The output information of single classifier has three forms of abstract , rank and measurement single classifier supplies both the unknown pattern classifying information on the measurement level and the wrong classifying distribution information of the training samples on the abstract level , which are used to design the fuzzy multiple classifiers combination method 单个分类器的输出信息有三种表现形式：符号层、排序层、度量层。应用单个分类器在度量层次上，对未知模式的分类信息；在符号层次上，训练样本的错分类分布状况，设计了模糊多分类器组合方法。
The research status is firstly analysed in this paper . after an analysis and comparing of existing 3dcm , the methods for constructing topographic model , building model , road model , water system model etc . are focused on the discussion . the tin and grid modeling method are applied for topographic model , a layer - combined model based on triangle partition is presented for building model and a independent triangle partition is presented for the other models . all these models are combined to topographic model in the end 本文首先讨论了国内外3dgis理论的研究现状，对已有的三维城市模型进行了分析和比较，着重探讨了三维城市模型中的地形模型、建筑物模型、道路及水系模型、独立地物模型的构造方法，对地形模型采用tin和grid的建模方法，对建筑物总结出了一种基于三角剖分及分层组合方法实现建筑物的模型构造，对道路及水系等地物采用三角形片面剖分实施单独控制，最后融入dem中。
Then this paper introduced the main method in multi - sensor integrated navigation - kalman filtering method , and a two - level optimization multi - sensor information fusion structure - combined filter which was originated by carlson and kerr , based on the structure of combined filter , it studied the method of navigating by the multi - sensor navigation system integrated by ins milemeter altimeter and piloting , then analyzed the effect of several filters . simulation proved that when altimeter were integrated , the height error was reduced a lot , and the combined filter is more effective than one - level kalman filter 然后，介绍了组合导航中的关键技术? ?卡尔曼滤波方法，以及一种二级最优多传感器融合结构? ? carlson , kerr等人提出的联合滤波器，并以联合滤波器的结构为基础研究了车载捷联惯导系统与里程计、气压高度计、地标组合导航的方法，比较了几种组合方法的效果。仿真结果表明，引入气压高度计可以有效的减小高度误差，二级联合滤波器的效果优于一级结构的卡尔曼滤波器。
( 5 ) a series of design methods of classifiers are proposed , including the classifier based on the generalized inverse and the probabilistic reasoning method ( prm ) , a new self - adaptive kohonen clustering network which overcomes the shortcomings of the conventional clustering algorithms , and the fuzzy neural classifier . the experimental study efface recognition is presented based on the combination of multi - feature multi - classifier . ( 6 ) this paper proposes a hybrid feature extraction method for face recognition , which is a combination of the eigen matrix , fisher discriminant analysis , and the generalized optimal set of discriminant vectors ( 5 )对图象分类器设计方法进行研究，主要包括：提出了一种基于广义逆和概率推理的分类器设计方法；提出了一种新的自适应模糊聚类算法；提出了基于模糊神经网络的分类器设计方法；并对多特征多分类器组合方法在人脸识别中进行实验研究； ( 6 )提出了一种只要一个训练样本就能解决人脸识别问题的新方法，该方法结合了特征矩阵、 fisher最优鉴别分析和广义最优鉴别分析方法的优点。
Using the combinatorial method of constructibility and the technique of exchanging colors , we present the best upper bounds of dynamic chromatic number of halin graphs and sp graphs , and determine the dynamic chromatic number of a type of sp graphs , we determine the incidence chromatic number of some descartes product graphs and some join graphs . at last we determine the entire coloring number of 1 - tree and prove a conjecture of edge - face coloring 利用构造性组合方法和换色技巧给出了halin图和系列平行图动态色数的最小上界，并确定了一类特殊系列平行图的动态色数，确定了某些笛卡儿积图和某些联图的关联色数，确定了1 -树图的完备色数并证明了有关边面着色的一个猜想。
The classifier ' s output information to the training and test samples on the measurement level is used to design another multiple classifiers combination method , in which the decision information of the combined classifier to the training samples is denoted with the prior knowledge matrix and the decision information of single classifier to the samples to be recognized is denoted with the similarity measurement . the similarity measurement is denoted with 应用分类器对于训练样本和测试样本在度量层次的输出信息，设计了另外一种多分类器组合方法，参与组合的分类器对训练样本的决策信息用先验知识摘要2001年8月矩阵表示:单个分类器对待识样本的决策信息用相似度表示，相似度反映待识样本属于某个类别的可能性，用后验知识矩阵表示。
