基于内容的卫星云图挖掘方法研究
|
摘要
卫星云图全面、及时、动态的反映各类云系的特点及变化过程,成为气象、水利部门在防洪抗旱决策过程中不可或缺的重要参考依据。多年的云图接收积累了数量巨大的卫星云图,依靠人工判读方式根本无法满足时效性要求,尽管一些人工智能的方法能自动完成数据分析,但这类方法只能按照设定的规则执行,不能主动发现隐含在数据内部的知识。图像挖掘技术作为数据挖掘领域研究的前沿,提供了从大量图像中获取隐含的、有价值的、可理解知识的理论及方法。本文以图像挖掘技术理论与方法为指导,设计了面向云图集和云图—雨量混合数据集的三类挖掘任务,所获得知识将对云图智能化理解和基于卫星云图的降水预测等研究具有重要价值。论文的研究工作及贡献包括以下方面:
(1)在卫星云图预处理方法研究中,提出了新的非线性自适应噪声滤除算法。该算法与常用的中值滤波技术相比,它能有效的消除椒盐噪声,保护云图中非噪声点不受影响,确保像素信息能够真实反映云内状态。云图中存在经纬线、地名等标注对象,它们会影响云图特征参数的提取。针对标注对象的形状特点,提出一种基于整体变分技术的标注对象剔除算法,通过引入权值改进了整体变分的离散化过程。结果表明算法有效剔除标注对象的同时保护了邻域信息。
(2)在云图感兴趣区域提取研究中,提出了基于云图直方图的加权聚类算法,利用该算法实现典型云区的提取。为了更加符合云图数据样本在特征空间的分布特点,重点研究了对聚类算法的改进策略:1)针对类别个数自适应确定方法的改进,提出利用遗传算法结合评价指标曲线找出最优类别数,提高算法自动化水平。2)针对相似性测度的改进,提出基于链式距离的相似性测度,克服了欧式距离测度对数据分布的敏感性问题。3)针对聚类机制的改进,引入半监督思想,既能克服单纯聚类的盲目性问题,又能避免分类面临的训练样本问题。以直方图替代云图像素作为聚类对象,大幅减少了算法处理时间。
(3)在云类智能识别的研究中,本文针对特征提取、特征选择、分类模型三个问题提出了对应的算法及模型。针对云区的无规则特性,提出了“基圆模型描述法”用于云区的描述,在此基础上提取云的形态特征参数,克服了以往算法只能提取颜色、纹理等特征的不足。为避免过拟合问题,本文采用特征曲线分析方法,从特征候选集中确定分类模型的输入特征集。本文提出将“IPSO—BP网络模型”作为分类模型。该模型采用改进的粒子群优化算法替代后向学习算法作为BP神经网络模型的学习算法,在一定程度上克服了收敛速度慢,易陷入局部极小值,过分依赖初始值的选择等不足。为了在原有分类模型框架下更好的利用多特征信息,本文提出了基于多特征融合的组合分类模型,将特征子集分别送入子分类模型后作出本地决策,采用投票表决法将多个本地决策融合后获得最终的结果。结果表明多特征融合分类模型在分类精度上优于单一分类模型。
(4)在基于云图—雨量混合数据集的关联规则挖掘研究中,本文以云图灰度和云顶亮温间的关系为基础,设计了四种与降雨关系密切的云状态参数。通过时空同步处理,云图参数和雨量数据构成统一的混合数据集。为实现数值属性的转换,本文提出一种基于聚类的数值属性分区方法,它克服了“等深度区间划分法”对数据倾斜敏感的问题。为了提高对大规模云图—雨量混合数据集的处理效率,本文提出了基于数据分割的两阶段关联规则挖掘算法,它通过将原始数据库划分为多个独立的区间,由每个子区间的局部频繁项集产生全局候选项集,并设计了专门用于支持度计算的数据结构tidlists ,这些策略有效的减少了算法对数据库的扫描次数,大幅提高了算法的效率。结果表明当支持度阈值处于较低水平时,本文算法的执行效率显著优于Apriori算法的执行效率。
The satellite cloud image which can reflect the characteristics and changing process of cloud system has become a very important reference factor to give the flood and drought forecast. The cloud image archive is a huge information resource. It is a difficult and time-consuming work to interpret these images manually. Although some artificial intelligence techniques can automatically accomplish the data analysis, they can’t abstract the latent knowledge that embedded in the data, for these techniques strictly followed some predefined rules. As the Frontiers of the Discipline, the image mining (IM) technology provides the theory and methods of abstracting unaware, potential, comprehensible and useful information and knowledge from the cloud image archives. Three kinds of image mining tasks facing mixed data sets consisting of cloud image and rainfall data is designed in this thesis, and the acquired knowledge is much valuable for cloud image content understanding and rainfall forecasting. The primary work includes the following aspects.
(1)In the research of the cloud image preprocessing, a new nonlinear adapted de-noising algorithm is proposed. Compared with the classical median filter, the proposed algorithm shows a better performance in term of eliminating the salty and pepper noise. The algorithm can preserve the non-noise pixel from being changed. Therefore, it is guaranteed that the pixel information truly reflects the state of cloud. The cloud image which includes some labeling objects such as longitude, latitude and placename, may influence the feature extracting. Considering that most of the labeled objects are line objects, a TV based labeling objects eliminating algorithm is proposed. The method improves the discretization by introducing the weight strategy. Experiments show that the improved algorithm efficiently eliminates the objects at the same time preserving the neighborhood information.
(2)In the research of the ROI extracting method, the thesis develop a weighted clustering method based on the cloud image histogram. The algorithm fulfills the representative cloud domain extraction. In order to adapt to the sample distribution in the feature space, we focus on the improving of the clustering algorithm strategy. There are three strategies: The first strategy is focused on the improvements on the clustering number self-confirming method. A genetic algorithm confirming the optimized clustering number combing the evaluating index is proposed. This strategy improves the automatic level. The second strategy is focused on the improvements on the similarity measurements. A link-distance similarity measurement is proposed. Different from Euclidian distance, the link-distance is not sensitive to the data distribution. The third strategy is focused on the clustering mechanism. The Semi-supervised method which can overcome the blindness brought by the single clustering also can avoid the requirement of many training samples for the classification, is proposed. Finally, to reduce the time spending, the histogram of cloud image is used as the clustering object instead of the origin cloud image pixels.
(3)In the research of cloud classification, three algorithms are proposed corresponding to the feature extraction, the feature selection and the classification model. To deal with the irregularity of cloud domain, the‘basic round description model’is proposed to describe the cloud domain. The shape features are extracted based on this model and combined with the color and texture to form a comprehensive candidate feature sets. Also, a‘BP-IPSO’model that adopts pso optimizing algorithm as learning algorithm instead of the bp neural network algorithm is proposed. The BP-IPSO model deals with the problems of slow convergence speed, easily falling into local minimum, and sensitive to the initial value. To efficiently fuse multiple features under the original classification mechanism, we developed a multiple features combination classification model. The local decisions made by child classification model are used to form the final decision by the voting method. Compared with the single classification model, the combination classification model acquires higher accuracy.
(4)In the research of association rules mining based on the cloud-rainfall mixture data, four kinds of parameters which can reflecting the cloud state, is introduced. These state parameters take the relation between the grayscale of cloud image and the temperature of cloud top as the basis. Cloud state parameters and rainfall constitute the uniform mixture data through the synchronizing of time and space. To implement the transform of numerical attribute, a numerical attribute partition algorithm based on the clustering technology is proposed. The algorithm deals with the problem that the equal-depth partition method is sensitive to the data skew. To improve the processing efficient of large scale cloud-rainfall mixture dataset, a‘Two-step Association Rules Mining based on the data partition’algorithm is proposed. Firstly, the algorithm partitions the database into several independent intervals. The global candidate itemsets are generated by the local large itemsets in each interval. Finally, we designed the‘tidlists’data structure for the support count. These strategies improve the efficiency of the method by reducing the database scanning. It is proved that the method executes much more efficiently than Apriori method when the support threshold is low.
(1)在卫星云图预处理方法研究中,提出了新的非线性自适应噪声滤除算法。该算法与常用的中值滤波技术相比,它能有效的消除椒盐噪声,保护云图中非噪声点不受影响,确保像素信息能够真实反映云内状态。云图中存在经纬线、地名等标注对象,它们会影响云图特征参数的提取。针对标注对象的形状特点,提出一种基于整体变分技术的标注对象剔除算法,通过引入权值改进了整体变分的离散化过程。结果表明算法有效剔除标注对象的同时保护了邻域信息。
(2)在云图感兴趣区域提取研究中,提出了基于云图直方图的加权聚类算法,利用该算法实现典型云区的提取。为了更加符合云图数据样本在特征空间的分布特点,重点研究了对聚类算法的改进策略:1)针对类别个数自适应确定方法的改进,提出利用遗传算法结合评价指标曲线找出最优类别数,提高算法自动化水平。2)针对相似性测度的改进,提出基于链式距离的相似性测度,克服了欧式距离测度对数据分布的敏感性问题。3)针对聚类机制的改进,引入半监督思想,既能克服单纯聚类的盲目性问题,又能避免分类面临的训练样本问题。以直方图替代云图像素作为聚类对象,大幅减少了算法处理时间。
(3)在云类智能识别的研究中,本文针对特征提取、特征选择、分类模型三个问题提出了对应的算法及模型。针对云区的无规则特性,提出了“基圆模型描述法”用于云区的描述,在此基础上提取云的形态特征参数,克服了以往算法只能提取颜色、纹理等特征的不足。为避免过拟合问题,本文采用特征曲线分析方法,从特征候选集中确定分类模型的输入特征集。本文提出将“IPSO—BP网络模型”作为分类模型。该模型采用改进的粒子群优化算法替代后向学习算法作为BP神经网络模型的学习算法,在一定程度上克服了收敛速度慢,易陷入局部极小值,过分依赖初始值的选择等不足。为了在原有分类模型框架下更好的利用多特征信息,本文提出了基于多特征融合的组合分类模型,将特征子集分别送入子分类模型后作出本地决策,采用投票表决法将多个本地决策融合后获得最终的结果。结果表明多特征融合分类模型在分类精度上优于单一分类模型。
(4)在基于云图—雨量混合数据集的关联规则挖掘研究中,本文以云图灰度和云顶亮温间的关系为基础,设计了四种与降雨关系密切的云状态参数。通过时空同步处理,云图参数和雨量数据构成统一的混合数据集。为实现数值属性的转换,本文提出一种基于聚类的数值属性分区方法,它克服了“等深度区间划分法”对数据倾斜敏感的问题。为了提高对大规模云图—雨量混合数据集的处理效率,本文提出了基于数据分割的两阶段关联规则挖掘算法,它通过将原始数据库划分为多个独立的区间,由每个子区间的局部频繁项集产生全局候选项集,并设计了专门用于支持度计算的数据结构tidlists ,这些策略有效的减少了算法对数据库的扫描次数,大幅提高了算法的效率。结果表明当支持度阈值处于较低水平时,本文算法的执行效率显著优于Apriori算法的执行效率。
The satellite cloud image which can reflect the characteristics and changing process of cloud system has become a very important reference factor to give the flood and drought forecast. The cloud image archive is a huge information resource. It is a difficult and time-consuming work to interpret these images manually. Although some artificial intelligence techniques can automatically accomplish the data analysis, they can’t abstract the latent knowledge that embedded in the data, for these techniques strictly followed some predefined rules. As the Frontiers of the Discipline, the image mining (IM) technology provides the theory and methods of abstracting unaware, potential, comprehensible and useful information and knowledge from the cloud image archives. Three kinds of image mining tasks facing mixed data sets consisting of cloud image and rainfall data is designed in this thesis, and the acquired knowledge is much valuable for cloud image content understanding and rainfall forecasting. The primary work includes the following aspects.
(1)In the research of the cloud image preprocessing, a new nonlinear adapted de-noising algorithm is proposed. Compared with the classical median filter, the proposed algorithm shows a better performance in term of eliminating the salty and pepper noise. The algorithm can preserve the non-noise pixel from being changed. Therefore, it is guaranteed that the pixel information truly reflects the state of cloud. The cloud image which includes some labeling objects such as longitude, latitude and placename, may influence the feature extracting. Considering that most of the labeled objects are line objects, a TV based labeling objects eliminating algorithm is proposed. The method improves the discretization by introducing the weight strategy. Experiments show that the improved algorithm efficiently eliminates the objects at the same time preserving the neighborhood information.
(2)In the research of the ROI extracting method, the thesis develop a weighted clustering method based on the cloud image histogram. The algorithm fulfills the representative cloud domain extraction. In order to adapt to the sample distribution in the feature space, we focus on the improving of the clustering algorithm strategy. There are three strategies: The first strategy is focused on the improvements on the clustering number self-confirming method. A genetic algorithm confirming the optimized clustering number combing the evaluating index is proposed. This strategy improves the automatic level. The second strategy is focused on the improvements on the similarity measurements. A link-distance similarity measurement is proposed. Different from Euclidian distance, the link-distance is not sensitive to the data distribution. The third strategy is focused on the clustering mechanism. The Semi-supervised method which can overcome the blindness brought by the single clustering also can avoid the requirement of many training samples for the classification, is proposed. Finally, to reduce the time spending, the histogram of cloud image is used as the clustering object instead of the origin cloud image pixels.
(3)In the research of cloud classification, three algorithms are proposed corresponding to the feature extraction, the feature selection and the classification model. To deal with the irregularity of cloud domain, the‘basic round description model’is proposed to describe the cloud domain. The shape features are extracted based on this model and combined with the color and texture to form a comprehensive candidate feature sets. Also, a‘BP-IPSO’model that adopts pso optimizing algorithm as learning algorithm instead of the bp neural network algorithm is proposed. The BP-IPSO model deals with the problems of slow convergence speed, easily falling into local minimum, and sensitive to the initial value. To efficiently fuse multiple features under the original classification mechanism, we developed a multiple features combination classification model. The local decisions made by child classification model are used to form the final decision by the voting method. Compared with the single classification model, the combination classification model acquires higher accuracy.
(4)In the research of association rules mining based on the cloud-rainfall mixture data, four kinds of parameters which can reflecting the cloud state, is introduced. These state parameters take the relation between the grayscale of cloud image and the temperature of cloud top as the basis. Cloud state parameters and rainfall constitute the uniform mixture data through the synchronizing of time and space. To implement the transform of numerical attribute, a numerical attribute partition algorithm based on the clustering technology is proposed. The algorithm deals with the problem that the equal-depth partition method is sensitive to the data skew. To improve the processing efficient of large scale cloud-rainfall mixture dataset, a‘Two-step Association Rules Mining based on the data partition’algorithm is proposed. Firstly, the algorithm partitions the database into several independent intervals. The global candidate itemsets are generated by the local large itemsets in each interval. Finally, we designed the‘tidlists’data structure for the support count. These strategies improve the efficiency of the method by reducing the database scanning. It is proved that the method executes much more efficiently than Apriori method when the support threshold is low.
引文
[1]叶泽刚.利用气象卫星云图进行洪水预警探讨-湖南95.7和96.7洪水云图变化过程分析.中南水力发电[J],1999.
[2]叶泽刚,沈寿珊.湖南省防汛信息服务系统建设与应用.计算机系统应用,1996.
[3]史忠植.知识发现[M].北京:清华大学出版社,2002.
[4] Han Jiawei, Kambr Micheline. Data mining: conceptes and techniques[M]. Morgan Kaufmann Publishers,2001.
[5] Fayyad U. Data mining and knowledge discovery in databases[J], Communications of the ACM,1996, 139(11):24-26.
[6] R.Brachman,T.Anand. Data archeology. In knowledge discovery in databases[C], AAAI workshop (KDD'93): 1993.
[7] SPSS Inc. Neural connection applications guide, Chicago: SPSS Inc,1995.
[8] Fayyad U. Branching on Attribute values in decision tree generation[C]. In proceeding of the twelfth national conference on artifical intelligence AAAI-94, 1994:601-606.
[9] Fayyad U., Irani K.B. The attribute selection problem in decision tree generation[C]. In proceedings of the tenth national conference on artifical intelligence AAAI-92,1992 (104-110).
[10] Fayyad U. Weir.N and Djorgovski.S. Skicat: A machine learning system for the automated cataloging of large-scale sky surveys[C]. In proceeding of .the Tenth international conference on machine learning,1993(112-119).
[11] Flickner M.,Sawhney., Niblack W. Query byimage and video content: The QBIC system. IEEE Computer[J],1995,28(9):23~22.
[12] Smith J R., Chang S-F. Visually seaching the web for content[J]. IEEE Multimedia Magazine, 1997,4(3): 12~20.
[13] Wactlar H, Hauptmann A, Witbrock M. Informedia: News-on-demand experiments in speech recognition[C]. In Proceedings of ARPA Speech Recognition Workshop. Arden House, Harriman, NY, 1996: 18~21.
[14] Simeon J. Variations on multimedia data mining.[C] In Proceedings of theInternational Workshop on Multimedia Data Mining, Boston,USA,2000.
[15] Simeon J, Simoff, Osmar R Z. Report on MDM/KDD2000[C]: The 1st International Workshop on Multimedia Data Mining. SIGKDD Explorations, 2001,2(2):103~105.
[16] Zajane O R, . Multimediaminer: Asystem prototype: for multimedia data mining[C]. In Proceedings of ACM SIGMOD Conf. on Management of Data,Seattle, 1998: 581~583.
[17] Wijesekera Duminda, Barbara aniel. Mining cinematic Knowledge: an extended abstract[C]. MDM/KDD2000. Boston,MA,USA,2000.
[18] Matsuo Yuya, Shirahama Kimiaki, Uehara Kuniaki. Video data mining: extracting cinmatic rules from movie[C]. SIGKDD,2003:24~27.
[19] Lienhart R, Pfeiffer S. Video abstracting[C]. Communications of the ACM, 1997,40(12):55~62.
[20] Zhu Xingquan, Fan Jianping, Aref Walid G. ClassMiner: Mining medical video content structure and events towards efficient access and scalable skimming[C]. Proc. ACM SIGMOD Workshop, Madison,WI,2002:9~16.
[21] Zhu Xing-Quan, Wu Xindong. Sequential association mining for video summarization[C]. Proc. of IEEE Int, Conf. on Multimedia,Baltimore,2003(3):333~336.
[22] M. Datcu,K. Seidel. In summary, image mining is a promising field for Image information mining: exploration of image content in large archives[C], IEEE Conference on Aerospace, 2000(3).
[23] O. R. Zaiane, J. W. Han. Mining MultiMedia Data[C], CASCON'98: Meeting of Minds, Toronto, Canada,1998(83-96).
[24] Michael C.Burl, Charless Fowlkes, Joe Rodem, Andre Stechert. Diomond Eye: A Distributed Architecture for Image Data Mining[C], SPIE DMKD, Orlando,1999.
[25] J Zhang. An Information-driven Framwork for Image Mining[C]. In Proceeding of 12th Int Con on Database and Expert Systems Applications DEXA, Munich, Germany,2001.
[26] J.S.D., Bonet. Image preprocessing for rapid selection in "Pay attention mode"[J], MIT,2000.
[27] M.C Burl., Mining for image content[J]. In Systemics,Cybernetrics,and Informatics / Information Systems: Analysis and Synthesis,1999.
[28] Gibson,S., Intelligent mining in image databases[J]. with applications to satellite imaging and to web search, Data Mining and Computational Intelligence, 2001.
[29] Michael. C, Burl and Charless. F, Joesph. R. Mining for image content[C].in Systemics, Cybernetics, and Informatics/ Information System: Analysis and synthesis, 1999.
[30] R. Kazman, J. Kominek. Information organization in multimedia resources[C], Proceedings of the 11th annual international conference on Systems documentation, 1993:149~162.
[31] Y.Rui., T.S.Huang. Image retrieval: Past, present and future[C], Int Symposium on Multimedia Information Processing, 1997.
[32] K .Lin, H.V. Jagadish, C. Faloutscs. The TVtree: An index structure for high -dimentional data[J], The VLDB ,1994,3(4):517~542.
[33] T. Sellis, N. Roussopoulos, C.Faloutscs. The R+ tree: A dynamic index for multi-dimentional objects[C], In Proc 12th VLDB, 1987.
[34] D White, R.Jain. Similarity indexing: Algorithms and performance[C], In Proc. SPIE Storage and Retrival for image and Video Databases, 1996.
[35] A. Vailaya, A.T.Figueiredo, A.K.Jain,H.J.Zhang. Image classification for content-based indexing[J], IEEE Transactions on Image Processing, 2001.
[36] R.F.Cromp, W.J.Campbell. Data mining of multi-dimentional remotely sensed images[C], International Conference on Information and Knowledge Management(CIKM), 1993.
[37] J.Z.Wang, J.Li. System for Screening Objectionable image Using Daubechies' Wavelets and Color Histograms, Interactive Distributed Multimedia Systems and Telecommunication Services[C], Proceedings of the Fourth European Workshop(IDMS'97), 1997.
[38] A.K.Jain, M.N.Murty, P.J.Flynn. Data clustering: a review[C], ACM Computing survey, 1999.
[39] V.Megalooikonomou, C.Davataikos, E.H.Herskovits. Mining lesion-defict associations in a brain image database[C], KDD San Diego,CA USA, 1999.
[40] C.Ordonez, E.Omiecinski. Discovering association rules based on image content[C], Proceedings of the IEEE Advanced in Digital Libraries Conference(ADL'99), 1999.
[41] Turkey. W. Exploratory data analysis[M], Addison-Wesley, New York,1971.
[42] kim V, Yaroslavskii L. Rank algorithm for picture processing[J], Computer Vision Graphics, Image Processing. 1986,35(2):234~258.
[43] Lin H M, Willson A N. Median Fiters with adaptive length[J], IEEE CASI, 1988, 35(6): 675~690.
[44] Florencio D A F, Schafer R W. Decision-based median filter using local signal statistice[C], In: Proc SPIE Syme. Visual Comm. Image Processing, Chicago, 1994, 2308:268~275.
[45] Hardie R E, Barner K E. Rank condition rank selection filters for signal restoration[J], IEEE IP, 1994,3(2): 192~206.
[46] Kim S. R., Effort A. Adaptive robust impulse noise filtering[J], IEEE Trans. Signal Processing , 1995,43(8): 1855~1866.
[47] Abreu E, Lightone M, Mitra S K. A new efficient approach for the removal of impulse noise from highly corrupted images[J], IEEE IP,1996,5(6):1012~1025.
[48] Zhang D., Wang Z. Impulse noise detection and removal using fuzzy techniques[J]. Electronics Letters, 1997 ,33(5):378~379.
[49] Wang Z., Zhang D. Restoration of impulse noise corrupted images using long—range correlation[J]. IEEE Signal Processing Letter, 1998, 1(5):4~7.
[50] Jiawei Han, Micheline Kamber著范明,孟小峰等译Data Mining Conceptes and Techniques[M],北京:机械工业出版社, 2001.
[51] Chris Ding. A Tutorial on Spectral Clustering[C]. ICML, 2004.
[52] Ester M, Kriegel H-P, Sander J. A Denity-based A lgorithm for Discovering Cluster in Large Spatial Databases with Noise[C]. Portland: Proceedings of the 2nd ACM SIGKDD, 1996, 226~231.
[53] Hinneburg A, Keim D. An Efficent Approach to Clustering Large Multimedia Databases with Noise[C]. New York: Proceedings of the 4th ACM SIGKDD,1998, 58~65.
[54] Wang W, Yang J, Muntz R. STING: A Statistical Information Grid Approach to Spatial Data Mining[C], Athens Proceedings of the 23rd Conference on VLDB,1997,186~195.
[55] Wang W, Yang J, Muntz R R. STNG +:An Approach to Active Spatial Data Ming[C]:Sydney: Proceedings of the 15th ICDE, 1999, 116~125.
[56] Agrawal R, Gehrke J, Gunopulos D. Automatic Subspace Clustering of High Dimensional Data for Data Mining Applications[C]. Seatlle: Proceedings of the ACM SKIMOD Conference, 1998, 94~105.
[57]陈国良,王煦法,庄镇泉等.遗传算法及其应用[M].北京:人民邮电出版社, 1996.
[58]周明,孙树栋.遗传算法原理及应用[M],北京:国防工业出版社, 2001.
[59]陈文伟.智能决策技术[M],北京:电子工业出版社, 1998.
[60] B.Fischer, J.M.Buhmann. Bagging for Path-Based Clustering[J], IEEE Trans.Pattern Analysis and Machine Intelligence, 2003, 25(11):1411~1415.
[61] B.Fischer, J.M.Buhmann. Path-Based Clusetring for Grouping Smooth Curves and Texture Segmentation[J], IEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25(4):513~518.
[62]邹进上等,大气物理学[M],气象出版社, 1982.
[63]吴伯雄,大气物理基础[M],江苏科学技术出版社, 1980.
[64] Adler,R.F., A.J.Negri,1998,A satellite infrared technique to estimate tropiical convective and stratiform rainfall[J], Appl. Meteor. ,1998, 27:31~51.
[65] Adler, R.F., R.A.Mack. Thunderstorm cloud height -rainfall rate relations for use with satellite rainfall estimation techniques[J], Appl. Meteor.,1984, 23:280~296.
[66]杨行峻,郑君里.人工神经网络[M],北京:高等教育出版社, 1992.
[67]罗四维,人工神经网络建模[M],北京:中国铁道出版社, 1998.
[68]王耀生,冯晓娟.卫星云图的计算机分析识别[J],气象, 1994, 20(6):24~32.
[69]刘正光,林孔元,郭爱民.卫星云图形态特征提取[J].计算机研究与发展,1997, 34(9): 689~693.
[70] Kitamoto A, Takagi M. Retrieval satellite cloud imagery based on subjective similarity[C]. Scandinavia: 9th Scandinavian Conference on Image Analysis (SCIA95), 1995:449~456.
[71] Gibson S, Mirtich B. A survey of deformable modeling in computer graphics[R], Cambridge: Mitsubishi Electric Research Lab,1997:1~33.
[72] Press W, Teukolsky S, Vetterling W. Numerical recipes in C[EB/OL], http://www.library comell edu/nr/bookcpdf html, 1992: 425~429.
[73] George G, Paull R. Incorporation shap into histograms for CBIR[J], Pattern Recognition, 2002, 35(11):81~91.
[74] Borgefors G. Hierarchical chamfer matching A parametric edge matching algorithm[J], IEEE Transactions on Pattern Analyse and Machine Intelligence, 1988, 10(6): 849~865.
[75] Koffler R. A Procedure for Estimating Cloud Amount and Height from Satellite Infrared Radiation Data[J], MonWeaRev, 1973, 101:240~243.
[76] Shenk W E, Holub R T, Neff R A. A Multispectral Cloud Type Identification Method Developed for Tropical Ocean Area with Nimbus-3 MRIR Measurements[J], Mon Wea Rev, 1976, 104: 284~291 [J].
[77] Haralick R M, Shanmugam K, Dinstein I Textural Features for Image Classification [J], IEEE Trans Sys Man Cybern, 1973, 3:610~621.
[78] Weszka J S, Dyer C R, Rosenfeld A. A Comparative Study of Texture Measurements for Terrain Classification [J], IEEE Trans Syst Man Cybern,1976, 6:269~285.
[79] Welch R M, Sengupta S K, Chen D W. Cloud Field Classification Based Upon High Spatial Resolution Textual Features, Part I, Gray level Cooccurence Matrix Approach [J], J Geophys Res, 1988, 93:12663~12681.
[80] Welch R M, Sengupta S K, Goroch A K. Polar Cloud and Surface Classification Using AVHRR Imagery: An Intercomparison of Methods[J], J Appl Meteoro 1992, 31: 405~420.
[81]李俊,周凤仙.气象卫星台风云图的自动识别方法及其应用[J].应用气象学报, 1992 ,3(4):402~409.
[82]师春香,翟建华.用神经网络方法对NOAA-AVHRR资料进行客观分类[J].气象学报, 2002, 60(2):250~255.
[83] R.Caruana, D.Freitag. Greedy Attribute Selection[C], 11th International Conference on Machine Learning, 1994.
[84] G.Castelano, A.M.Fanelli, M.Pelillo. An Iterative Prunning Algorithm for Feedforward Neural Networks, IEEE Transaction on Neural Networks, 1997,8(3):519~531.
[85] I.Kononenko. Estimation attributes: Analysis and Extensions of RELIEF[C], European Conference on Machine Learning, Catana,Italy, 1994:171~182.
[86] P.Pudil, J.NovoVicova, J.Kittler. Floating Search Methods in Feature Selection[J], Pattern Recognition Letters, 1994, 15:1119~1125.
[87] Reynold D.W., T.H. Vonder Haar. A Bispectral Method for Cloud Parameter Determination[J], Monthly Weather Review, 1977, 105:447~457.
[88] Hayden C.M. GOES/VAS Simultaneous Temperature Retrieval Algorithm[J], Journal of Applied Meteorology, 1988, 27:705~733.
[89] Derrien M., H. Le.Gleau. Cloud Classification Extracted from AVHRR and GOES Imagery[EB/OL], http://www.meteorologie.eu.org/safnwc/, 1992.
[90]郁凡,陈渭民.双光谱云图的云分类探讨[J],南京气象学院学报, 1994, 17(1):117~125.
[91] Stowe L. Evaluation of NLMBUS-7 THIR/CLE and Air Force Three-dimensional Nephanalysis Estimates of Cloud Amont[J], Journal of GeophysicalResearch, 1984, 89:5370~5380.
[92] Coakley J.A. , F.P.Bretherton. Cloud Cover from High-Resolution Scanner Data: Detecting and Allowing for Partially Filled Files of View[J], Journalof Geophysical Research, 1982, 87:4917~4832.
[93] Koffler R., A.G. DeCotiis, P.K. Rao. A Procedure for Estimation Cloud Amount and Height from Satellite Infrared Radiation Data[J], Monthly Weather Review, 1973, 101:240~243.
[94] Welch R.M., S.K. Sengupta, K.S. Kuo. Marine Stratocumulus Cloud Fields off the Coast of Southern California Observed Using Landsat Imagery. Part II : Textual Analysis[J], Journal of Applied Meteorology, 1988, 27:362~378.
[95] Desbois M., G. Seze, G. Szejwach. Automatic Classification of Clouds on METEOSAT Imagery Application to High-level Cloud[J], Journal of Applied Meteorogy, 1982 ,21:401~412.
[96] Welch R.M., Navar M.S., Sengupta S.K. The effect of Resolution upon Texture-based Cloud Field Classification[J], Jounal of Geophysical Research, 1989, 94:14767~14781.
[97] Key J., J.A.Maslanik, A.J. Schweiger. Classification of Merged AVHRR and SMMR Arctic Data With Neural Netwoks[J], Photogrammetric Engineering and Remote Sensing, 1989, 55(9):1331~1338.
[98] Lee J., Weger R.C., Sengupta S.W. A Neural Network Approach to CloudClassification[J], IEEE Transaction on Geosciences and Remote Sensing, 1990, 28(5):846~855.
[99]蒋德明,陈渭民.基于径向基函数网络的云自动分类研究[J].南京气象学院学报, 2003, 26(1):89~96.
[100] Richard O.Duda, Peter E. Hart, David G.Stork.模式分类(2)[M].北京:机械工业出版社, 2003.
[101] Hornk K, Stinchcombe M, White H. Mutilayer Feedfoeword Networks Are Universal Approximates[J], Neural Networks, 1989, 2:359~366.
[102] Hornk K, Stinchcombe M, White H. Universal Approximation of an Unknown Mapping and Its Derivatives Using Mutilayer Feedforward Networks[J], Neural Networks, 1990, 3:551~560.
[103] Sexton R S, Dorsey R E. Reliable Classification using neural networks: a genetic algorithm and backprogation compassion[J], Decision Support System, 2000, 30(1):11~22.
[104] Kennedy J., Eberhart R. Particle Swarm Optimization[C], In: IEEE Int'l Conf on Neural Network, Perth, Australia, 1995: 1942~1948.
[105]杨燕,靳蕃, Kamel M.微粒群优化算法研究现状及其进展[J],计算机工程,2004, 30(21):3~4.
[106]谢晓峰,张文俊,杨文廉.微粒群算法综述[J],控制与决策, 2003, 18(2): 129~134.
[107]李爱国,覃征,鲍复民.粒子群优化算法[J].计算机工程与应用, 2002, 38(21):1~3.
[108] Van den F B, Engelbrecht AP. Cooperative Learning in Neural Networks using Particle Swarm Optimizer[C], In: Proc. SAICSIT, 2000.
[109]孙即祥.现代模式识别[M],长沙:国防科技大学出版社, 2002.
[110] L.Lam, C.Y.Suen. Application of majority voting to pattern recognition: an analysis of its behavior and performance[J]. IEEE Trans. on SMC part A. 1997, 27(5):553~568.
[111]叶泽刚.湖南大型水库防洪调度决策支持系统开发及应用[J],计算机系统应用, 1999.
[112]易宏杰. BP网络原理及应用研究[D],硕士,中国海洋大学, 2004.
[113]师春香,卢乃锰,张文建.卫星面降水估计人工神经网络[J],气候与环境研究, 2001, 6(4):467~472.
[114]师春香,谢正辉.基于静止气象卫星观测的降水时间降尺度研究[J],地理科学进展, 2008, 27(4):16~22.
[115]师春香,卢乃锰,张文建.卫星面降水估计人工神经网络方法[J],大气与环境研究, 2001, 6(4).
[116]卢乃锰,吴蓉璋.强对流降水云团的云图特征分析[J],应用气象学报, 1997,8(3):269~275.
[117]卢乃锰,师春香,张文健.卫星降水估计结果与地面观测结果的融合技术[J],淮河流域能量与水分循环研究(一),北京:气象出版社,1999:125~129.
[118]李伟钢,石利华.气象卫星云图多分辨小波分解及人工神经网络降水估计研究[J],南京气象学院学报, 2000, 23(2):272~282.
[119]王彦磊,刘巍,张韧,陈奕德,王辉赞,黄志松.基于云分类和降水先验知识的卫星云图降水估计[J],应用基础与工程科学学报, 2002(14).
[120]王彦磊,江海英,赵中军,李文才,张韧.多光谱卫星云图降水区域与强度估计的模糊推理模型[J].解放军理工大学学报(自然科学版), 2007, 8(2).
[121]张韧,王彦磊.云类降水知识提取与卫星云图降水估计[C].会议征文: Session 1-大气综合探测技术, 2006.
[122]马力军,关联规则算法性能分析与仿真研究[D],西安交通大学硕士学位论文.
[123] R.Agrawal. Database mining: A performance perspective[J], IEEE transactions on knowledge and data engineering, 1993, 5(6):914~925.
[124] S.Brin, R.Motwani, C.Silverstein. Beyond market basket: Generalizing association rules to correlations[C], In Proc. ACM-SIGMOD Int. Conf. Management of data (SIGMOD'97), 1997:265-276.
[125] N.Pasquier, Y.Bastide, R.Taouil, L.Lakhal. Discovering frequent closed itemsets for association rules[C]. In Proc. 7thInt. Conf. Database Theory(ICDT'99), 1999:398-416.
[126] Jian. Ma, Ballantyne,S.B. LandSat Thematic Used to Mapper with ground truth element distribution : an example from British Cokunbi Golden Triangle Dneriet, Program with Abstracts[J], GSC Forum, Canada, 1992.
[127] QiW Z, Zheng X B. Application of Weather Satellite Image on Precipitation Forecast System[J], Electri Power of Central China, 2001, 14(3):57~59.
[128]卢乃锰,师春香,张文健.卫星降水估计结果与地面降水观测结果的融合技术[J],淮河流域能量与水分循环研究(一),北京:气象出版社, 1999, 125~129.
[129]卢乃锰,吴蓉璋.强对流降水云团的云团特征分析[J],应用气象学报, 1997,8(3):269~275.
[130]师春香,谢正辉.基于静止气象卫星观测的降水时间降尺度研究[J].地理科学进展, 2008, 27(4).
[131] Fukuda T, Morimoto Y, Morishita S. Mining optimized association rules for numeric attributes[C], In Proceedings of the Fifteenth ACM SIGMOD-SIGART Symposium on Principles of Database Systems, Montreal ,Canada, 1996:182~191.
[132] R. Agrawal, R.Srikant. Fast algorithms for mining association rules in large databases[C]. In Proceedings of the 20th international Conference on Very Large Data Bases, Santiago, Chile, 1994.
[133] R. Agrawal, T.Imielinski, A.Swami. Mining association rules between sets of items in large databases[C], In Proceedings of 1993 ACM SIGMOD International Conference on Management of Data, 1993:207-216.
[134]谷晓平,王长耀,王汶. GMS5红外卫星云图参数化及在降水预测中的应用[J],遥感学报, 2005, 9(4).
[135] Weir.N, Djorgoveski. S, Fayyad. U, Roden. J, Roquette. N. SKICAT:A system for the scientific analysis of Palomar—STSCI Digital Sky Survey[C], In Proceeding of the ESO Conference , Haguenau, 1992.
[136] Rudin. L, Osher. S, Fatemi E. Nonlinear total variation based noise removal algorithms[C]. In Proceedings of Mddiz.Mat.Traitement d’Images, INRIA, 1992:149~179.
[137] Rudin.L, Osher.S. Total variation based image restoration with free local constrains[C]. In Proceedings of IEEE International Conference on Image Processing, Austin,1994:31~35.
[138]罗炳伟,余沪涛,江晓.细胞图像分割的新方法.电子科技大学学报[J]. 1990,19(1): 54~59.
[139] Pal. N.R, Bezdek.J.C. On cluster validity for the fuzzy c-means model[J]. IEEE Trans Fuzzy System, 1995, 3(3):370~379.
[140] Magurran.A.E. Ecological Diversity and Its Measurement[M]. New Jersey, Princeton University Press, 1988.
[141] Dunn.J.C. Well-seperated clusters and the optimal fuzzy partitions[J]. Cybernet, 1974,4(1):95~104.
[142] Bezdek.J.C. Pattern recognition with fuzzy objective function algorithms[R]. Plenum Press, New York, 1981.
[143] Bezdek.J.C. Clustering validity with fuzzy sets[J]. Mathematical Biology, 1974, 1:57~71.
[144] Windham.M.P. Cluster validity for fuzzy clustering algorithms[J]. FSS, 1981, 5(2):177~185.
[145] Windham.M.P. Cluster validity for fuzzy c-means clustering algorithms[J]. IEEE Trans. PAMI, 1982,4(4):357~363.
[146] Gunderson.R.G. Applications of fuzzy ISODATA algorithms to startracker printing systems[C]. In Proc. 7 th Triennual World IFAC Congress, 1978:1319~1323.
[147] Xie.X.L., Beni.G. A validity measure for fuzzy clustering[J]. IEEE Trans. PAMI, 1991, 13:841~847.
[148] Bensaid.A.M., Hall.L.O. Validity-guided clustering with applications to image segmentation. IEEE Trans. FS, 1996, 4(2):112~122.
[149] Jain.A.K., Moreau.J.V. Bootatrap techniques in cluster analysis[J]. PR, 1987,20(5):347~363.
[150] Beni.C., Liu.M.X. A least biased fuzzy clustering method. IEEE Trans. PAMI, 1992, 16(9):954~960.
[151] Li.J., Gao.X.B., Jiao.L.C. A new cluster validity function based on the modified partition fuzzy degree[C]. In Proceeding of Fourth International Conference on Rough Sets and Current Trends in Computing(RSCTC), 2004, 3066:586~591.
[152]范九伦.模糊聚类有效性研究[D].西安,西安电子科技大学,1998:30~36.
[153] Franchini. M. Use of a genetic algorithm combined with a local search method for the automatic calibration of conceptual rainfall-runoff models[J]. Hydrological Science Journal, 1996, 41(1):21~39.
[2]叶泽刚,沈寿珊.湖南省防汛信息服务系统建设与应用.计算机系统应用,1996.
[3]史忠植.知识发现[M].北京:清华大学出版社,2002.
[4] Han Jiawei, Kambr Micheline. Data mining: conceptes and techniques[M]. Morgan Kaufmann Publishers,2001.
[5] Fayyad U. Data mining and knowledge discovery in databases[J], Communications of the ACM,1996, 139(11):24-26.
[6] R.Brachman,T.Anand. Data archeology. In knowledge discovery in databases[C], AAAI workshop (KDD'93): 1993.
[7] SPSS Inc. Neural connection applications guide, Chicago: SPSS Inc,1995.
[8] Fayyad U. Branching on Attribute values in decision tree generation[C]. In proceeding of the twelfth national conference on artifical intelligence AAAI-94, 1994:601-606.
[9] Fayyad U., Irani K.B. The attribute selection problem in decision tree generation[C]. In proceedings of the tenth national conference on artifical intelligence AAAI-92,1992 (104-110).
[10] Fayyad U. Weir.N and Djorgovski.S. Skicat: A machine learning system for the automated cataloging of large-scale sky surveys[C]. In proceeding of .the Tenth international conference on machine learning,1993(112-119).
[11] Flickner M.,Sawhney., Niblack W. Query byimage and video content: The QBIC system. IEEE Computer[J],1995,28(9):23~22.
[12] Smith J R., Chang S-F. Visually seaching the web for content[J]. IEEE Multimedia Magazine, 1997,4(3): 12~20.
[13] Wactlar H, Hauptmann A, Witbrock M. Informedia: News-on-demand experiments in speech recognition[C]. In Proceedings of ARPA Speech Recognition Workshop. Arden House, Harriman, NY, 1996: 18~21.
[14] Simeon J. Variations on multimedia data mining.[C] In Proceedings of theInternational Workshop on Multimedia Data Mining, Boston,USA,2000.
[15] Simeon J, Simoff, Osmar R Z. Report on MDM/KDD2000[C]: The 1st International Workshop on Multimedia Data Mining. SIGKDD Explorations, 2001,2(2):103~105.
[16] Zajane O R, . Multimediaminer: Asystem prototype: for multimedia data mining[C]. In Proceedings of ACM SIGMOD Conf. on Management of Data,Seattle, 1998: 581~583.
[17] Wijesekera Duminda, Barbara aniel. Mining cinematic Knowledge: an extended abstract[C]. MDM/KDD2000. Boston,MA,USA,2000.
[18] Matsuo Yuya, Shirahama Kimiaki, Uehara Kuniaki. Video data mining: extracting cinmatic rules from movie[C]. SIGKDD,2003:24~27.
[19] Lienhart R, Pfeiffer S. Video abstracting[C]. Communications of the ACM, 1997,40(12):55~62.
[20] Zhu Xingquan, Fan Jianping, Aref Walid G. ClassMiner: Mining medical video content structure and events towards efficient access and scalable skimming[C]. Proc. ACM SIGMOD Workshop, Madison,WI,2002:9~16.
[21] Zhu Xing-Quan, Wu Xindong. Sequential association mining for video summarization[C]. Proc. of IEEE Int, Conf. on Multimedia,Baltimore,2003(3):333~336.
[22] M. Datcu,K. Seidel. In summary, image mining is a promising field for Image information mining: exploration of image content in large archives[C], IEEE Conference on Aerospace, 2000(3).
[23] O. R. Zaiane, J. W. Han. Mining MultiMedia Data[C], CASCON'98: Meeting of Minds, Toronto, Canada,1998(83-96).
[24] Michael C.Burl, Charless Fowlkes, Joe Rodem, Andre Stechert. Diomond Eye: A Distributed Architecture for Image Data Mining[C], SPIE DMKD, Orlando,1999.
[25] J Zhang. An Information-driven Framwork for Image Mining[C]. In Proceeding of 12th Int Con on Database and Expert Systems Applications DEXA, Munich, Germany,2001.
[26] J.S.D., Bonet. Image preprocessing for rapid selection in "Pay attention mode"[J], MIT,2000.
[27] M.C Burl., Mining for image content[J]. In Systemics,Cybernetrics,and Informatics / Information Systems: Analysis and Synthesis,1999.
[28] Gibson,S., Intelligent mining in image databases[J]. with applications to satellite imaging and to web search, Data Mining and Computational Intelligence, 2001.
[29] Michael. C, Burl and Charless. F, Joesph. R. Mining for image content[C].in Systemics, Cybernetics, and Informatics/ Information System: Analysis and synthesis, 1999.
[30] R. Kazman, J. Kominek. Information organization in multimedia resources[C], Proceedings of the 11th annual international conference on Systems documentation, 1993:149~162.
[31] Y.Rui., T.S.Huang. Image retrieval: Past, present and future[C], Int Symposium on Multimedia Information Processing, 1997.
[32] K .Lin, H.V. Jagadish, C. Faloutscs. The TVtree: An index structure for high -dimentional data[J], The VLDB ,1994,3(4):517~542.
[33] T. Sellis, N. Roussopoulos, C.Faloutscs. The R+ tree: A dynamic index for multi-dimentional objects[C], In Proc 12th VLDB, 1987.
[34] D White, R.Jain. Similarity indexing: Algorithms and performance[C], In Proc. SPIE Storage and Retrival for image and Video Databases, 1996.
[35] A. Vailaya, A.T.Figueiredo, A.K.Jain,H.J.Zhang. Image classification for content-based indexing[J], IEEE Transactions on Image Processing, 2001.
[36] R.F.Cromp, W.J.Campbell. Data mining of multi-dimentional remotely sensed images[C], International Conference on Information and Knowledge Management(CIKM), 1993.
[37] J.Z.Wang, J.Li. System for Screening Objectionable image Using Daubechies' Wavelets and Color Histograms, Interactive Distributed Multimedia Systems and Telecommunication Services[C], Proceedings of the Fourth European Workshop(IDMS'97), 1997.
[38] A.K.Jain, M.N.Murty, P.J.Flynn. Data clustering: a review[C], ACM Computing survey, 1999.
[39] V.Megalooikonomou, C.Davataikos, E.H.Herskovits. Mining lesion-defict associations in a brain image database[C], KDD San Diego,CA USA, 1999.
[40] C.Ordonez, E.Omiecinski. Discovering association rules based on image content[C], Proceedings of the IEEE Advanced in Digital Libraries Conference(ADL'99), 1999.
[41] Turkey. W. Exploratory data analysis[M], Addison-Wesley, New York,1971.
[42] kim V, Yaroslavskii L. Rank algorithm for picture processing[J], Computer Vision Graphics, Image Processing. 1986,35(2):234~258.
[43] Lin H M, Willson A N. Median Fiters with adaptive length[J], IEEE CASI, 1988, 35(6): 675~690.
[44] Florencio D A F, Schafer R W. Decision-based median filter using local signal statistice[C], In: Proc SPIE Syme. Visual Comm. Image Processing, Chicago, 1994, 2308:268~275.
[45] Hardie R E, Barner K E. Rank condition rank selection filters for signal restoration[J], IEEE IP, 1994,3(2): 192~206.
[46] Kim S. R., Effort A. Adaptive robust impulse noise filtering[J], IEEE Trans. Signal Processing , 1995,43(8): 1855~1866.
[47] Abreu E, Lightone M, Mitra S K. A new efficient approach for the removal of impulse noise from highly corrupted images[J], IEEE IP,1996,5(6):1012~1025.
[48] Zhang D., Wang Z. Impulse noise detection and removal using fuzzy techniques[J]. Electronics Letters, 1997 ,33(5):378~379.
[49] Wang Z., Zhang D. Restoration of impulse noise corrupted images using long—range correlation[J]. IEEE Signal Processing Letter, 1998, 1(5):4~7.
[50] Jiawei Han, Micheline Kamber著范明,孟小峰等译Data Mining Conceptes and Techniques[M],北京:机械工业出版社, 2001.
[51] Chris Ding. A Tutorial on Spectral Clustering[C]. ICML, 2004.
[52] Ester M, Kriegel H-P, Sander J. A Denity-based A lgorithm for Discovering Cluster in Large Spatial Databases with Noise[C]. Portland: Proceedings of the 2nd ACM SIGKDD, 1996, 226~231.
[53] Hinneburg A, Keim D. An Efficent Approach to Clustering Large Multimedia Databases with Noise[C]. New York: Proceedings of the 4th ACM SIGKDD,1998, 58~65.
[54] Wang W, Yang J, Muntz R. STING: A Statistical Information Grid Approach to Spatial Data Mining[C], Athens Proceedings of the 23rd Conference on VLDB,1997,186~195.
[55] Wang W, Yang J, Muntz R R. STNG +:An Approach to Active Spatial Data Ming[C]:Sydney: Proceedings of the 15th ICDE, 1999, 116~125.
[56] Agrawal R, Gehrke J, Gunopulos D. Automatic Subspace Clustering of High Dimensional Data for Data Mining Applications[C]. Seatlle: Proceedings of the ACM SKIMOD Conference, 1998, 94~105.
[57]陈国良,王煦法,庄镇泉等.遗传算法及其应用[M].北京:人民邮电出版社, 1996.
[58]周明,孙树栋.遗传算法原理及应用[M],北京:国防工业出版社, 2001.
[59]陈文伟.智能决策技术[M],北京:电子工业出版社, 1998.
[60] B.Fischer, J.M.Buhmann. Bagging for Path-Based Clustering[J], IEEE Trans.Pattern Analysis and Machine Intelligence, 2003, 25(11):1411~1415.
[61] B.Fischer, J.M.Buhmann. Path-Based Clusetring for Grouping Smooth Curves and Texture Segmentation[J], IEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25(4):513~518.
[62]邹进上等,大气物理学[M],气象出版社, 1982.
[63]吴伯雄,大气物理基础[M],江苏科学技术出版社, 1980.
[64] Adler,R.F., A.J.Negri,1998,A satellite infrared technique to estimate tropiical convective and stratiform rainfall[J], Appl. Meteor. ,1998, 27:31~51.
[65] Adler, R.F., R.A.Mack. Thunderstorm cloud height -rainfall rate relations for use with satellite rainfall estimation techniques[J], Appl. Meteor.,1984, 23:280~296.
[66]杨行峻,郑君里.人工神经网络[M],北京:高等教育出版社, 1992.
[67]罗四维,人工神经网络建模[M],北京:中国铁道出版社, 1998.
[68]王耀生,冯晓娟.卫星云图的计算机分析识别[J],气象, 1994, 20(6):24~32.
[69]刘正光,林孔元,郭爱民.卫星云图形态特征提取[J].计算机研究与发展,1997, 34(9): 689~693.
[70] Kitamoto A, Takagi M. Retrieval satellite cloud imagery based on subjective similarity[C]. Scandinavia: 9th Scandinavian Conference on Image Analysis (SCIA95), 1995:449~456.
[71] Gibson S, Mirtich B. A survey of deformable modeling in computer graphics[R], Cambridge: Mitsubishi Electric Research Lab,1997:1~33.
[72] Press W, Teukolsky S, Vetterling W. Numerical recipes in C[EB/OL], http://www.library comell edu/nr/bookcpdf html, 1992: 425~429.
[73] George G, Paull R. Incorporation shap into histograms for CBIR[J], Pattern Recognition, 2002, 35(11):81~91.
[74] Borgefors G. Hierarchical chamfer matching A parametric edge matching algorithm[J], IEEE Transactions on Pattern Analyse and Machine Intelligence, 1988, 10(6): 849~865.
[75] Koffler R. A Procedure for Estimating Cloud Amount and Height from Satellite Infrared Radiation Data[J], MonWeaRev, 1973, 101:240~243.
[76] Shenk W E, Holub R T, Neff R A. A Multispectral Cloud Type Identification Method Developed for Tropical Ocean Area with Nimbus-3 MRIR Measurements[J], Mon Wea Rev, 1976, 104: 284~291 [J].
[77] Haralick R M, Shanmugam K, Dinstein I Textural Features for Image Classification [J], IEEE Trans Sys Man Cybern, 1973, 3:610~621.
[78] Weszka J S, Dyer C R, Rosenfeld A. A Comparative Study of Texture Measurements for Terrain Classification [J], IEEE Trans Syst Man Cybern,1976, 6:269~285.
[79] Welch R M, Sengupta S K, Chen D W. Cloud Field Classification Based Upon High Spatial Resolution Textual Features, Part I, Gray level Cooccurence Matrix Approach [J], J Geophys Res, 1988, 93:12663~12681.
[80] Welch R M, Sengupta S K, Goroch A K. Polar Cloud and Surface Classification Using AVHRR Imagery: An Intercomparison of Methods[J], J Appl Meteoro 1992, 31: 405~420.
[81]李俊,周凤仙.气象卫星台风云图的自动识别方法及其应用[J].应用气象学报, 1992 ,3(4):402~409.
[82]师春香,翟建华.用神经网络方法对NOAA-AVHRR资料进行客观分类[J].气象学报, 2002, 60(2):250~255.
[83] R.Caruana, D.Freitag. Greedy Attribute Selection[C], 11th International Conference on Machine Learning, 1994.
[84] G.Castelano, A.M.Fanelli, M.Pelillo. An Iterative Prunning Algorithm for Feedforward Neural Networks, IEEE Transaction on Neural Networks, 1997,8(3):519~531.
[85] I.Kononenko. Estimation attributes: Analysis and Extensions of RELIEF[C], European Conference on Machine Learning, Catana,Italy, 1994:171~182.
[86] P.Pudil, J.NovoVicova, J.Kittler. Floating Search Methods in Feature Selection[J], Pattern Recognition Letters, 1994, 15:1119~1125.
[87] Reynold D.W., T.H. Vonder Haar. A Bispectral Method for Cloud Parameter Determination[J], Monthly Weather Review, 1977, 105:447~457.
[88] Hayden C.M. GOES/VAS Simultaneous Temperature Retrieval Algorithm[J], Journal of Applied Meteorology, 1988, 27:705~733.
[89] Derrien M., H. Le.Gleau. Cloud Classification Extracted from AVHRR and GOES Imagery[EB/OL], http://www.meteorologie.eu.org/safnwc/, 1992.
[90]郁凡,陈渭民.双光谱云图的云分类探讨[J],南京气象学院学报, 1994, 17(1):117~125.
[91] Stowe L. Evaluation of NLMBUS-7 THIR/CLE and Air Force Three-dimensional Nephanalysis Estimates of Cloud Amont[J], Journal of GeophysicalResearch, 1984, 89:5370~5380.
[92] Coakley J.A. , F.P.Bretherton. Cloud Cover from High-Resolution Scanner Data: Detecting and Allowing for Partially Filled Files of View[J], Journalof Geophysical Research, 1982, 87:4917~4832.
[93] Koffler R., A.G. DeCotiis, P.K. Rao. A Procedure for Estimation Cloud Amount and Height from Satellite Infrared Radiation Data[J], Monthly Weather Review, 1973, 101:240~243.
[94] Welch R.M., S.K. Sengupta, K.S. Kuo. Marine Stratocumulus Cloud Fields off the Coast of Southern California Observed Using Landsat Imagery. Part II : Textual Analysis[J], Journal of Applied Meteorology, 1988, 27:362~378.
[95] Desbois M., G. Seze, G. Szejwach. Automatic Classification of Clouds on METEOSAT Imagery Application to High-level Cloud[J], Journal of Applied Meteorogy, 1982 ,21:401~412.
[96] Welch R.M., Navar M.S., Sengupta S.K. The effect of Resolution upon Texture-based Cloud Field Classification[J], Jounal of Geophysical Research, 1989, 94:14767~14781.
[97] Key J., J.A.Maslanik, A.J. Schweiger. Classification of Merged AVHRR and SMMR Arctic Data With Neural Netwoks[J], Photogrammetric Engineering and Remote Sensing, 1989, 55(9):1331~1338.
[98] Lee J., Weger R.C., Sengupta S.W. A Neural Network Approach to CloudClassification[J], IEEE Transaction on Geosciences and Remote Sensing, 1990, 28(5):846~855.
[99]蒋德明,陈渭民.基于径向基函数网络的云自动分类研究[J].南京气象学院学报, 2003, 26(1):89~96.
[100] Richard O.Duda, Peter E. Hart, David G.Stork.模式分类(2)[M].北京:机械工业出版社, 2003.
[101] Hornk K, Stinchcombe M, White H. Mutilayer Feedfoeword Networks Are Universal Approximates[J], Neural Networks, 1989, 2:359~366.
[102] Hornk K, Stinchcombe M, White H. Universal Approximation of an Unknown Mapping and Its Derivatives Using Mutilayer Feedforward Networks[J], Neural Networks, 1990, 3:551~560.
[103] Sexton R S, Dorsey R E. Reliable Classification using neural networks: a genetic algorithm and backprogation compassion[J], Decision Support System, 2000, 30(1):11~22.
[104] Kennedy J., Eberhart R. Particle Swarm Optimization[C], In: IEEE Int'l Conf on Neural Network, Perth, Australia, 1995: 1942~1948.
[105]杨燕,靳蕃, Kamel M.微粒群优化算法研究现状及其进展[J],计算机工程,2004, 30(21):3~4.
[106]谢晓峰,张文俊,杨文廉.微粒群算法综述[J],控制与决策, 2003, 18(2): 129~134.
[107]李爱国,覃征,鲍复民.粒子群优化算法[J].计算机工程与应用, 2002, 38(21):1~3.
[108] Van den F B, Engelbrecht AP. Cooperative Learning in Neural Networks using Particle Swarm Optimizer[C], In: Proc. SAICSIT, 2000.
[109]孙即祥.现代模式识别[M],长沙:国防科技大学出版社, 2002.
[110] L.Lam, C.Y.Suen. Application of majority voting to pattern recognition: an analysis of its behavior and performance[J]. IEEE Trans. on SMC part A. 1997, 27(5):553~568.
[111]叶泽刚.湖南大型水库防洪调度决策支持系统开发及应用[J],计算机系统应用, 1999.
[112]易宏杰. BP网络原理及应用研究[D],硕士,中国海洋大学, 2004.
[113]师春香,卢乃锰,张文建.卫星面降水估计人工神经网络[J],气候与环境研究, 2001, 6(4):467~472.
[114]师春香,谢正辉.基于静止气象卫星观测的降水时间降尺度研究[J],地理科学进展, 2008, 27(4):16~22.
[115]师春香,卢乃锰,张文建.卫星面降水估计人工神经网络方法[J],大气与环境研究, 2001, 6(4).
[116]卢乃锰,吴蓉璋.强对流降水云团的云图特征分析[J],应用气象学报, 1997,8(3):269~275.
[117]卢乃锰,师春香,张文健.卫星降水估计结果与地面观测结果的融合技术[J],淮河流域能量与水分循环研究(一),北京:气象出版社,1999:125~129.
[118]李伟钢,石利华.气象卫星云图多分辨小波分解及人工神经网络降水估计研究[J],南京气象学院学报, 2000, 23(2):272~282.
[119]王彦磊,刘巍,张韧,陈奕德,王辉赞,黄志松.基于云分类和降水先验知识的卫星云图降水估计[J],应用基础与工程科学学报, 2002(14).
[120]王彦磊,江海英,赵中军,李文才,张韧.多光谱卫星云图降水区域与强度估计的模糊推理模型[J].解放军理工大学学报(自然科学版), 2007, 8(2).
[121]张韧,王彦磊.云类降水知识提取与卫星云图降水估计[C].会议征文: Session 1-大气综合探测技术, 2006.
[122]马力军,关联规则算法性能分析与仿真研究[D],西安交通大学硕士学位论文.
[123] R.Agrawal. Database mining: A performance perspective[J], IEEE transactions on knowledge and data engineering, 1993, 5(6):914~925.
[124] S.Brin, R.Motwani, C.Silverstein. Beyond market basket: Generalizing association rules to correlations[C], In Proc. ACM-SIGMOD Int. Conf. Management of data (SIGMOD'97), 1997:265-276.
[125] N.Pasquier, Y.Bastide, R.Taouil, L.Lakhal. Discovering frequent closed itemsets for association rules[C]. In Proc. 7thInt. Conf. Database Theory(ICDT'99), 1999:398-416.
[126] Jian. Ma, Ballantyne,S.B. LandSat Thematic Used to Mapper with ground truth element distribution : an example from British Cokunbi Golden Triangle Dneriet, Program with Abstracts[J], GSC Forum, Canada, 1992.
[127] QiW Z, Zheng X B. Application of Weather Satellite Image on Precipitation Forecast System[J], Electri Power of Central China, 2001, 14(3):57~59.
[128]卢乃锰,师春香,张文健.卫星降水估计结果与地面降水观测结果的融合技术[J],淮河流域能量与水分循环研究(一),北京:气象出版社, 1999, 125~129.
[129]卢乃锰,吴蓉璋.强对流降水云团的云团特征分析[J],应用气象学报, 1997,8(3):269~275.
[130]师春香,谢正辉.基于静止气象卫星观测的降水时间降尺度研究[J].地理科学进展, 2008, 27(4).
[131] Fukuda T, Morimoto Y, Morishita S. Mining optimized association rules for numeric attributes[C], In Proceedings of the Fifteenth ACM SIGMOD-SIGART Symposium on Principles of Database Systems, Montreal ,Canada, 1996:182~191.
[132] R. Agrawal, R.Srikant. Fast algorithms for mining association rules in large databases[C]. In Proceedings of the 20th international Conference on Very Large Data Bases, Santiago, Chile, 1994.
[133] R. Agrawal, T.Imielinski, A.Swami. Mining association rules between sets of items in large databases[C], In Proceedings of 1993 ACM SIGMOD International Conference on Management of Data, 1993:207-216.
[134]谷晓平,王长耀,王汶. GMS5红外卫星云图参数化及在降水预测中的应用[J],遥感学报, 2005, 9(4).
[135] Weir.N, Djorgoveski. S, Fayyad. U, Roden. J, Roquette. N. SKICAT:A system for the scientific analysis of Palomar—STSCI Digital Sky Survey[C], In Proceeding of the ESO Conference , Haguenau, 1992.
[136] Rudin. L, Osher. S, Fatemi E. Nonlinear total variation based noise removal algorithms[C]. In Proceedings of Mddiz.Mat.Traitement d’Images, INRIA, 1992:149~179.
[137] Rudin.L, Osher.S. Total variation based image restoration with free local constrains[C]. In Proceedings of IEEE International Conference on Image Processing, Austin,1994:31~35.
[138]罗炳伟,余沪涛,江晓.细胞图像分割的新方法.电子科技大学学报[J]. 1990,19(1): 54~59.
[139] Pal. N.R, Bezdek.J.C. On cluster validity for the fuzzy c-means model[J]. IEEE Trans Fuzzy System, 1995, 3(3):370~379.
[140] Magurran.A.E. Ecological Diversity and Its Measurement[M]. New Jersey, Princeton University Press, 1988.
[141] Dunn.J.C. Well-seperated clusters and the optimal fuzzy partitions[J]. Cybernet, 1974,4(1):95~104.
[142] Bezdek.J.C. Pattern recognition with fuzzy objective function algorithms[R]. Plenum Press, New York, 1981.
[143] Bezdek.J.C. Clustering validity with fuzzy sets[J]. Mathematical Biology, 1974, 1:57~71.
[144] Windham.M.P. Cluster validity for fuzzy clustering algorithms[J]. FSS, 1981, 5(2):177~185.
[145] Windham.M.P. Cluster validity for fuzzy c-means clustering algorithms[J]. IEEE Trans. PAMI, 1982,4(4):357~363.
[146] Gunderson.R.G. Applications of fuzzy ISODATA algorithms to startracker printing systems[C]. In Proc. 7 th Triennual World IFAC Congress, 1978:1319~1323.
[147] Xie.X.L., Beni.G. A validity measure for fuzzy clustering[J]. IEEE Trans. PAMI, 1991, 13:841~847.
[148] Bensaid.A.M., Hall.L.O. Validity-guided clustering with applications to image segmentation. IEEE Trans. FS, 1996, 4(2):112~122.
[149] Jain.A.K., Moreau.J.V. Bootatrap techniques in cluster analysis[J]. PR, 1987,20(5):347~363.
[150] Beni.C., Liu.M.X. A least biased fuzzy clustering method. IEEE Trans. PAMI, 1992, 16(9):954~960.
[151] Li.J., Gao.X.B., Jiao.L.C. A new cluster validity function based on the modified partition fuzzy degree[C]. In Proceeding of Fourth International Conference on Rough Sets and Current Trends in Computing(RSCTC), 2004, 3066:586~591.
[152]范九伦.模糊聚类有效性研究[D].西安,西安电子科技大学,1998:30~36.
[153] Franchini. M. Use of a genetic algorithm combined with a local search method for the automatic calibration of conceptual rainfall-runoff models[J]. Hydrological Science Journal, 1996, 41(1):21~39.