利用输入信号先验知识构造某些分类神经网络的研究

提出一种前向神经网络只有一个隐元就可以解决奇偶校验或对称性校验问题，讨论了如何根据输入模式的先验知识来推导隐元的传递函数的构造该分类神经网络的方法，和已有的研究工作相比，提出的前向神经网络是解决某些线性不可分的模式识别问题的最简单的网络结构，所提出的分析方法也可推广用于类似的网络构造问题。     

K—距离空间中某些不动点定理

本文首次引进Ｋ－距离空间的概念，推广了２－距离空间的概念，并且给出了Ｋ－距离空间中某些不动点定理，它不仅是距离空间中相应定理的推广，也是２－距离空间中相应定理的推广。     

汉字识别误差校正

本文提出了一种对句法模式进行误差校正的方法,通过分析变形笔划y与文法G能接受的笔划x,求出y与G的最小误差校正距离|J|,比较y与其它文法G′的最小误差校正距离|J′|,确定y应属于G或G′。为了改善误差校正剖析程序的执行速度,规定了一个能减少回溯次数的误差校正算子的优先级。同时,用启发式方法进行搜索以减少搜索的深度。最后给出实验结果。     

企业领导人素质浅议

在社会主义市场经济条件下，企业领导人必须具有如下素质：一、政治素质、二、道德素质；三、知识素质；四、经营素质。     

黄瓜病虫害诊断专家系统知识组织的研究与设计

针对黄瓜病虫害的特点和特征描述,利用产生式-特征表结合的表达方式、模糊逻辑和可能性理论,对黄瓜病虫害诊断的知识组织进行研究,解决了黄瓜病虫害诊断过程中的症状表现的偶然性和差异性。该研究对于开发一系列的蔬菜病虫害诊断专家系统有很好的应用和参考价值。图1,表1,参10。     

Integrated semantic similarity model based on ontology

To solve the problem of the inadequacy of semantic processing in the intelligent question answering system. an integrated semantic similarity model which calculates the semantic similarity using the geometric distance and informarion content is presented in this paper. With the help of interrelationship between concepts, the information content ofconcepts and the strength of the edges in the ontology network. we can calculate the semantic similarity between two concepts and provide information for the further calculation of the semantic similarity between user‘s question and answers in knowlegdge base. The results of the experiments on the prototype have shown that the semantic problem in natural language processing can also be solved with the help of the knowledge and the abundant semantic information in ontology. More than 90% accuracy with less than 50 ms average searching time in the intelligent question answering prototype system based on ontology has been reached. The result is vety satisfied.     

Empirical study on mutual fund objective classification

Mutual funds are usually classified on the basis of their objectives. If the activities of mutual funds are consistent with their stated objectives, investors may look at the latter as signals of their risks and incomes. This work analyzes mutual fund objective classification in China by statistical methods of distance analysis and discriminant analysis; and examines whether the stated investment objectives of mutual funds adequately represent their attributes to investors. That is, if mutual funds adhere to their stated objectives, attributes must be heterogeneous between investment objective groups and homogeneous within them. Our conclusion is to some degree, the group of optimized exponential funds is heterogeneous to other groups. As a whole, there exist no significant differences between different objective groups; and 50% of mutual funds are not consistent with their objective groups.     

Study on properties of residue-residue contacts in protein

Residue-residue contacts are very important in forming protein structure. In this work, we calculated the average probability of residue-residue contacts in 470 globular proteins and analyzed the distribution of contacts in the different interval of residues using Contacts of Structural Units (CSU) and Structural Classification (SCOP) software. It was found that the relationship between the average probability PL and the residue distance L for four structural classes of proteins could be expressed as lgPL=a+b x L, where a and b are coefficients. We also discussed the connection between two aspects of proteins which have equal array residue number and found that the distribution probability was stable (or un-stable) if the proteins had the same (or different) compact (for example synthase) in the same structural class.     

A flower image retrieval method based on ROI feature

Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images. For flower retrieval, we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets, Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH), to characterize the shape features of a flower contour. Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions. Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest (ROI) based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard (1991) and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).     

21世纪图书馆文献信息人员的自我更新势在必行

走进21世纪,严峻的现实使我们更加认识到,经济对知识的依赖性越来越强.任何一个人单凭一方面专长已无法适应多变的环境要求,精一门、专一门、学三门,终身受教育,已成为愈来愈多的人的共识.早在1994年11月国际社会就于意大利罗马举行的"首届世界终身学习会议"上,提出"终身学习是21世纪的生存概念".这势必要求我们通过学习,吸取新知识、新信息和提出问题的能力,不断进行自我更新,变"学会"为"会学".