算法

CBFEC emphasizes direct correspondence of concepts in EC with its software architecture for ease of understanding and using; minimal coupling with specific problem structure for easy adaptation it to solve a large number of wholly different problems; interface-centered design for extendibility. To achieve those objects, the problem-solving method of EC is analyzed and the problem-solving procedure of EC is divided into three interactive aspects: population-based stochastic searching mechanism, problem specific information to implicitly guide the stochastic searching, and the observation and control of the computation procedure of EC. Then the key concepts of EC are identified in those three aspects; the normal implementations of those concepts are summarized; the interfaces represents those concepts in software are abstracted; the collaborations of components through those interfaces are designed. CBFEC is implemented on mainstream component software platform COM/DCOM (Component Object Model/Distributed COM from Microsoft), which includes interfaces definitions, commonly using EC components implemented those interfaces, such as Simply EA component, Steady State EA component, EA component, EA component, Population component, Tournament Selection component, Linear Ranking Selection component, Nonlinear Ranking Selection component, Random Number Generator component, etc, and the collaborations of those components through those interfaces.

具体的做法是把演化计算看作是基于组件的软件工程的一个应用领域：首先分析了演化计算求解问题的一般思路和方法，把演化计算问题求解过程分为："设计基于群体的随机搜索机制"、"研究问题的性质并以此隐含地定义算法的搜索方向"和"求解过程的观察与控制"三个部分；然后分别找出各个部分中的关键概念，总结这些概念现有的一般实现方法，抽取其本质，以此结合设计模式来定义组件软件的接口；通过分析演化计算各个概念之间的相互联系来设计组件软件间通过接口的进行交互的方式；最后还在目前一种主流组件软件开发平台COM／DCOM（微软提出的组件对象模型）的基础上实现了常用的演化计算组件，如简单演化算法组件、稳态演化算法组件、演化算法组件、演化算法组件、种群组件、锦标赛选择策略组件、线性排名选择策略组件、非线性排名选择策略组件、随机数发生器组件等等。

Since the B-spline is a locally supported function, the smoothing formula can be strictly limited in a neighborhood of each point. The smoothing surface defined by the smoothing formula has the same convexity as that of the original image. Secondly, the edge points are detected by either computing the local extremum points of the directional derivative or computing zero-crossing of the second-order directional derivative of the smoothing surface. Finally, an example of an edge detector is given.

针对反卷积视觉模型的病态性，增加了适当的约束，给出了基于低松弛迭代格式的快速自适应滤波算法，对于一个N×N输入图象，由于变换核的局部支撑性质以及低松弛迭代格式的引入，使得快速自适应滤波算法的计算复杂度降为象素个数N〓的线性量阶N〓，就最小二乘算法的复杂性而言，优于不动点迭代算法的O以及基于FFT的预处理共轭梯度算法的O。

It solves the problem that the unitary contour presentation can not correctly extract face contour in a face image which suffers from scale, rotation etc. The definition of the internal and external energy function is provided. At the same time, the global matching algorithm and local matching algorithm is given. The experiment shows that this presentation and the accompanying matching algorithm can be used to extract the face contour very well. So the image segmentation can be implemented by using it.②By analyzing the recognition principle of PCA method, we can conclude that the face images coming from different surrounding consist of different face image space. This is the essential reason that makes the generality of PCA method worse. Also, we give a measurement means to measure the distance from different face image space, so we can analyze face image space more conveniently.③We also construct various scale models and rotation pose models to detect the scale and rotating angle of face image to be recognized. The experiment results show that the detecting precision is very high. So it is good for face image feature extraction and face image representation.④Similarly, we construct local feature models of face image and utilize them to detect the local feature of face image. At the same time, we put forward a novel face image local feature detection algorithm, locating step by step. The experiment results show that this method can accurately detect the location of local face feature in a image.⑤A novel face image presentation model, dual attribute graph , is put forward. Firstly, it utilizes attribute graph to present the face image, then exact the local principal component coefficient and Gabor transform coefficient of thc pixels which corresponds to the nodes of the graph as the attribute of the nodes. This representation fully makes use of the statistical characteristic of the local face feature and utilizes Gabor transform to present the topographical structure of face image. So DAG has more general property.⑥Based on the DAG presentation, we give a DAG matching function and matching algorithm. During the design of the function and algorithm, the noise factor, e. g., lighting, scale and rotation pose are considered and tried to be eliminated. So the algorithm can give more general property.⑦A general face image recognition system is implemented. The experiment show the system can get better recognition performance under the noise surrounding of lighting, scale and rotation pose.

本文在上述研究的基础上，取得了如下主要研究成果：①构造了一个通用的人脸轮廓模型表示，解决了由于人脸图象尺度、旋转等因素而使得仅用单一轮廓表示无法正确提取人脸轮廓的问题，并给出了模型内、外能函数的定义，同时给出了模型的全局与局部匹配算法，实验表明，使用这种表示形式以及匹配算法，能够较好地提取人脸图象的轮廓，可实际用于人脸图象的分割；②深入分析了PCA方法的识别机制，得出不同成象条件下的人脸图象构成不同的人脸图象空间的结论，同时指出这也是造成PCA方法通用性较差的本质原因，并给出了不同人脸空间距离的一种度量方法，使用该度量方法能够直观地对人脸图象空间进行分析；③构造了各种尺度模板、旋转姿势模板以用于探测待识人脸图象的尺度、旋转角度，实验结果表明，探测精确度很高，从而有利于人脸图象特征提取，以及图象的有效表示；④构造了人脸图象的各局部特征模板，用于人脸图象局部特征的探测；同时提出了一种新的人脸图象局部特征探测法---逐步求精定位法，实验结果表明，使用这种方法能够精确地得到人脸图象各局部特征的位置；⑤提出了一种新的人脸图象表示法---双属性图表示法；利用属性图来表示人脸图象，并提取图节点对应图象位置的局部主成分特征系数以及Gabor变换系数作为图节点的属性，这种表示方法充分利用了人脸图象的局部特征的统计特性，并且使用Gabor变换来反映人脸图象的拓扑结构，从而使得双属性图表示法具有较强的通用性；⑥在双属性图表示的基础上，给出双属性图匹配函数及匹配算法，在函数及算法设计过程中，考虑并解决了光照、尺度、旋转姿势变化等因素对人脸图象识别的影响，使得匹配算法具有较强的通用性；⑦设计并实现了一个通用的人脸图象识别系统，实验结果表明，该系统在图象光照、尺度、旋转姿势情况下，得到了较好的识别效果。

Genetic algorithm and three kinds of hybrid genetic algorithms are presented for parallel machines earliness/tardiness production line scheduling problem.

三。对并行机器生产线提前／拖后调度问题提出了遗传算法和三种混合遗传算法（基于进化交叉的遗传算法、基于模拟退火的遗传算法、基于进化交叉及模拟退火的遗传算法）。

The method this paper discussed was based following theoretic analysis: Square and multiplication of large integer are two basic operations in modular exponential m_ary algorithm. The main operations of m_ary algorithm of point multiplication in elliptic curve encryption were doublings and point addition. The steps of m_ary algorithm in point multiplication was similar to modular exponential.

其基于以下理论分析：模幂m_ary算法的基本运算为大数乘法，其中包括大数平方算法和一般大数乘法；椭圆曲线加密算法中点乘的m_ary算法步骤与模幂的m_ary算法相同，后者的基本运算为倍乘和加法。

UP to now two algorithms for computing a local optimum of the optimal fuzzy equivalent matrix of a fuzzy similarity matrix and some heuristic methods have been introduced.

求与一个模糊相似矩阵"距离"最近的模糊等价矩阵，至今已提出了两个求局部最优解的算法和一些启发式算法，本文也提出一个简便可行的求局部最优解的算法，这算法与线性规划的单纯形算法一样，也是在有限个"顶点"上寻优。

Analysis on the Astringency of a Hybrid-Domain Basis Function Based on Exponential Series Function;2. Research the Corn Production Efficiency of China Based on Malmquist Model and Astringency;3. The background of application of genetic algorithm to reservoir optimal operation and its astringency are introduced.

介绍了遗传算法在水库优化调度中的应用背景及算法的收敛性，讨论了水库优化调度中遗传算法的基本应用步骤以及存在的问题，给出了算法的各种改进方法，并对遗传算法的应用前景进行了展望。

Ant colony algorithm is a simulation of ant foraging behavior of heuristic process This paper introduces the concept of ant colony algorithm and its development trends, analysis of the basic principles of ant colony algorithm to establish a general mathematical model of ant colony algorithm, presented its typical application.

蚁群算法是一种模拟蚂蚁觅食过程行为的启发式算法，本文介绍了蚁群算法的概念及其发展趋势，分析了蚁群算法的基本原理，建立了一般的蚁群算法数学模型，提出了它的典型应用。

Therefore, the main characteristics of this paper are:(1) Given orbits generated correlation theory of learning subspace which is the base of researching algorithm;(2) Advanced orbits generated Breadth first, Depth first and Heuristic algorithms, enrich and develop the basic content of LML further;(3) Given corresponding examples to validate the algorithms. However, all the work is tentive and much needs advanced research.

由此可以看出，本文的特色主要体现在以下几个方面：(1)给出了李群机器学习子空间轨道生成的相关理论，为研究学习子空间轨道生成算法奠定了基础；(2)提出了李群机器学习子空间广度优先轨道生成学习算法，深度优先轨道生成学习算法以及带有启发信息的轨道生成学习算法，丰富和发展了LML的基本内容；(3)对所提出的算法给出了相应的实例验证。

In accordance with the generating principle of line echo and after analyzing main echo cancellation algorithms, and after in-depth study on the core algorithms of all the module of adaptive echo canceller, in particular, adaptive filtering algorithm and double talk detection algorithm, considering with complexities and capabilities of all the candidates, this paper chooses NLMS algorithm to implement echo canceller.

首先，对回波产生原理和目前几种常用回波消除算法进行了分析，在研究自适应回波消除器的各个模块，特别是深入分析各种自适应滤波算法和双讲检测算法，综合考虑各种算法的运算复杂度和性能的情况下，这里采用NLMS算法实现白适应回波消除器。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。