基于粗糙集理论和C4.5算法相结合的遥感影像分类研究
|
摘要
GIS的应用提高了遥感影像的数据提取和分析能力,遥感影像信息的提取和分类是GIS在土地资源应用中最主要的信息源。解决遥感影像识别问题并满足一定的精度,是遥感影像分析中的一个关键问题,具有十分重要的意义。
本文选取地物类型较复杂的福州市的城乡结合区的一小块区域为试验区,并集成遥感影像的光谱特征、纹理特征及地形特征构建了多源空间数据库,利用基于C4.5算法、基于粗糙集理论及基于粗糙集理论和C4.5算法相结合的方法,从空间数据库的训练样本数据集中挖掘分类规则,进行分类实验,并分别与传统的最大似然分类法进行比较与分析。研究结果表明,基于知识分类方法的分类精度都明显高于传统的最大似然法,其中基于粗糙集和C4.5算法相结合的分类方法的分类效果最好,并不同程度的弥补了单一的基于粗糙集理论和基于C4.5算法分类中的不足。因而基于多种算法相结合的分类方法,可以充分发挥其优点,并弥补分类中各自的不足,是促进基于知识的遥感影像分类方法在土地利用分类中广泛应用的一项有效手段。
The Application of GIS enhances the data extraction and analysis ability of remote sensing images, and the information extraction and classification of remote sensing image is the most important source of information in the land resources application of GIS. However, how to distinguish kinds of Images and meet the accuracy to a certain extent is a key problem in remote sensing image research, which takes on very important significance.
The paper takes a small plot in the outskirts of Fuzhou with complicated land use in Fujian Province as study area. The classification rules are discovered from the training samples of the spatial database based on C4.5 algorithm, Rough Sets and both with together, which integrate spectral characteristics, texture characteristics and terrain features of remote sensing image to build a multi-source spatial database. And the classification tests are carried out based on the rules. The traditional maximum likelihood classification is also compared to check the classification accuracies. The results have suggested that the accuracy of classification based on knowledge is markedly higher than the traditional maximum likelihood classification. The combination of Rough Sets and C4.5 algorithm is the best, which can make up for the shorts based on Rough Sets or C4.5 algorithm to a different extent. So the classification method based on multi-algorithm, which can take a good advantage of kinds of classification algorithm and make up for the shorts respectively, is a good way to promote the wide application of the classification methods of remote sensing image based on knowledge in land use classification.
本文选取地物类型较复杂的福州市的城乡结合区的一小块区域为试验区,并集成遥感影像的光谱特征、纹理特征及地形特征构建了多源空间数据库,利用基于C4.5算法、基于粗糙集理论及基于粗糙集理论和C4.5算法相结合的方法,从空间数据库的训练样本数据集中挖掘分类规则,进行分类实验,并分别与传统的最大似然分类法进行比较与分析。研究结果表明,基于知识分类方法的分类精度都明显高于传统的最大似然法,其中基于粗糙集和C4.5算法相结合的分类方法的分类效果最好,并不同程度的弥补了单一的基于粗糙集理论和基于C4.5算法分类中的不足。因而基于多种算法相结合的分类方法,可以充分发挥其优点,并弥补分类中各自的不足,是促进基于知识的遥感影像分类方法在土地利用分类中广泛应用的一项有效手段。
The Application of GIS enhances the data extraction and analysis ability of remote sensing images, and the information extraction and classification of remote sensing image is the most important source of information in the land resources application of GIS. However, how to distinguish kinds of Images and meet the accuracy to a certain extent is a key problem in remote sensing image research, which takes on very important significance.
The paper takes a small plot in the outskirts of Fuzhou with complicated land use in Fujian Province as study area. The classification rules are discovered from the training samples of the spatial database based on C4.5 algorithm, Rough Sets and both with together, which integrate spectral characteristics, texture characteristics and terrain features of remote sensing image to build a multi-source spatial database. And the classification tests are carried out based on the rules. The traditional maximum likelihood classification is also compared to check the classification accuracies. The results have suggested that the accuracy of classification based on knowledge is markedly higher than the traditional maximum likelihood classification. The combination of Rough Sets and C4.5 algorithm is the best, which can make up for the shorts based on Rough Sets or C4.5 algorithm to a different extent. So the classification method based on multi-algorithm, which can take a good advantage of kinds of classification algorithm and make up for the shorts respectively, is a good way to promote the wide application of the classification methods of remote sensing image based on knowledge in land use classification.
引文
[1]裴韬,周成虎,骆剑承,韩志军,汪闽,秦承志,蔡强.空间数据知识发现研究进展评述[J].中国图像图形学报,2001,6(9):854-860
[2]李德仁,王树良,李德毅,王新洲.论空间数据挖掘和知识发现的理论与方法[J].武汉大学学报信息科学版,2002,27(3):221-233
[3]李德仁,王树良,史文中,王新洲.论空间数据挖掘和知识发现[J].武汉大学学报信息科学版,第2001,26(6):491-499
[4]王海起,王劲峰.空间数据挖掘技术研究进展[J].地理与地理信息科学,2005,21(4):6-10
[5]陈中祥,岳超源.空间数据挖掘的研究与发展[J].计算机工程与应用,2003:5-7,33
[6]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M],科学出版社,2006:1-7
[7]郭际元,江宝得,江雯倩,李洋.空间数据挖掘技术与发展趋势[J].国土资源导刊:49-50
[8]李爽,丁圣彦,许叔明.遥感影像分类方法比较研究[J].河南大学学报(自然科学版),2002,32(2):70-73
[9]莫登奎.中高分辨率遥感影像分割与信息提取研究[J].2006
[10]余达太,蓝荣钦,张世涛,关爱杰.空间数据挖掘的方法和实施[J].测绘学院学报,2003,20(2):132-134
[11]王新洲.论空间数据处理与空间数据挖掘[J].武汉大学学报信息科学版,2006,31(1):1-4,8
[12]厍向阳,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):333-338
[13]伍振军.遥感技术在数字流域中的应用研究[D].硕士论文,2002
[14]邸凯昌,李德仁,李德毅.Rough集理论及其在GIS属性分析和知识发现中的应用[J].武汉测绘科技大学学报,1999,24(1):6-10
[15]陈小瑜.基于空间数据挖掘与知识发现的遥感影像分类研究[J].硕士研究论文,2007
[16]李朝峰.基于知识发现和决策规则的遥感图像城区土地覆盖/利用分类方法[J].计算机工程与应用,2004,23:212-215
[17]邓芳,秦军,李鉴.提高遥感影像分类精度方法的研究[J].铁路航测,2003,(2):4-7
[18]陈述彭,鲁学军,周成虎.地理信息系统导论[M].北京:科学出版社,2000:3-10
[19]H J.Data MiningTechniques.ACM-SIGMOD'96 Conf.Tutorial,June,1996
[20]蒋良孝,蔡之华.空间数据挖掘的回顾与展望[J].计算机工程,2003,29(6):9-10,58
[21]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M].科学出版社,2006:278
[22]邸凯昌著.空间数据挖掘与知识发现[M].武汉大学出版社,2001:122
[23]邸凯昌.空间数据挖掘和知识发现的理论与方法[D].武汉测绘科技大学博士论文,1999
[24]Huang Xueqiao and John R.Jensen.A Machine-Learning Approach to Automated Knowledge Based Building for Remote Sensing Image Analysis with GIS Data[J].Photogrammetry Engineering and Remote Sensing,1997.63(10):1185-1184
[25]Hansen M & Dubayah R et al.Classification trees:an alternative to traditional land cover classifiers[J].International Journal of Remote Sensing,1996,17(5):1075-1081
[26]Eklund P.W,Kirbky S.D,A.Salim.Datamining and soil salimty analysis[J].Int.J.of GIS,1998,12(3):247-268
[27]Lawrence Rick L,Andrea Wright.Rule-based classification systems using classification and regression tree analysis[J].Photogrammetric Engineering & Remote Sensing,2001,67(10):1137-1142
[28]McIver D K,Friedl M A.Using prior probabilities in decision-tree classification of remotely sensed data[J].Remote Sensing of Environment,2002,81:253-261
[29]李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21
[30]申文明,王文杰,罗海江,张峰,刘小曼,熊文成.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):333-338
[31]游代安.GIS辅助的遥感影像处理与分析技术的研究[D].硕士论文,2001
[32]李爽,丁圣彦等.决策树分类方法及其在土地覆盖分类中的应用[J].遥感技术与应用,2002,17(1):6-11
[33]赵萍.基于知识的江南典型地区土地利用覆被分类研究[D].博士论文,2003
[34]陈艳丽,张万昌等.地理信息系统支持下的山区遥感影像决策树分类[J].2006(1):69-74
[35]李强.创建决策树算法的比较研究--ID3,C4.5,C5.0算法的比较.甘肃科学学报,2006,8(4):85-87
[36]季桂树,陈沛玲,宋航.决策树分类算法研究综述[J].科技广场,2007:9-12
[37]李德仁,程涛.从空间数据库中发现知识[J].测绘学报,1995,24(1):37-44
[38]李明诗.基于ASTER遥感数据的建湖县杨树信息提取的研究--分类、建模与反演制图[D].博士论文,2005
[39]Q uinlan Ross J.C4.5:Programs for Machine Learning[M].SanMate,CA:Morgan Kaufmann Publishers,1993
[40]David Hand Heikki Padhraic Smyth著.数据挖掘原理[M](廖丽,宋俊等译).北京:机械工业出版社,2003
[41]王晓国,黄韶坤,朱炜等.应用C4.5算法构造客户分类决策树的方法[J].计算机工程,2003(14): 89-91
[42]祝峰.粗糙集理论的现状与前景[J].新疆石油学院学报,2000,12(3):71-73
[43]李年攸.粗糙集理论在图像分割中的应用[J].三明学院学报,2005,22(4):382-385。
[44]旷海兰,罗可,王樱.Rough Set理论在数据挖掘中的应用[J].衡阳师范学院学报,2005,26(3):81-84
[45]祝峰,王加佳,严向奎.粗糙集理论的现状与前景[J].新疆大学学报(自然科学版),2000,17(4):1-4
[46]巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用[J].测绘学报,2003,32(1),53-57
[47]董广军,范永弘,罗睿.基于粗糙集的遥感影像分类研究[J].计算机工程与应用,2003:103-105
[48]黄金杰,李士勇,左兴权.一个基于粗糙集的水土流失防治动态决策系统[J].中国地质灾害与防治学报,2002,13(3):67-72
[49]L.P.Khoo,S.B.Tor,L.Y.Zhai.A Rough-Set-Based Approach for Classification and Rule Induction[J].Advanced Manufacturing Technology,1999,15:438-444
[50]James,F.Peters,Sheela Ramanna.Towards a Software Change Classification System:A Rough Set Approach[J].Software Quality Journal,2003,11:121-147
[51]郭平,叶莲,范丽.基于粗糙集的空间信息预处理方法[J].计算机科学,2005,32:101-104
[52]宋立松,陈武,向卫华,陈彩妮.基于粗糙集的杭州湾含沙量遥感模型[J].水利学报,2004,5:58-63
[53]胡小梅,李众立.一种基于粗糙集理论的彩色图像滤波算法[J].计算机与现代化,2003,9:11-12
[54]Tung-Hsu Hou,Chun-chi Huang.Application of fuzzy logic and variable precision rough set approach in a remote monitoring manufacturing process for diagnosis role induction[J],Journal of Intelligent Manufacturing,2004,15:395-408
[55]Theresa Beaubouef,Frederick E.Petry.Representation of spatial data in an OODB using rough and fuzzy set modeling[J].Soft Comput,2005,9:364-373
[56]刘树安,杜红涛,王晓玲.粗糙集理论与应用发展[J].系统工程理论与实践,2001,10:77-82
[57]林婷.福州市士地利用景观空间格局分析[J].福建地理,2003(3):16
[58]吴健平.区域土地利用土地覆盖遥感调查[M].上海:华东师范大学出版社,1999
[59]梅安新,彭望碌,秦其明等.遥感导论[M].北京:高等教育出版社,2001
[60]余明,廖克,李春华.福建生态环境信息图谱数据库设计与实现[J].地球信息科学2005,7(4):117-121
[61]余明,祝国瑞,李春华.地学信息图谱图形与属性信息的双向查询与检索的方法研究[J].武汉大学学报(信息版),2005,30(4):348-350,354
[62]遥感图像处理与应用[J].2002
[63]边肇祺,张学工.模式识别第2版[M],北京:清华大学出版社,2000
[64]王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005,27(12):68-71
[65]赵锋,赵荣椿.纹理分割及特征提取方法综述[J].中国体视学与图像分析,1998,3(4):238-245
[66]夏德深,傅德胜.现代影像处理技术与应用[M].南京:东南大学出版社,1997
[67]Treitz P,Howarth P.Integrating Spectral,Spatial,and Terrain Variables for Forest Ecosystem Classification[J].Photogrammetric Engineering & Remote Sensing,2000,66(3):305-317
[68]Franklin S E,Pebble D R.Spectral Texture for Improved Class Discrimination in Complex Terain[J].International Journal of Remote Sensing,1989,54:1727-173
[69]蒲俊.Matlab6.0数学手册[M].上海:浦东电子出版社,2002
[70]徐袭,刘玉波,范学鑫.基于模糊工具箱和ROSETTA的粗糙集数据挖掘[J].数据库、数据仓库、数据挖掘《微计算机信息》(管控一体化),2007,23(6-3):174-178
[71]程玉胜.Rosetta实验系统在机器学习中的应用[J].安庆师范学院学报(自然科学版),2005,11(2):69-72
[72]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M].科学出版社,2006:490
[73]王庆,巴德纯,孟祥志.基于rough sets-c4.5的故障征兆提取与判别[J].东北大学学报(自然科学版),2006,27(10):1138-1141
[74]党安荣,王晓栋等.ERDAS IMAGINE遥感影像处理方法[M].清华大学出版社,2003
[75]甘甫平,王润生,王永江等.基于遥感技术的土地利用与土地覆盖的分类方法[J].国土资源遥感,1999,42(4):39-44
[76]Anssen L L F,Vanderwel F J M.Accuracy Assessment of Satellite-derived Land-cover Data-A Review [J].Photogrammetric Engineering and Remote Sensing,1994,60(4):419-426
[77]KalkhanM A,Reich R M.Assessing the Accuracy of Landsat Thmeatic Mapper Classification Using Double Sampling[J].International Journal of Remote Sensing,1998,19(11):2049-2060
[78]Congalton R G.A review of assessing the accuracy of classifications of remotely sensed data[J].Remote Sensing of Enviroment,1991,37(1):35-46
[79]Congalton R G.A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data[J].Remote Sensing of Environment,1991,37(1):35-46
[80]Hay A M.The Derivation of Global Estimation from a Confusion Matrix[J].International Journal of Remote Sensing,1988,9(8):1395-1398
[2]李德仁,王树良,李德毅,王新洲.论空间数据挖掘和知识发现的理论与方法[J].武汉大学学报信息科学版,2002,27(3):221-233
[3]李德仁,王树良,史文中,王新洲.论空间数据挖掘和知识发现[J].武汉大学学报信息科学版,第2001,26(6):491-499
[4]王海起,王劲峰.空间数据挖掘技术研究进展[J].地理与地理信息科学,2005,21(4):6-10
[5]陈中祥,岳超源.空间数据挖掘的研究与发展[J].计算机工程与应用,2003:5-7,33
[6]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M],科学出版社,2006:1-7
[7]郭际元,江宝得,江雯倩,李洋.空间数据挖掘技术与发展趋势[J].国土资源导刊:49-50
[8]李爽,丁圣彦,许叔明.遥感影像分类方法比较研究[J].河南大学学报(自然科学版),2002,32(2):70-73
[9]莫登奎.中高分辨率遥感影像分割与信息提取研究[J].2006
[10]余达太,蓝荣钦,张世涛,关爱杰.空间数据挖掘的方法和实施[J].测绘学院学报,2003,20(2):132-134
[11]王新洲.论空间数据处理与空间数据挖掘[J].武汉大学学报信息科学版,2006,31(1):1-4,8
[12]厍向阳,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):333-338
[13]伍振军.遥感技术在数字流域中的应用研究[D].硕士论文,2002
[14]邸凯昌,李德仁,李德毅.Rough集理论及其在GIS属性分析和知识发现中的应用[J].武汉测绘科技大学学报,1999,24(1):6-10
[15]陈小瑜.基于空间数据挖掘与知识发现的遥感影像分类研究[J].硕士研究论文,2007
[16]李朝峰.基于知识发现和决策规则的遥感图像城区土地覆盖/利用分类方法[J].计算机工程与应用,2004,23:212-215
[17]邓芳,秦军,李鉴.提高遥感影像分类精度方法的研究[J].铁路航测,2003,(2):4-7
[18]陈述彭,鲁学军,周成虎.地理信息系统导论[M].北京:科学出版社,2000:3-10
[19]H J.Data MiningTechniques.ACM-SIGMOD'96 Conf.Tutorial,June,1996
[20]蒋良孝,蔡之华.空间数据挖掘的回顾与展望[J].计算机工程,2003,29(6):9-10,58
[21]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M].科学出版社,2006:278
[22]邸凯昌著.空间数据挖掘与知识发现[M].武汉大学出版社,2001:122
[23]邸凯昌.空间数据挖掘和知识发现的理论与方法[D].武汉测绘科技大学博士论文,1999
[24]Huang Xueqiao and John R.Jensen.A Machine-Learning Approach to Automated Knowledge Based Building for Remote Sensing Image Analysis with GIS Data[J].Photogrammetry Engineering and Remote Sensing,1997.63(10):1185-1184
[25]Hansen M & Dubayah R et al.Classification trees:an alternative to traditional land cover classifiers[J].International Journal of Remote Sensing,1996,17(5):1075-1081
[26]Eklund P.W,Kirbky S.D,A.Salim.Datamining and soil salimty analysis[J].Int.J.of GIS,1998,12(3):247-268
[27]Lawrence Rick L,Andrea Wright.Rule-based classification systems using classification and regression tree analysis[J].Photogrammetric Engineering & Remote Sensing,2001,67(10):1137-1142
[28]McIver D K,Friedl M A.Using prior probabilities in decision-tree classification of remotely sensed data[J].Remote Sensing of Environment,2002,81:253-261
[29]李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21
[30]申文明,王文杰,罗海江,张峰,刘小曼,熊文成.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):333-338
[31]游代安.GIS辅助的遥感影像处理与分析技术的研究[D].硕士论文,2001
[32]李爽,丁圣彦等.决策树分类方法及其在土地覆盖分类中的应用[J].遥感技术与应用,2002,17(1):6-11
[33]赵萍.基于知识的江南典型地区土地利用覆被分类研究[D].博士论文,2003
[34]陈艳丽,张万昌等.地理信息系统支持下的山区遥感影像决策树分类[J].2006(1):69-74
[35]李强.创建决策树算法的比较研究--ID3,C4.5,C5.0算法的比较.甘肃科学学报,2006,8(4):85-87
[36]季桂树,陈沛玲,宋航.决策树分类算法研究综述[J].科技广场,2007:9-12
[37]李德仁,程涛.从空间数据库中发现知识[J].测绘学报,1995,24(1):37-44
[38]李明诗.基于ASTER遥感数据的建湖县杨树信息提取的研究--分类、建模与反演制图[D].博士论文,2005
[39]Q uinlan Ross J.C4.5:Programs for Machine Learning[M].SanMate,CA:Morgan Kaufmann Publishers,1993
[40]David Hand Heikki Padhraic Smyth著.数据挖掘原理[M](廖丽,宋俊等译).北京:机械工业出版社,2003
[41]王晓国,黄韶坤,朱炜等.应用C4.5算法构造客户分类决策树的方法[J].计算机工程,2003(14): 89-91
[42]祝峰.粗糙集理论的现状与前景[J].新疆石油学院学报,2000,12(3):71-73
[43]李年攸.粗糙集理论在图像分割中的应用[J].三明学院学报,2005,22(4):382-385。
[44]旷海兰,罗可,王樱.Rough Set理论在数据挖掘中的应用[J].衡阳师范学院学报,2005,26(3):81-84
[45]祝峰,王加佳,严向奎.粗糙集理论的现状与前景[J].新疆大学学报(自然科学版),2000,17(4):1-4
[46]巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用[J].测绘学报,2003,32(1),53-57
[47]董广军,范永弘,罗睿.基于粗糙集的遥感影像分类研究[J].计算机工程与应用,2003:103-105
[48]黄金杰,李士勇,左兴权.一个基于粗糙集的水土流失防治动态决策系统[J].中国地质灾害与防治学报,2002,13(3):67-72
[49]L.P.Khoo,S.B.Tor,L.Y.Zhai.A Rough-Set-Based Approach for Classification and Rule Induction[J].Advanced Manufacturing Technology,1999,15:438-444
[50]James,F.Peters,Sheela Ramanna.Towards a Software Change Classification System:A Rough Set Approach[J].Software Quality Journal,2003,11:121-147
[51]郭平,叶莲,范丽.基于粗糙集的空间信息预处理方法[J].计算机科学,2005,32:101-104
[52]宋立松,陈武,向卫华,陈彩妮.基于粗糙集的杭州湾含沙量遥感模型[J].水利学报,2004,5:58-63
[53]胡小梅,李众立.一种基于粗糙集理论的彩色图像滤波算法[J].计算机与现代化,2003,9:11-12
[54]Tung-Hsu Hou,Chun-chi Huang.Application of fuzzy logic and variable precision rough set approach in a remote monitoring manufacturing process for diagnosis role induction[J],Journal of Intelligent Manufacturing,2004,15:395-408
[55]Theresa Beaubouef,Frederick E.Petry.Representation of spatial data in an OODB using rough and fuzzy set modeling[J].Soft Comput,2005,9:364-373
[56]刘树安,杜红涛,王晓玲.粗糙集理论与应用发展[J].系统工程理论与实践,2001,10:77-82
[57]林婷.福州市士地利用景观空间格局分析[J].福建地理,2003(3):16
[58]吴健平.区域土地利用土地覆盖遥感调查[M].上海:华东师范大学出版社,1999
[59]梅安新,彭望碌,秦其明等.遥感导论[M].北京:高等教育出版社,2001
[60]余明,廖克,李春华.福建生态环境信息图谱数据库设计与实现[J].地球信息科学2005,7(4):117-121
[61]余明,祝国瑞,李春华.地学信息图谱图形与属性信息的双向查询与检索的方法研究[J].武汉大学学报(信息版),2005,30(4):348-350,354
[62]遥感图像处理与应用[J].2002
[63]边肇祺,张学工.模式识别第2版[M],北京:清华大学出版社,2000
[64]王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005,27(12):68-71
[65]赵锋,赵荣椿.纹理分割及特征提取方法综述[J].中国体视学与图像分析,1998,3(4):238-245
[66]夏德深,傅德胜.现代影像处理技术与应用[M].南京:东南大学出版社,1997
[67]Treitz P,Howarth P.Integrating Spectral,Spatial,and Terrain Variables for Forest Ecosystem Classification[J].Photogrammetric Engineering & Remote Sensing,2000,66(3):305-317
[68]Franklin S E,Pebble D R.Spectral Texture for Improved Class Discrimination in Complex Terain[J].International Journal of Remote Sensing,1989,54:1727-173
[69]蒲俊.Matlab6.0数学手册[M].上海:浦东电子出版社,2002
[70]徐袭,刘玉波,范学鑫.基于模糊工具箱和ROSETTA的粗糙集数据挖掘[J].数据库、数据仓库、数据挖掘《微计算机信息》(管控一体化),2007,23(6-3):174-178
[71]程玉胜.Rosetta实验系统在机器学习中的应用[J].安庆师范学院学报(自然科学版),2005,11(2):69-72
[72]李德仁,王树良,李德毅著.空间数据挖掘理论与应用[M].科学出版社,2006:490
[73]王庆,巴德纯,孟祥志.基于rough sets-c4.5的故障征兆提取与判别[J].东北大学学报(自然科学版),2006,27(10):1138-1141
[74]党安荣,王晓栋等.ERDAS IMAGINE遥感影像处理方法[M].清华大学出版社,2003
[75]甘甫平,王润生,王永江等.基于遥感技术的土地利用与土地覆盖的分类方法[J].国土资源遥感,1999,42(4):39-44
[76]Anssen L L F,Vanderwel F J M.Accuracy Assessment of Satellite-derived Land-cover Data-A Review [J].Photogrammetric Engineering and Remote Sensing,1994,60(4):419-426
[77]KalkhanM A,Reich R M.Assessing the Accuracy of Landsat Thmeatic Mapper Classification Using Double Sampling[J].International Journal of Remote Sensing,1998,19(11):2049-2060
[78]Congalton R G.A review of assessing the accuracy of classifications of remotely sensed data[J].Remote Sensing of Enviroment,1991,37(1):35-46
[79]Congalton R G.A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data[J].Remote Sensing of Environment,1991,37(1):35-46
[80]Hay A M.The Derivation of Global Estimation from a Confusion Matrix[J].International Journal of Remote Sensing,1988,9(8):1395-1398