基于...

It settles the problems of fast video clip retrieval in large amount video database with effective organization of video features database by VA-File and fast query algorithms by restricted sliding window. In addition, we design a new similarity measure which synthetically considers the visual similarity and temporal order between video clips.

在基于低层特征的视频检索方面，本文提出了基于高维索引结构的快速视频检索算法，该方法利用高维索引结构VA-File组织视频数据库，设计了两种不同的子片段分割算法，以及新的包含视觉相似性和时序关系的视频片段相似度度量，并通过基于限定性滑动窗口的快速查询算法，在一定程度上解决了大规模视频数据库的快速高效查询问题。

Then the spatial index is constructed which includes not only the external approximate expression but also interior approximate expression of spatial object and is extended from tranditional index only with external approximate expression. The index structures of MR-tree and MRD-tree based on multi-approximate expression are set up with the prototype index of R-tree, and the relevant algorithms about the index of insertion, deletion and search are provided. Then, the efficiencies of constructing index based on the multi-approximate expression and window range query are analysised and compared. In addition, the several algorithms and efficiency of soving the maximum enclosed circle and maximum enclosed rectangle are discussed and analyzed during constructing index based on multi-approximate expression.

首先，论文讨论了空间数据的特点、空间数据库的关键技术以及空间对象间的拓扑、距离以及方向关系，分析了空间对象的外部和内部近似表达，然后将传统索引中只利用空间对象的外部近似扩展为既有空间对象的外部近似又有空间对象的内部近似，即以空间对象的多重近似来构建索引，并以R-tree为索引原型构建基于多重近似的MR-tree和MRD-tree索引结构，然后给出了相关索引的插入、删除及查找算法，并通过实验比较分析了基于多重近似索引与基于外部近似索引的构建效率及窗口范围查询效率。

Some statistical properties of product assembly are obtained on the basis of industrial investigation of assembly procedure and analysis of assembly operations of typical products; concept of fuzzy quotient set is introduced to the study of assembly sequence planning and a theoretical frame and algorithm for assembly sequence planning based on product fuzzy quotient set is presented; theory and method of fuzzy automata and fuzzy decision are used in the investigation of sensor based assembly sequence planning and a theoretical frame and algorithm for assembly sequence planning based on information sensing of assembly process are presented; an assembly model for product is put forward; study of product disassemblability is carried on.

论文通过对产品装配工艺的工厂调研及典型产品的装配作业分析得到了有关产品装配的一些统计特征；将模糊商集合的概念引入装配顺序规划的研究中，提出了基于产品模糊商集合的装配顺序规划的理论框架和算法；将模糊自动机及模糊决策的理论和方法应用到基于感知的装配顺序规划的研究中，提出了基于装配过程信息感知的装配顺序规划的理论框架和算法；提出了一种产品装配模型；进行了产品可拆卸性的研究。

It was independent of the methods based on radiometric source or detectors.

为提高定标精度，提出一种基于相关光子的光辐射定标方法，它是一种独立于基于辐射源和基于探测器的定标方法。

This paper studies the concrete implementation flow of contour-based retrieval based on wavelet transform modulus maxima , multi-scale morphology and invariant relative moments. Also, experimental results are given to validate the feasibility of our strategy and the corresponding retrieval performance is analyzed.

从理论和技术的角度研究了在基于目标形状的遥感影像检索中，应用基于小波变换模极大值和多尺度形态学的边缘检测方法以及基于不变相对矩的轮廓特征描述方法的具体实现技术流程，通过实验充分验证了本文方法的可行性，并分析了检索性能。

Making a primary research on member deletion. Three kinds of member deletion schemes are annlyzed, including schemes based on witness, accumulator and Chinese Remainder Theorem.

对群成员的删除题目作了初步的探索，剖析了现有的几种群成员删除计划，包括基于证据值的删除计划，基于动态累加器的删除计划和基于中国剩余定理的删除计划。

Computer simulation on a non=isothermal CSTR process monitoring problem demonstrates the effectiveness and efficiency of the proposed method.3 Optimal design of the incidence matrix for Structured Residual Approach with Maximized Sensitivity is discussed in this paper, in order to overcome the shortcoming of SRAMS that ignores the speed and sensitivity of fault diagnosis while considering the isolability of fault codes in the incidence matrix design.

通过非等温连续反应釜过程的故障检测与诊断的应用实例，说明了基于具有优化结构的FS KPCA信号重构传感器故障诊断方法的快速性和有效性。3针对一种基于结构化残差PCA的传感器故障诊断方法，即：基于具有最大敏感性结构化残差的传感器故障检测与诊断方法，在设计影响矩阵时只考虑故障编码的可分离性，而没有考虑故障诊断的快速性和灵敏性的缺点，提出了故障敏感度和故障诊断灵敏度等指标，并给出了两种影响矩阵结构的优化设计算法，从而提高传感器故障诊断的快速性和准确性。

Experiments show that rhomb partitioning is more powerful in suppressing block artifacts than square partitioning, results in much higher reconstructed image quality, but takes longer encoding time; 2 For solving exhausting encoding problem of fractal image coding, we present a fast rhomb-partitioning fractal image coding based on neighbor-searching; we present a fast rhomb-partitioning fractal image coding based on block classification; we present a fast square-partitioning fractal image coding based on neighbor-searching, block classification and wavelet transform.

2针对分形图象压缩编码过程非常耗时的致命弱点，提出了基于邻域搜索的菱形块分割的快速分形图象压缩编码方法，提出了基于块分类的菱形块分割的快速分形图象压缩编码方法，提出了基于邻域搜索·块分类和小波变换的方块分割的快速分形图象压缩编码方法，实验结果表明，我们提出的快速分形图象压缩编码与传统的分形图象压缩编码相比，编码速度提高了近40倍。

Because of the sampling processing, we can take the simple concave domain analysis and ICM optimization in two different levels, so as to make both the parameter estimation and optimization much easier to implement, while delivering a satisfactory result; The third one is based on the multi-resolution analysis, robust statistics and majority game theory. 4. Propose a new clustering algorithm based on the entropy concept, which is used for unsupervised segmentation of color images.

重点讨论非监督的图象分割问题，并给出了三种新方法：一是基于贝叶斯学习和全局竞争策略的方法，把参数估计和图象分割有机地结合在一起；二是基于分层的框架，从抽样定理出发，在两个不同的层次上使用简单的凹域分析和ICM优化，可以使得参数估计和优化问题都变得简单易行，并得到满意的结果；三是基于多级分析、鲁棒统计的参数估计和多数博弈论的优化算法。

First, the traffic flow time series chaotic feature is extracted by chaos theory. pretreatment for traffic flow time series, and the wavelet neural networks model was build by this. Second, the chaotic mechanism and the chaotic probability is described. Based on chaotic learning algorithm, and the wavelet neural networks fast learning algorithm of traffic flow time series is designed based on chaotic algorithm. Last, a single-step and multi-step prediction of traffic flow chaotic time series is researched by BP neural networks, wavelet neural networks and wavelet neural networks based on chaotic algorithm. The results showed that the wavelet neural networks predictive performance is better than the BP networks and the wavelet neural networks by the simulation results and root-mean-square value.

首先，通过混沌理论提取了交通流量时间序列的混沌特征，并在此基础上建立了小波神经网络交通流量时间序列模型；接着，阐述了混沌学习算法的混沌机理、混沌产生的概率，设计了基于混沌算法的小波神经网络交通流量混沌时间序列快速学习算法；最后利用交通流量混沌时间序列对BP网络、非混沌算法的小波神经网络以及基于混沌算法的小波神经网络进行了单步预测和多步预测，并对预测结果的仿真图和真实值与预测值的方均根进行了比较，结果表明基于混沌学习算法的小波神经网络的预测性能明显优于应用BP网络和非混沌算法的小波神经网络。

Recall that, in the Kolmogorov axiomatization, measurable sets are the sets which have a probability or, in other words, the sets corresponding to yes/no questions that have a probabilistic answer.

延期开工的Kolmogorov宣布要衡量所有套职能有限许多坐标限制在于衡量子寅。换句话说，如果是/否的问题回答f可看的价值观念在许多最有限坐标，然后它有一个概率的答案。

The experimental results showed that the algorithm can filter singular points and remain fixity of the target edge.

实验表明：基于模糊理论的图像智能滤波方法比常规图像滤波方法运算量小，它既能去除奇异点，又能保持图像中目标的边缘不变性，具有很好的滤波效果。