数据分类方法研究[J].中南林业调查规划,2001,20(增刊)：75-79.
[120]肖化顺,张贵,刘大鹏,蔡学理.模糊数据挖掘技术支持下的林火蔓延模型选择研究[J],北京林业大学学报,2006,28(6)：93-97
[121]夏建涛.基于机器学习的高维多光谱数据分类[D].西安：西北工业大学,2002.
[122]冼广铭,曾碧卿,李星丽.半监督SVM的工作集样本预选取方法[J],计算机工程与应用,2008,44(20)：172-175
[123]肖宇,于剑.基于近邻传播算法的半监督聚类[J],软件学报2008,19(11)：2789-2790
[124]谢和平.分形应用中的数学基础与方法[M].北京：科学出版社,1997,2：21-36
[125]徐毅,金博,杨光辉等.产品性能计算系统集成框架及关键技术[J],计算机工程与应用,2007,43(25)：102-104
[126]徐岩,朱恒民.数据挖掘与数据库的集成方法[J],吉林大学学报(信息科学版),2007,2(25)：228-232
[127]闫光辉,李怀战.两阶段无监督顺序前向分形属性规约算法[J],计算机研究与发展,2008,45(11)：1955-1964
[128]杨彩霞,刘克成.基于.NET的电力企业信息系统一体化设计及实现[J],电网技术,2007,31(24)：86-90
[129]一种使用UDDI和WSDL的新方法：介绍新的OASIS UDDI WSDL TechnicalNote[EB/OL].http// www.ibm.com/developerworks/cn/WEBservices/ws-udmodl/index.html[2008-8-10]
[130]尹学松,胡恩良,陈松灿.基于成对约束的判别型半监督聚类分析[J],软件学报2008,19(11)：2791-2802
[131]于守健,李卫民,吴国文等BPEL中基于有限状态自动机的WEB服务自动组合[J].小型微型计算机系统,2007,28(4)：742-747
[132]张登荣,俞乐,邓超,狄黎平.基于OGCWPS的WEB环境遥感图像处理技术研究[J],浙江大学学报(工学版),2008,42(7)：1184-1188
[133]张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J],遥感学报,2006,10(1)：49-57.
[134]张怀清,鞠洪波,陈永富.森林资源环境网络在线决策支持系统研究[J],林业科学研究,2002,15(6)：637,643
[135]张爽,刘雪华,靳强.决策树学习方法应用于生境景观分类[J],清华大学学报(自然科学版),2006,46(9)：1564-1567
[136]张文元,秦昆,张成才,杨丽娜,马茹菲.基于知识的遥感图像地物提取方法研究[J],地理空间信息,2007,5(1)：66-69
[137]张永,迟忠先,谢福鼎.基于改进的PCM支持向量描述多类分类器[J],计算机科学,2008,35(8)：149-153
[138]张永胜,徐丽丽,齐峰,王强.基于三层组织模型的一种WEB服务组合策略[J],计算机工程与应用,2008,44(22)：89-91,112
[139]张永胜,王强,杨海波.基于BPEL的业务流程管理框架的研究[J].山东师范大学学报,2008,23(3)：22-24
[140]赵茂程,高素萍,潘一凡,郑加强.分形理论及其在林业中的应用与研究进展[J],世界林业研究,2002,15(2)：28-34
[141]赵英刚,陈奇,何钦铭.一种基于支持向量机的直推式学习算法[J],江南大学学报(自然科学版),2006,5(4)：441-444
[142]曾联明,吴湘滨,刘鹏.感兴趣区域遥感图像分类与支持向量机应用研究[J],计算机工程与应用,2009,45(6)：243-245
[143]曾波.一种基于单事务项集组合的频繁项集挖掘算法[J],计算机科学,2008,1(35)：196-197,226
[144]周广通,尹义龙,郭文鹃,任春晓.基于协同训练的指纹图像分类算法[J],山东大学学报(工学版),2009,39(1)：22-26
[145]周廷刚,郭达志,盛业华.灰度矢量多波段遥感影像纹理特征及其描述(J).西安科技学院学报,2000,20(4)：336-338.
[146]周志华.半监督学习中的协同训练风范[G],机器学习及其应用,北京：清华大学出版社,2007：259-275
[2]Anantha M. Prasad,Louis R.Iverson, Andy Liaw. Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction[J]. Ecosystems,2006,9:181-199
[3]B.B.Mandelbrot.The Fractal Geometry of Nature[M].New York:W.H.Freemanand Company,1982:1-3
[4]B.Mandelbrot,文志英译.分形对象：形、机遇和维数[M].北京：世界图书出版社,1999,3：3-7
[5]BEASystems, IBM, MicroSoft, et al.Business process execution lan-guage for WEB services version1.1[EB/OL](2005-02).http://www-106.ibm.comdeveloperworksWEBserviceslibraryws-bpel.
[6]Bill Evjen, Billy Hollis. Professional VB.Net 2003[M],清华大学出版社.2005,6：297-303,671-676
[7]Brandon M.Collins,et al.Spatial patterns of large natural fires in Sierra Nevada wilderness areas[J]. Landscape Ecol,2007,22:545-557
[8]Chun yu Zhao,Ling kui Meng,Chang qing Huang.The study of relevant techniques for intellectual integra-tion of GIS and RS[C]. Proc.ACRS2001-22 Asian Conference on Remote Sensing,2001(2):1285-1290.
[9]Christian Nagel,Bill Evjen,Jay Glynn,李铭译C#2005&.Net3.0高级编程(第五版),北京,清华大学出版社,2007,12:32-76,121-201,660-693,921-978,1175-1198,1501-1558
[10]David Sceppa. Programming Microsoft ADO.Net 2.0 Core Reference[M],清华大学出版社.2007,6: 9,301-336,607,621
[11]D. J. KING, I. OLTHOF1, et al. Modelling and Mapping Damage to Forests from an Ice Storm Using Remote Sensing and Environmental Data[J], Natural Hazards,2005,35:321-342
[12]D.J.Miller,H.S.Uyar,Amixture of experts classfier with learning based on both labeled and unlabeled data.In:M.Mozer, M.I.Jordon,T.Petsche,eds. Advances in Neural Information Processing System 9,Cambridge,Ma:MIT Press,1997,571-577
[13]Fu X, Bultan T, Su J.Analysis of interacting BPEL WEB services[C]//The 13th International World Wide WEB Conference,2004.
[14]Franklin SE, Peddle DR..Classification of SPOTHRV Imagery and Texture Features[J].International Journal of Remote Sensing,1990,11 (3):551-556.
[15]HAO H.What is service-oriented architecture [EB/OL]. [2003-8-1]. http://WEBservices.xml.com/pub/a/ ws/2003/09/30/soa.html
[16]Hisashi Hasegawa,Tetsuhiko Yoshimura.Estimation of GPS positional accuracy under different forest conditions using signal interruption probability[J], Journal Forest Research,2007,12:1-7
[17]Hisatomo Taki, Peter G. Kevan,John S.Ascher. Landscape effects of forest loss in a pollination system[J],Landscape Ecol,2007,22:1575-1587
[18]HSU C W, LIN C J.A comparison of methods for multi-class support vector machines[J].IEEE Transaction on Neural Network,2002,13 (2):415-425.
[19]JIA HU, NING AHONG,.Organizing Multiple Data Source For Developing Intelligent e-Business Ports[J], Data Mining and Knowledge Discovery,12,127-150,2006
[20]Jiawei Han, Micheline Kamber.范明,孟小峰译Data Mining:Concepts and Techniques[M],机械工业出版社,2005,8：130,152
[21]Kazuhiro Aruga.Tabu search optimization of horizontal and vertical alignments of forest roads[J], Journal Forest Research,2005,10:275-284
[22]Lee J,Philpot W.Spectral Textures Pattern Matching:Aclassifier for Digit Imagery[J].IEEE Transactions on Geosciences and Remote Sensing,1991,19:545-548
[23]Li Z Y, Tang S W, Yan S C.Multi-class SVM classifier based on pair wise coupling [C]//Lecture Notes in Computer Science 2388.Berlin:Springer-Verlag,2002:321-333.
[24]Masato Katoh.Classifying tree species in a northern mixed forest using high-resolution IKONOS data[J],Journal Forest Research,2004,9:7-14
[25]Mike Gunderloy, Joseph L.Jorden, David W.Tschanz. Mastering Microsoft SQL Server 2005[M],人民邮电出版社,2008,4：221-252,312-332
[26]OASIA UDDI Specification[EB/OL].http://www.oasia-open.org/committees/tc_home.php?wg_abbrev= uddi-spec[2008-8-10]
[27]OASIA WEB Services Business Process Execution Language Version 2.0[EB/OL],[2007-5-9].http:// www.oasis-open.org/wsbpel/2.0/OS/wsbpel-v2.0-OS.html
[28]OASIA WEB Service Transaction1.1[EB/OL].http://www.oasia-open.org/committees/tc_home.php?wg_abbrev=ws_tx[2008-8-10]
[29]Peddle DR and Franklin SE.Multisourse Evidential Classification of Surface and Frozen Ground[J].International Journal of Remote Sensing,1992,13(17):3375-3380.
[30]Peddle DR.An Empirical Comparison of Evidential Reasoning,Linear Discriminant Analysis,and Maximum Likelihood Algorithms for Alpine Land Cover Classification[J]. Canadian Journal of Remote Sensing,1993,19(1):13-44.
[31]Pang-Ning,Tan Michael,Steinbach Vipin Kumar著,范明,范宏建等译.数据挖掘导论[M],人民邮电出版社2006,5：105-116
[32]Raul Romero-Calcerrada,C.J.Novillo,et al.GIS analysis of spatial patterns of human-caused wildfire ignition risk in the SW of Madrid (Central Spain)[J], Landscape Ecol,2008,23:341-354
[33]Risto Seppala.The future of forest research in a changing world[J], Journal Forest Research,2004, 9:313-316
[34]Roger Jennings.Expert one-on-one Visual Basic 2005 Database Programming [M],清华大学出版社,2006,11：22-33,335-338
[35]RUSHINGJA., RANGANATHH etal. Image segmentation using association rule feature[J]. IEEE Transactions on Image Processing,2002,11(5):558-567
[36]Sambasivam S,Theodosopoulos N.Advanced data clustering methods of mining WEB document[J]. Issues in Information Science and Information Technology,2006,3:563-579
[37]Sedat Keles, Fatih Sivrikaya,et al. Urbanization and forest cover change in regional directorate of Trabzon forestry from 1975 to 2000 using landsat data[J], Environ Monit Assess,2008,140:1-14
[38]S.Goldman,Y.Zhou.Enhancing supervised learning with unlabeled data. Proceedings of the 17th International Conference on Machine Learning,San Francisco,CA,2000,327-334.
[39]Srinivasan A Konowledge-based Techniques for Multi-source Classification[J].InternationalJournal of Remote Sensing,1990,11(3):505-522.
[40]Steve Cumming, Pierre Vernier.Statistical models of landscape pattern metrics with applications to regional scale dynamic forest simulations[J], Landscape Ecology,2002,17:433-444
[41]Tapan Kamdar, Anupam Joshi. Using incremental WEB log mining to create adaptive WEB servers[J], Int J Digit Libr (2005)5:133-150
[42]Thomas Eri著,王满红,陈荣华译.SOA概念、技术与设计[M],北京：机械工业出版社,2007：16-28,105-133
[43]Tomohiro,Nishizono,et al.Effects of thinning and site productivity on culmination of stand growth:results from long-term monitoring experiments in Japanese cedar (Cryptomeria japonica D. Don) forests in northeastern Japan[J],2008,13:264-274
[44]Townsend PA, Walsh SJ.Remote sensing of for ested wetlands:application of multitemporal and multispectral satellite imagery to determine plant community composition and structure in southeastern USA[J].PlantEcology,2001,157:129-149.
[45]Traina Jr c, Traina A et al. Fast fetures selection using fractal dimension[C]//Proc of XV Brazilian Database Symposium on Database. Berlin:Springer,2000:158-171
[46]Tsuyoshi,Kajisa,Takuhiko, et al.Estimation of stand volumes using the k-nearest neighbors method in Kyushu, Japan[J], Journal Forest Research,2008,13:249-254
[47]Vapnik V N. Statistical Learning Theory. Wiley-Interscience Publication, John Wiley&Sons, Inc,1998,6
[48]Vapnik V N. The Nature of Statistical Learning Theory. Springer-Verlag, New York 1995.5
[49]WEB Coverage Service (WCS)Implementation Standard[EB/OL],[2008-3-19]. http://www.openg eospatial.org/legal/
[50]WEB服务：SOAP专题[EB/OL].http//www.ibm.com/developerworks/cn/WEBservices/ws-theme/ ws-soap.html[2008-8-10]
[51]WEB服务：WSDL专题[EB/OL]. http//www.ibm.com/developerworks/cn/WEBservices/ws-theme/ ws-wsdl.html[2008-8-10]
[52]White Paper:Microsoft.Net framework 3.0 [EB/OL][2008-08-10] http://www.microsoft.com/.net framework/2008/en/us/white-papers.aspx
[53]White Paper:Microsoft SQL Server 2008 [EB/OL][2008-08-10] http://www.microsoft.com/sqlserver /2008/en/us/white-papers.aspx
[54]Yasushi Minowa. Classification rules discovery from selected trees for thinning with the C4.5 machine learning system[J], Journal Forest Research,2005,10:221-231
[55]yunsong Wang, Evan F,Bollig.Benjamin J,Kadlec Zachary A,Garbow. Gardon Erlebacher, David A yuen, Maxwell Rudolph, Lilli X.Yang, Erik.O.D.Sevre.WEB-IS(integrated system):an overall view[J],Vis Geosci,2006,10:27-42
[56]Z.-H.Zhou, M.Li. Tri-training:Exploiting unlabeled data using three classifiers.Ieee Transactions on Knowledge and data Engineering,2005,17(11):1529-1541
[57]Zhu Gu Bing, Dan G Blumberg. Classification Using ASTER Data and SVM Algorithms:The Case Study of Beer Sheva,Israel[J]. Remote Sensing of Environment,2002,80(2):233-240·
[58]鲍玉斌,王琢,孙怀良,于戈.一种基于分形维的快速属性选择算法[J],东北大学学报,2003,24(6)：527-530
[59]毕晓丽,洪伟,吴承祯,闫淑君,蓝斌.黄山松林不同树种树冠分形特征研究.福建林学院学报,2001,21(4)：347-350
[60]邓书斌,武红敢,江涛.GIS辅助下的基于数据挖掘的林型遥感分类方法研究[J],测绘科学,2008,5,33(3)：121-123
[61]丁海勇,卞正富.支持向量机理论及其在遥感图像处理中的应用[J],计算机工程与设计,2008,29(5)：1231-1234
[62]陈冰,张化祥.集成学习的多分类器动态组合方法[J],计算机工程,2008,24(12)：218-220
[63]陈昌鹏,吴保国.数据挖掘技术在森林资源信息管理系统中的应用[J],河北林果研究,2004,19(2)：149-153
[64]陈薇,李健.数据挖掘在农村林业中的应用[J],森林工程,2007,23(4)：82-84
[65]冯仲科,姚山,刘永霞,臧淑英.从林业信息数据采集到森林知识获取[J].北京林业大学学报,2007,29(8)：1-7
[66]高峻,张劲松,孟平.分形理论及其在林业科学中的应用[J].世界林业研究,2004,11(6)：11-15
[67]郭平,陈其鑫,王燕霞.基于分形维数的属性约减[J],计算机科学,2007,34(9)：189-190,239
[68]郭艳卿,孔祥维,尤新刚,何德全.基于Tri-training半监督学习的JPEG隐密分析方法[J],通信学报,2008,10：205-209,214
[69]贾萍,李海涛,林卉,顾海燕,韩颜顺.基于SVM的多源遥感影像分类研究[J],测绘科学,2008,33(4)：21-22.7
[70]蒋礼,阳柳.林火初期蔓延的分形模型[J].火灾科学,1994,3(1)：1-8
[71]李崇贵,赵宪文.聚类分析在监测区域样地分类中的应用研究[J],遥感学报,2006,10(3)：256-261
[72]李德仁,王树良,李德毅.空间数据挖掘理论与应用[M].科学出版社2006：9：269-275
[73]李广水,宋丁全,郑滔.分布式服务下的遥感影像挖掘的设计与实现[J],计算机工程,2009,11
[74]李金铭,刘荣其,宁正元.基于贝叶斯算法的森林成熟预测研究[J],厦门大学学报(自然科学版),2009,48(3)：342-346
[75]李金萍.分形理论的发展及其研究前景[J],英才高职论坛,2008,4(4)：55-59
[76]李明诗,谭莹,彭世揆.基于ASTER遥感数据的杨树林分因子建模及制图研究[J],南京林业大学学报,2006,30(5)：123-126
[77]李明诗,彭世揆等.基于ASTER数据的决策树自动构建及分类研究[J],国土资源遥感,2006,69(3)：33-36,42
[78]李慧,陈健飞,余明.线性光谱混合模型的ASTER影像植被应用分析[J],地球信息科学,2005,7(1)：103-106,115
[79]李星敏,郑有飞,刘安麟.遥感植被分类方法的概述及发展[J].陕西气象,2002(3)：20-23.
[80]廖明生,江利明,林珲,杨立民.基于CART集成学习的城市不透水层百分比遥感估算[J],武汉大学学报(信息科学版),2007,32(12)：1099-1102,1106
[81]刘剑平,陈松岭,胡晓娟.林业基础空间数据挖掘系统设计[J],西北林学院学报,2007,22(1)：157-160
[82]刘军志,宋现锋,汪超亮,胡勇.基于OGCWPS的遥感图像分布式检索系统研究[J],地理与地理信息科学,2008,24(4)：1-5
[83]刘庆连,宁正元.基于数据仓库的林业信息数据模型的设计[J],福建电脑,2006(2)：3,2
[84]刘龙飞,陈云浩,李京.遥感影像纹理分析方法综述与展望[J],遥感技术与应用,2003,18(6)：441-44
[85]刘小平,黎夏,何晋强,艾彬,彭晓鹃.基于蚁群智能的遥感影像分类新方法[J],遥感学报2008,12(2)：253-260
[86]刘雪华,张爽,靳强.贝叶斯专家系统分类器中专家知识的自动提取[J],地理与地理信息科学,2008,24(4)：20-24
[87]毛新生.SOA原理.方法.实践[M],北京：电子工业出版社,2007：16-18,36-102
[88]明德廷,李娟,尹怡欣.基于WEB Service的数据挖掘系统的研究与应用[J],计算机工程与设计2007,9(28)：1995-1997,2065
[89]倪志伟,胡正华.基于工作流和WEB服务技术的MIS研究[J],微计算机信息,2008,24(7)：20-22
[90]牛丽敏Apriori算法分析与改进综述[J],桂林电子科技大学学报,2007,27(1)：27-30
[91]彭光雄,李京,何宇华等.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J],遥感技术与应用,2007,22(1)：8-13
[92]彭岩,张道强.半监督典型相关分析算法[J],软件学报,2008,19(11)：2814-2821
[93]普雷斯.软件工程：实践者的研究方法[M],第5版,北京：机械工业出版社,2004：470-476.
[94]祁亨年,杨建刚,方陆明.基于多类支持向量机的遥感图像分类及其半监督式改进策略[J],复旦学报(自然科学版)2004,43(5)：781-785
[95]库向阳,薛惠锋,雷学武,汤国安.基于分类规则挖掘的遥感影像分类研究[J],遥感学报,2006,10(3)：332-338
[96]盛庆红,张剑清,肖晖.基于颜色和纹理的森林影像分割方法[J],武汉大学学报·信息科学版,2008,33(3)：306-309
[97]申文明,王文杰,罗海江等.基于决策树分类技术的遥感影像分类方法研究[J],遥感技术与应用,2007,22(3)：333-337
[98]史忠植.高级人工智能[M],北京,科学出版社,2006,9：216-223,242-256
[99]宋丽萍,佘光辉.深圳绿化树种选择智能决策支持系统的构建[J],南京林业大学学报,2005,29(2)：87-91
[100]宋波,李妙妍.面向WEB服务的BPEL的研究与实现[J],计算机工程与设计,2007,28(9)：2213-2219
[101]孙吉贵,刘杰,赵连宇.聚类算法研究[J],软件学报,2008,19(1)：48-61
[102]谭三清.聚类分析法在森林火险区划中的应用[J],中南林业科技大学学报,2008,28(1)：127-129,133
[103]谈冉,陆正球,严新平.分布式环境基于相似度的关联规则挖掘模型的研究[J],计算机应用研究,2008,3(25)：695-697,701
[104]汤井田,胡丹,龚智敏.基于SVM的图像纹理特征分类研究[J],计算机工程与科学,2008,30(8)：44-45,48
[105]唐耀华,高静怀,包乾宗.一种新的选择性支持向量机集成学习算法[J],西安交通大学学报,2008,42(10):1221-1225
[106]王阗,佘光辉.决策树C4.5算法在森林资源二类调查中的应用[J].南京林业大学学报,2007,31(3)：115-118
[107]王阗,彭世揆,佘光辉Apriori算法在森林资源二类调查数据分析中的应用[J],南京林业大学学报,2006,30(3)：63-66
[108]王占刚,庄大方,邱冬生,明涛.林业数据挖掘与可视化的应用分析[J],地球信息科学,2007,9(4)：19-22
[109]王涛,李舟军等.数据挖掘分类技术综述[J],计算机研究与发展,2007,44(11)：1809-1815
[110]汪杭军,方陆明,张广群.粗糙集在林业信息管理中的应用[J],森林资源管理,2006,1：85-87,94
[111]万幼川,刘良明,张永军.我国摄影测量与遥感发展探讨[J],测绘通报,2007,1：1-4
[112]王路,卓晴,王文渊.基于Co-Training的协同目标跟踪[J],计算机工程,2009,35(3)：202-204
[113]王佐成,薛丽霞,凌聪.遥感图像纹理关联规则挖掘[J].重庆邮电大学学报(自然科学版),2007,19(4)：438-441,449
[114]韦佳,彭宏.基于局部与全局保持的半监督维数约减方法[J],软件学报,2008,19(11)：2833-2842
[115]吴达胜,范雪华,应志辉.空间数据挖掘技术在森林资源管理信息系统中的应用研究[J],浙江林业研究,2004,24(3)：78-81
[116]吴柯,舒华忠.应用Krawtchouk矩和支持向量机的图像纹理分割[J],应用科学学报,2008,26(5)：521-525
[117]吴涛,秦昆,肖启芝,尹宁.图像纹理特征数据挖掘不确定性分析[J],计算机工程与设计,2007,28(12)：2905-2908
[118]吴小竹,陈崇成.利用WEB Services技术构建开放式数据挖掘系统[J],计算机工程与设计,2007,15(28)：2563-2565,3620
[119]肖红生,罗富和.基于小班取证推理的林业遥感数据分类方法研究[J].中南林业调查规划,2001,20(增刊)：75-79.
[120]肖化顺,张贵,刘大鹏,蔡学理.模糊数据挖掘技术支持下的林火蔓延模型选择研究[J],北京林业大学学报,2006,28(6)：93-97
[121]夏建涛.基于机器学习的高维多光谱数据分类[D].西安：西北工业大学,2002.
[122]冼广铭,曾碧卿,李星丽.半监督SVM的工作集样本预选取方法[J],计算机工程与应用,2008,44(20)：172-175
[123]肖宇,于剑.基于近邻传播算法的半监督聚类[J],软件学报2008,19(11)：2789-2790
[124]谢和平.分形应用中的数学基础与方法[M].北京：科学出版社,1997,2：21-36
[125]徐毅,金博,杨光辉等.产品性能计算系统集成框架及关键技术[J],计算机工程与应用,2007,43(25)：102-104
[126]徐岩,朱恒民.数据挖掘与数据库的集成方法[J],吉林大学学报(信息科学版),2007,2(25)：228-232
[127]闫光辉,李怀战.两阶段无监督顺序前向分形属性规约算法[J],计算机研究与发展,2008,45(11)：1955-1964
[128]杨彩霞,刘克成.基于.NET的电力企业信息系统一体化设计及实现[J],电网技术,2007,31(24)：86-90
[129]一种使用UDDI和WSDL的新方法：介绍新的OASIS UDDI WSDL TechnicalNote[EB/OL].http// www.ibm.com/developerworks/cn/WEBservices/ws-udmodl/index.html[2008-8-10]
[130]尹学松,胡恩良,陈松灿.基于成对约束的判别型半监督聚类分析[J],软件学报2008,19(11)：2791-2802
[131]于守健,李卫民,吴国文等BPEL中基于有限状态自动机的WEB服务自动组合[J].小型微型计算机系统,2007,28(4)：742-747
[132]张登荣,俞乐,邓超,狄黎平.基于OGCWPS的WEB环境遥感图像处理技术研究[J],浙江大学学报(工学版),2008,42(7)：1184-1188
[133]张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J],遥感学报,2006,10(1)：49-57.
[134]张怀清,鞠洪波,陈永富.森林资源环境网络在线决策支持系统研究[J],林业科学研究,2002,15(6)：637,643
[135]张爽,刘雪华,靳强.决策树学习方法应用于生境景观分类[J],清华大学学报(自然科学版),2006,46(9)：1564-1567
[136]张文元,秦昆,张成才,杨丽娜,马茹菲.基于知识的遥感图像地物提取方法研究[J],地理空间信息,2007,5(1)：66-69
[137]张永,迟忠先,谢福鼎.基于改进的PCM支持向量描述多类分类器[J],计算机科学,2008,35(8)：149-153
[138]张永胜,徐丽丽,齐峰,王强.基于三层组织模型的一种WEB服务组合策略[J],计算机工程与应用,2008,44(22)：89-91,112
[139]张永胜,王强,杨海波.基于BPEL的业务流程管理框架的研究[J].山东师范大学学报,2008,23(3)：22-24
[140]赵茂程,高素萍,潘一凡,郑加强.分形理论及其在林业中的应用与研究进展[J],世界林业研究,2002,15(2)：28-34
[141]赵英刚,陈奇,何钦铭.一种基于支持向量机的直推式学习算法[J],江南大学学报(自然科学版),2006,5(4)：441-444
[142]曾联明,吴湘滨,刘鹏.感兴趣区域遥感图像分类与支持向量机应用研究[J],计算机工程与应用,2009,45(6)：243-245
[143]曾波.一种基于单事务项集组合的频繁项集挖掘算法[J],计算机科学,2008,1(35)：196-197,226
[144]周广通,尹义龙,郭文鹃,任春晓.基于协同训练的指纹图像分类算法[J],山东大学学报(工学版),2009,39(1)：22-26
[145]周廷刚,郭达志,盛业华.灰度矢量多波段遥感影像纹理特征及其描述(J).西安科技学院学报,2000,20(4)：336-338.
[146]周志华.半监督学习中的协同训练风范[G],机器学习及其应用,北京：清华大学出版社,2007：259-275