模糊C-球壳聚类算法及其在血液细胞图像中的应用

文章从经典的模糊C均值算法开始通过改变其中相似性的度量形式，介绍了一种模糊C球壳聚类（FCSS）算法。在将该算法应用于细胞显微图像半径统计时，采用基于形态学的图像预处理措施，可以获得FCSS算法中有关原型模式的知识，加快收敛速度并避免随机初始化造成的局部极小问题。     

A Unified View on Clustering Binary Data

Clustering is the problem of identifying the distribution of patterns and intrinsic correlations in large data sets by partitioning the data points into similarity classes. This paper studies the problem of clustering binary data. Binary data have been occupying a special place in the domain of data analysis. A unified view of binary data clustering is presented by examining the connections among various clustering criteria. Experimental studies are conducted to empirically verify the relationships.     

Design of statistical databases: A methodology for the conceptual step

The aim of the conceptual step in database design is to describe data involving in the application in a formal and abstract way, without any concern to the specific model and language chosen for the implementation. In statistical applications, data are described at different levels of aggregation, from elementary facts of the reality to complex aggregations such as classifications, time series, indexes. The paper describes a methodology for conceptual design of statistical databases that provides the designer suitable strategies for defining such different levels of aggregation starting from user requirements, and checking the completeness, coherence and minimality of the conceptual schema at the different levels. The methodology makes use of two data models for the representation of data: for elementary data the Entity-Relationship model, widely used in database applications, and for summary data a new model is proposed, designed to be an effective trade-off between expressive power and simplicity of use.     

一种基于Web文本聚类的用户兴趣发现模型的研究

研究了一种基于Web文本聚类的用户兴趣发现方法．他通过Web文档信息获取，文本的形式表示，以及Web文本聚类方法最终提取用户兴趣知识，并给出了一个设计模型。     

Studies of substrate specificities of lipases from different sources

Although lipases are widely applied in a wide variety of reactions, available information on the factors that are responsible for the substrate specificities of lipases from different sources is scarce. In this paper, nine lipase‐producing microorganism strains were isolated from oil‐containing samples. The properties of these enzymes, including pH optima, temperature optima, thermal stability, and pH stability, vary significantly with the different sources from which these lipases were isolated. The substrate specificities of the nine lipases, including fatty acid and positional specificities, were also studied. The fatty acid specificities of the nine lipases were observably different toward 15 substrates with different carbon chain lengths, different saturation degrees and different side chains. The lipases from S₃ Penicillium citrinum (PCL), MJ₁ Aspergillus niger (ANL), MJ₂ Aspergillus oryzae (AOL), YM Bacillus coughing (BCL), S₉ Geotrichum candidum (GCL), and S₁₁ Candida lypolytica (CLL) showed the strongest specificities to short‐chain esters, and the other lipases showed strong selectivity for medium‐ or long‐chain and branched esters. The positional specificities were examined by analyzing the hydrolytic products of triolein catalyzed by the nine lipases, using TLC. The lipases can be mainly classified into two groups by their specificities for the ester bond at position 2 of triglycerides; one group can selectively hydrolyze the ester bond at position 2 of the triglycerides, the other group cannot. All these nine lipases were divided into four groups by hierarchical clustering analysis on the basis of the results of fatty acid and positional specificities.     

Genetic algorithms for symbolic clustering

This paper introduces a novel methodology for clustering of symbolic objects by making use of Genetic Algorithms (GAs). GAs are a family of computational models inspired by evolution. These algorithms encode potential solutions to specific problems on simple chromosome-like data structures and apply recombination operators to these structures so as to preserve critical information. A new type of representation for chromosome structure is presented here along with a new method for mutation. The efficacy of the proposed method is examined by application to numeric data of known number of classes and also to assertion type of symbolic objects drawn from the domain of fat oil, microcomputers, microprocessors and botany. The validity of the clusters obtained is examined.     

Familiarity and plausibility in conceptual combination: Reply to Gagné and Spalding (2006).

E. J. Wisniewski and G. L. Murphy (see record 2004-22496-015) suggested that the apparent effects of relation frequency in C. L. Gagné and E. J. Shoben's (1997; see record 1997-02349-004) conceptual combination experiments could be explained by differences between the familiarity and plausibility of their stimuli (noun-noun phrases). However, C. L. Gagné and T. L. Spalding (see record 2006-20573-017) argued that Wisniewski and Murphy's measures of plausibility and frequency are both sensitive to relation frequency. They also suggested that the stimuli were mostly novel, such that differences in familiarity could not explain Gagné and Shoben's findings. The current authors focus on the theoretical rationale for the plausibility and familiarity variables, arguing that the original interpretation of their findings is correct. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Pseudoinverse in clustering problems

The clustering of vector observations of hyperplanes is studied. Different cases of correspondence distances are proposed and investigated, including the algebraic Jack Knife one. The efficiency, constructivity, and explicit form of formulas are provided by using the pseudoinverse technique including the pseudoinverse-perturbation theory. Results important for the application of pseudoinverse and related operators are presented. __________ Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 73–92, July–August 2007.     

Optimal implementations of UPGMA and other common clustering algorithms

In this work we consider hierarchical clustering algorithms, such as UPGMA, which follow the closest-pair joining scheme. We survey optimal O(n²)-time implementations of such algorithms which use a ‘locally closest’ joining scheme, and specify conditions under which this relaxed joining scheme is equivalent to the original one (i.e. ‘globally closest’).     

Concealed weapon detection and visualization in a synthesized image

Images acquired by heterogeneous image sensors may provide complementary information about the scene, for instance, the visual image can provide personal identification information like the facial pattern while the infrared (IR) or millimeter wave image can detect the suspicious regions of concealed weapons. Usually, a technique, namely multiresolution pixel-level image fusion is applied to integrate the information from multi-sensor images. However, when the images are significantly different, the performance of the multiresolution fusion algorithms is not always satisfactory. In this study, a new strategy consisting of two steps is proposed. The first step is to use an unsupervised fuzzy k-means clustering to detect the concealed weapon from the IR image. The detected region is embedded in the visual image in the second step and this process is implemented with a multiresolution mosaic technique. Therefore, the synthesized image retains the quality comparable to the visual image while the region of the concealed weapon is highlighted and enhanced. The experimental results indicate the efficiency of the proposed approach.This material is based on part of the work carried out at the SPCR laboratory of Lehigh University and the work is partially supported by the U. S. Army Research Office under grant number DAAD19-00-1-0431. The content of the information does not necessarily reflect the position or the policy of the federal government, and no official endorsement should be inferred.