FindOut: Finding Outliers in Very Large Datasets

Finding the rare instances or the outliers is important in many KDD (knowledge discovery and data-mining) applications, such as detecting credit card fraud or finding irregularities in gene expressions. Signal-processing techniques have been introduced to transform images for enhancement, filtering, restoration, analysis, and reconstruction. In this paper, we present a new method in which we apply signal-processing techniques to solve important problems in data mining. In particular, we introduce a novel deviation (or outlier) detection approach, termed FindOut, based on wavelet transform. The main idea in FindOut is to remove the clusters from the original data and then identify the outliers. Although previous research showed that such techniques may not be effective because of the nature of the clustering, FindOut can successfully identify outliers from large datasets. Experimental results on very large datasets are presented which show the efficiency and effectiveness of the proposed approach. Received 7 September 2000 / Revised 2 February 2001 / Accepted in revised form 31 May 2001 Correspondence and offprint requests to: A. Zhang, Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY 14260, USA. Email: azhang@cse.buffalo.eduau     

中国学术期刊网燕化镜像站点建设

通过中国学术期刊网燕化镜像站点的建设，介绍了燕山石化镜像站点的配置及主要管理功能和对全文数据库的检索，浏览功能，同时介绍了新形势下，信息化建设的新观念，新思路，以及强化信息意识，加强信息服务产业化发展的重要性和迫切性。     

Ranking Pages by Topology and Popularity within Web Sites

We compare two link analysis ranking methods of web pages in a site. The first, called Site Rank, is an adaptation of PageRank to the granularity of a web site and the second, called Popularity Rank, is based on the frequencies of user clicks on the outlinks in a page that are captured by navigation sessions of users through the web site. We ran experiments on artificially created web sites of different sizes and on two real data sets, employing the relative entropy to compare the distributions of the two ranking methods. For the real data sets we also employ a nonparametric measure, called Spearman's footrule, which we use to compare the top-ten web pages ranked by the two methods. Our main result is that the distributions of the Popularity Rank and Site Rank are surprisingly close to each other, implying that the topology of a web site is very instrumental in guiding users through the site. Thus, in practice, the Site Rank provides a reasonable first order approximation of the aggregate behaviour of users within a web site given by the Popularity Rank.     

A Knowledge-Navigation System for Dimensional Metrology

Geometric dimensioning and tolerancing (GD&T) is a method to specify the dimensions and form of a part so that it will meet its design intent. GD&T is difficult to master for two main reasons. First, it is based on complex 3D geometric entities and relationships. Second, the geometry is associated with a large, diverse knowledge base of dimensional metrology with many interconnections. This paper describes an approach to create a dimensional metrology knowledge base that is organized around a set of key concepts and to represent those concepts as virtual objects that can be navigated with interactive, computer visualization techniques to access the associated knowledge. The approach can enable several applications. First is the application to convey the definition and meaning of GD&T over a broad range of tolerance types. Second is the application to provide a visualization of dimensional metrology knowledge within a control hierarchy of the inspection process. Third is the application to show the coverage of interoperability standards to enable industry to make decisions on standards development and harmonization efforts. A prototype system has been implemented to demonstrate the principles involved in the approach.     

Revising deductive knowledge and stereotypical knowledge in a student model

A user/student model must be revised when new information about the user/student is obtained. But a sophisticated user/student model is a complex structure that contains different types of knowledge. Different techniques may be needed for revising different types of knowledge. This paper presents a student model maintenance system (SMMS) which deals with revision of two important types of knowledge in student models: deductive knowledge and stereotypical knowledge. In the SMMS, deductive knowledge is represented by justified beliefs. Its revision is accomplished by a combination of techniques involving reason maintenance and formal diagnosis. Stereotypical knowledge is represented in the Default Package Network (DPN). The DPN is a knowledge partitioning hierarchy in which each node contains concepts in a sub-domain. Revision of stereotypical knowledge is realized by propagating new information through the DPN to change default packages (stereotypes) of the nodes in the DPN. A revision of deductive knowledge may trigger a revision of stereotypical knowledge, which results in a desirable student model in which the two types of knowledge exist harmoniously.     

"Interactive use of lexical information in speech perception": Correction to Connine and Clifton.

Reports an error in "Interactive use of lexical information in speech perception" by Cynthia M. Connine and Charles Clifton (Journal of Experimental Psychology: Human Perception and Performance, 1987[May], Vol 13[2], 291-299). In the aforementioned article, Figures 1 and 2 were inadvertently transposed. The figure on p. 294 is actually Figure 2, and the figure on p. 296 is actually Figure 1. The captions are correct as they stand. (The following abstract of the original article appeared in record 1987-23984-001.) Two experiments are reported that demonstrate contextual effects on identification of speech voicing continua. Experiment 1 demonstrated the infuence of lexical knowledge on identification of ambiguous tokens from word–nonword and nonword–word continua. Reaction times for word and nonword responses showed a word advantage only for ambiguous stimulus tokens (at the category boundary); no word advantage was found for clear stimuli (at the continua endpoints). Experiment 2 demonstrated an effect of a postperceptual variable, monetary payoff, on nonword–nonword continua. Identification responses were influenced by monetary payoff, but reaction times for bias-consistent and bias-inconsistent responses did not differ at the category boundary. An advantage for bias-consistent responses was evident at the continua endpoints. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

仿真环境中的网络攻击模型设计

阐述了仿真环境中的网络攻击模型的设计,建立了一个网络攻击仿真模型,用以产生网络攻击,以达到摧毁网络的机密性、完整性和可用性的目的;采用知识表达的方法来建立模型,该模型包含具有知识库和推理机的专家系统,通过随时间而变化的量,使模型具有基于仿真时钟的推理能力;在攻击模型的设计中,定义了它的基本状态和状态跃迁函数,说明了模型的行为,以及攻击策略的制定,最佳策略的选择,攻击选择原则等问题。     

合理开发利用钨矿资源 促进钨矿业可持续发展

简述了我国钨矿业概况、现有采选技术水平及钨矿加工利用率 ;从资源配置出发 ,阐述了钨矿业发展存在的几个主要问题 ,并且针对性地提出了可持续发展的几点建议。     

Diversity training in graduate school: An exploratory evaluation of the Safe Zone project.

How can psychologists and graduate students become more affirmative of lesbian, gay, bisexual, and transgender (LGBT) issues? Safe Zone is a diversity-training program to increase sensitivity toward, knowledge of, and advocacy for LGBT populations and issues that affect them. In this exploratory study, the implementation of Safe Zone is described within a school of professional psychology; its effectiveness was assessed by self-reported behavioral and attitudinal changes and from participant evaluations. Results were encouraging with regard to the goals of Safe Zone and its adaptation to institutions interested in improving relations with the LGBT community, but additional empirical studies are needed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

未结盟大学的联盟

通过梳理管理学界对战略联盟的定义，发现价值链的鸸释同样适用于大学问的战略联盟。通过对已有的大学战略联盟的分析，提出了名校联盟与非名校联盟间的若干差异，最后提出了我国大学联盟战略的若干建议。