范例推理结构相似性研究

本文将范例的结构相似性问题提炼为结构图的相似问题,改变了将范例属性线性地映射到区间的方式,建立以关键节点为特征的分层模型,来进行范例结构图比较,并得到一个可以计算的合理的相似度数值,可以较为方便地解决结构相似性度量的问题,为复杂范例的多种类型的带偏序的属性的综合比较提供了基础。最后本文提供了一个例子,对相似性模型作了说明。     

CBRDI:一种基于范例推理的数据集成方法

设计并实现了基于范例推理的数据集成系统CBRDI,能够通过积累的领域知识即范例进行有效的数据集成操作。CBRDI采用框架网络表示范例,并通过聚类方法对源范例进行组织和索引,提高了范例搜索的效率。CBRDI系统实现简单,并具有较强的自学习的能力,推理效率高。     

Information Technology Knowledge Sharing Using Case-Based Reasoning

In the relatively short time since the first case-based reasoning systems were implemented, there have been numerous academic CBR demonstrators. CBR systems have been used in diagnosis of diseases, planning, legal reasoning, software design, arbitration, weather forecasting, tutoring, and help desk operations, to name a few.     

Using a Benchmark in Case-Based Multiple-Criteria Ranking

A benchmark-based method is proposed for multiple-criteria ranking, and a case study is presented to demonstrate that the procedure can be efficient and effective in practice. Multiple-criteria ranking aims to help a decision maker (DM) assess a finite set of alternatives according to several criteria, usually conflicting, in order to rank the full set. The relation of benchmarks to multiple-criteria decision analysis is investigated systematically, and then, an approach based on distance from a benchmark is designed to incorporate information about a DM's judgements so as to produce a full ranking. The procedure is applied to rank 81 U.S. brownfield redevelopment projects based on available data and an accepted benchmark.      

名词隐喻相似度及推理识别研究

本文考察了汉语名词隐喻的相似性特点,尝试利用隐喻相似度推理、词典信息等多种方法实现n＋n隐喻表达的发现和提取。隐喻相似度推理,首先运用人机互助方法对中文概念词典(CCD)进行合理剪裁,建立了一个词语对应一个语义类的词典格式,为后续的推理实验提供了保证。同时也验证了名词隐喻知识库的有效性。实验证明,最大熵方法、隐喻相似度、词典知识等多种方法大大提高了识别效果。     

基于事例推理的棉纺工艺专家系统推理模型的设计

基于事例推理是人工智能中的一种重要的推理技术,它的优势在于用众多的事例来有效地支持设计者的工作。论文结合棉纺工艺设计过程详细地介绍了推理模型的设计,为基于事例推理的专家系统提供实用参考。     

Global Navigation in Dynamic Environments Using Case-Based Reasoning

This paper presents a global navigation strategy for autonomous mobile robots in large-scale uncertain environments. The aim of this approach is to minimize collision risk and time delays by adapting to the changes in a dynamic environment. The issue of obstacle avoidance is addressed on the global level. It focuses on a navigation strategy that prevents the robot from facing the situations where it has to avoid obstacles. To model the partially known environment, a grid-based map is used. A modified wave-transform algorithm is described that finds several alternative paths from the start to the goal. Case-based reasoning is used to learn from past experiences and to adapt to the changes in the environment. Learning and adaptation by means of case-based reasoning permits the robot to choose routes that are less risky to follow and lead faster to the goal. The experimental results demonstrate that using case-based reasoning considerably increases the performance of the robot in a difficult uncertain environment. The robot learns to take actions that are more predictable, minimize collision risk and traversal time as well as traveled distances.     

基于XML安全的Email可信SOAP传输

随着数据共享和互操作性的增强,Email传输的安全性越来越受到企业和政府的重视.文中通过在SOAP传输中结合XML安全,给出了一种解决方案,使Email能够以对外透明的形式发送给对方.同时,对应一封电子邮件,采用XML加密和签名分段封装Email,使接收者只能看到其中和自己相关的部分.这不仅实现了Email的共享,而且不会造成信息的泄漏.     

基于XML安全的Email可信SOAP传输

随着数据共享和互操作性的增强,Email传输的安全性越来越受到企业和政府的重视。文中通过在SOAP传输中结合XML安全,给出了一种解决方案,使Email能够以对外透明的形式发送给对方。同时,对应一封电子邮件,采用XML加密和签名分段封装Email,使接收者只能看到其中和自己相关的部分。这不仅实现了Email的共享,而且不会造成信息的泄漏。     

Understanding Similarity: A Joint Project for Psychology, Case-Based Reasoning, and Law

Case-based Reasoning (CBR) began as a theory of human cognition, but has attracted relatively little direct experimental or theoretical investigation in psychology. However, psychologists have developed a range of instance-based theories of cognition and have extensively studied how similarity to past cases can guide categorization of new cases. This paper considers the relation between CBR and psychological research, focussing on similarity in human and artificial case-based reasoning in law. We argue that CBR, psychology and legal theory have complementary contributions to understanding similarity, and describe what each offers. This allows us to establish criteria for assessing existing CBR systems in law and to establish what we consider to be the crucial goals for further research on similarity, both from a psychological and a CBR perspective.     

Learning and Herding Using Case-Based Decisions With Local Interactions

We evaluate repeated decisions of individuals using a variant of the case-based decision theory (CBDT), where individuals base their decisions on their own past experience and the experience of neighboring individuals. Looking at a range of scenarios to determine the successful outcome of a decision, we find that for learning to occur, agents must have a sufficient number of neighbors to learn from and access to sufficiently independent information. If these conditions are not fulfilled, we can easily observe herding in cases where no best decision exists.     

An Exception Handling of Rule-Based Reasoning Using Case-Based Reasoning

In this paper, we propose the CCAR (Combining Case-based And Rule-based reasoning) model for an exception handling of Rule-based Reasoning using Case-based Reasoning. The central idea of the model proposed in this paper is to represent the exception of a rule as a case, and to utilize the case for a solution to a problem, and then to search the case memory to retrieve a case which violates the conclusion of a rule. If the similarity between a target problem and the selected case is high, the conclusion of a case is applied. Otherwise, the conclusion of rule-based reasoning is applied.     

Language Structure Using Fuzzy Similarity

Learning of (context-free) grammar rules that are based on alignment between texts of a given collection of sentences has attracted the attention of many researchers. We define and study the alignment profile and formulate fuzzy similarity of alignment profiles for a given collection of sentences. Using the fuzzy-similarity-based profile alignment, we give a methodology to formulate stochastic context-free grammar (CFG) rules. We introduce profile-alignment-based dynamic sentence similarity threshold to formulate the rules of stochastic CFG. The proposed methodology is tested using Child Language Data Exchange System (CHILDES) dataset of sentences. The benefits of our approach are experimentally demonstrated. Since our approach does not make use of any domain knowledge, it is expected to be useful in wide variety of applications requiring model construction.     

基于文法推断的协议逆向工程

要深入了解网络中的各种应用过程,进而对这些应用进行自动分类、识别、跟踪和控制,首先就要获得代表这些应用会话过程的状态机.为此提出一种新的方法从采集的应用层数据中反推协议状态机.它采用基于差错纠正的文法推断方法,利用应用层协议交互过程中出现的标识符状态序列,逆向工程其协议状态机.为充分挖掘和发挥差错纠正的性能,提出了最佳路径匹配标准确定纠正路径,以及基于概率统计的异常入度区分及其剪枝的方法;通过去重的状态合并和相似行为意义的协议结构化简措施解决状态膨胀问题,从而获取最精简的协议状态机.通过在包含多种应用层协议的实际网络中的实验,验证了该方法的有效性.     

Design Pattern Detection Using Similarity Scoring

The identification of design patterns as part of the reengineering process can convey important information to the designer. However, existing pattern detection methodologies generally have problems in dealing with one or more of the following issues: identification of modified pattern versions, search space explosion for large systems and extensibility to novel patterns. In this paper, a design pattern detection methodology is proposed that is based on similarity scoring between graph vertices. Due to the nature of the underlying graph algorithm, this approach has the ability to also recognize patterns that are modified from their standard representation. Moreover, the approach exploits the fact that patterns reside in one or more inheritance hierarchies, reducing the size of the graphs to which the algorithm is applied. Finally, the algorithm does not rely on any pattern-specific heuristic, facilitating the extension to novel design structures. Evaluation on three open-source projects demonstrated the accuracy and the efficiency of the proposed method     

Local Community Detection Using Link Similarity

Exploring local community structure is an appealing problem that has drawn much recent attention in the area of social network analysis.As the complete information of network is often difficult to obtain,such as networks of web pages,research papers and Facebook users,people can only detect community structure from a certain source vertex with limited knowledge of the entire graph.The existing approaches do well in measuring the community quality,but they are largely dependent on source vertex and putting too strict policy in agglomerating new vertices.Moreover,they have predefined parameters which are difficult to obtain.This paper proposes a method to find local community structure by analyzing link similarity between the community and the vertex.Inspired by the fact that elements in the same community are more likely to share common links,we explore community structure heuristically by giving priority to vertices which have a high link similarity with the community.A three-phase process is also used for the sake of improving quality of community structure.Experimental results prove that our method performs effectively not only in computer-generated graphs but also in real-world graphs.     

利用分块相似系数构造感知图像Hash

提出一种基于图像分块相似系数的感知稳健图像Hash.先对图像预处理,再进行重叠分块,在密钥控制下,利用高斯低通滤波器生成伪随机参考图像块,分别计算每个分块与参考图像块的相关系数得到图像特征序列.依此将相邻两个分块特征值合并以缩短Hash长度,同时对压缩后的特征序列进行重排,进一步提高图像Hash的安全性.最后对归一化特征值进行量化,并运用Huffman方法对其编码,进一步压缩Hash长度.理论分析和实验结果表明,该图像Hash方法对JPEG压缩、适度的噪声干扰、水印嵌入、图像缩放以及高斯低通滤波等常见图像处理有较好的鲁棒性,能有效区分不同图像,冲突概率低,可用于图像篡改检测.