样本问题

School of Computer Science, National University of Defense Technology, Changsha 410073, ChinaAlthough progress in face recognition has been encouraged in constraint conditions, many problems still exist in unconstraint tasks.

虽然约束条件下的人脸识别已取得很大进展，但开放环境下的人脸识别仍有很多问题需要解决；其次，人脸识别实用系统往往难以获得待识别人的多个样本。

In view of the uncertainty of the real world, trust theory and statistical learning theory are combined to generalize the key theorem and the bounds on the rate of uniform convergence of learning theory. This paper mainly investigates the basic problems of statistical learning theory with rough samples.

考虑到现实世界的不确定性，本文结合统计学习理论和信赖理论的知识，讨论了基于粗糙样本的统计学习理论的基本问题，对作为统计学习理论基础的关键定理和学习过程一致收敛速度的界进行了推广。

In chapter 4, the practical problem of transductive SVM is studied in the case that there are a large number of unlabeled samples in radar target recognition.

第四章针对雷达目标识别存在大量无标签样本的实际情况，重点研究直推式支持向量机的应用问题。

The experiment results show that this measure can solve the algorithm's unsteadiness caused by the few random large samples.

实验结果表明，该方法能有效地解决随机大样本所造成的算法不稳定问题。

Based on the market microstructure theory, this paper firstly discusses how the different trading mechanisms decide the price and the relationship of the trading mechanism and the volatility of return. Then selecting the stocks synchronously listed in the market of Mainland China and Hong Kong as the sample, we empirically analyze the relationship of the trading mechanism and the volatility of return. After describing the originality variance ratio of the markets, this paper explains the outcome of the empirical and makes a GARCH (1, 1) model for further analyze.

本文以金融市场微观结构理论为基础，首先从理论上探讨了不同的交易机制对股票价格的确定过程，以及交易机制与股票价格波动性的关系问题；接着本文选用同在中国大陆和中国香港地区上市的公司股票每日的开盘和收盘价格为样本，分别以收益率的原始方差比和GARCH(1， 1)模型估计的方差比实证分析了交易机制与股价波动性的关系。

Throught adaptive algorithm of network, the system constantly revise right values distribute so as to meet goal. Distribute the heuristic knowledge and the experience knowledge to network interconnection and right value.?The reasoning machine carries on reasoning according to the knowledge that involve in knowledge base and fact that users offer.?Through front computation of nerve network, the output port obtains the output vector.?The explanation module of ES is explained to user.At last, this paper has realized grab hydraulic system based on ANNES intelligent diagnosis, it has proven this fault diagnosis method feasibility.

ANNES的工作过程是：①首先建立知识库；②学习系统获取知识时，它只要求专家提供范例及相应的解，通过神经网络学习算法对样本进行学习，经过网络内部自适应算法不断修改权值分布以达到要求，把专家求解实际问题的启发式知识和经验分布到网络的互连及权值分布上；③推理机根据知识库中的知识和用户提供的事实进行推理；④通过神经网络的前向计算，在输出端获得输出矢量：⑤经专家系

The syndrome of the most dementia patients from this study are inter-mediate level .The result of this study shows that the longer period patients got dementia and the more time caregivers have spent for caring patients, and the worse ADL, deviant behaviors and emotions of patients, the havier burden the caregivers would get.

样本群主要以中重度失智患者为主，本研究分析结论显示：当患者罹患失智症越久、照顾者照顾时间越长、照顾者每天花费於照顾患者的时间越多、患者之日常生活功能越差、患者之行为情绪问题越严重时，则照顾者之照顾负荷将越重。

At the early 1980s, is an effective mathematic tool to deal with the uncertain or fuzzy knowledge. Rough rule theory has been widely used in information retrieval, digital library, software engineering and knowledge discovery. Its main idea includes acquisition of rough decision rules by reduction of data under the condition of keeping an invariability of classification capacity. And it basically represents a concept by a pair of approximation sets according to the partition on the given data based on the indiscernibility relation. Rough sets theory is well suited to deal with inconsistency of the rough approximations. So it is a new mathematical tool dealing with vagueness and uncertainty, and has found its applications in many areas such as AI, KDD, pattern recognition and classification and fault diagnosis.

主要完成了以下几个方面的工作：(1)对于高速移动机器人车道线跟踪问题中的规则知识获取，首先阐述了模糊逻辑系统的基本特点、工作原理和基本作法，分析了模糊规则知识获取过于依赖专家经验知识、对于每一个细节几乎都需要人工主观经验的参与、难以处理大数据集样本等方面的不足，进而阐述了粗糙集合理论的基本特点、基于粗糙集合理论的规则获取的关键技术和工作原理，为后续章节中经典粗糙集合模型的扩展及粗糙决策规则集的性能分析做好基础；(2)在经典粗糙集理论及其一般扩展的可变精度粗糙集VPRS的基础上，提出了非均匀可变精度粗糙集模型k-VPRS。

One hundred and fifty specimens of Pelteobagrus intermedius from 12 drainage systems were collected to measure 21 morphometric characters using traditional taxonomic methods. Data on the morphometric characters were analyzed using principal component analysis in order to discuss the morphological variation and geographical differentiation of the characters.

为探讨不同水系中间黄颡鱼的形态差异及地理分化问题，采用形态学方法，测量12个水系中间黄颡鱼150尾样本的18个形态性状，进行主成分分析。

Methods: Questionaires from parents were seperately used to assess frequency of interparental discords and children's problem behaviors.

从前期研究样本中，选取父母报告均完整的儿童103人（男42人，女61人），采用互动适应量表和儿童行为核查表要求父母分别报告彼此之间分歧的频繁程度和儿童的问题行为。

Do you know, i need you to come back

你知道吗，我需要你回来

Yang yinshu、Wang xiangsheng、Li decang,The first discovery of haemaphysalis conicinna.

1〕 杨银书，王祥生，李德昌。安徽省首次发现嗜群血蜱。