Medical Image Retrieval Based on Multi-Layer Resampling Template

Medical image application in clinical diagnosis and treatment is becoming more and more widely, How to use a large number of images in the image management system and it is a very important issue how to assist doctors to analyze and diagnose. This paper studies the medical image retrieval based on multi-layer resampling template under the thought of the wavelet decomposition, the image retrieval method consists of two retrieval process which is coarse and fine retrieval. Coarse retrieval process is the medical image retrieval process based on the image contour features. Fine retrieval process is the medical image retrieval process based on multi-layer resampling template, a multi-layer sampling operator is employed to extract image resampling images each layer, then these resampling images are retrieved step by step to finish the process from coarse to fine retrieval.     

The verification and analysis on the results of the video retrieval system

The retrieval of video information is a key multimedia technology, which has been paid wide-range attention recently. This paper introduces the verification and analysis of video information results in the video retrieval system from three aspects： first, the way of the browse and navigation; second, video summary; third, display and interaction interface.     

Distributed and cooperative information retrieval on the World Wide Web

A masss of heterogeneous,distributed and dynamic information on the World Wide Web(the Web) has resulted in “information overload“ .It‘s an important and urgent reserach issue to provide users with effective information retrieval service on the Web.Web search enginees attempt to solve this problem,yet their effect is far from satisfying.In this paper,a distributed and cooperative strategy for information retrieval on the Web is proposed to substitute the centralized mode adopted by the current search engines.Then a new information retrieval system model IRSM is presented.which supports the retrieval of metadata about web documents and uses Z39.50 standard protocol to unify the heterogeneous interfaces of uments and uses Z39.50 standard protocol to unify the heterogeneous interfaces of different systems.Based on that,a distributed and cooperative information refieval framework,called DCIRF,is designed to help users in fast and effective information retrieval on the Web.     

CALA: A Web Analysis Algorithm Combined with Content Correlation Analvsis Method

Web hyperlink structure analysis algorithm plays a significant role in improving the precision of Web information retrieval. Current link algorithms employ iteration function to compute the Web resource weight. The major drawback of this approach is that every Web document has a fixed rank which is independent of Web queries. This paper proposes an improved algorithm that ranks the quality and the relevance of a page according to users' query dynamically. The experiments show that the current link analysis algorithm is improved.     

CALA: A Web analysis algorithm combined with content correlation analysis method

Web hyperlink structure analysis algorithm plays a significant role in improving the precision of Web information retrieval.Current link algorithms employ iteration function to compute the Web resource weight.The major drawback of this approach is that every Web document has a fixed rank which is independent of Web queries.This paper proposes an improved algorithm that ranks the quality and the relevance of a page according to users‘ query dynamically.The experiments show that the current link analysis algorithm is improved.     

Content-based facial image retrieval using common vector

Abstract： Facial image retrieval is an essential application of content-based image retrieval. Based on the analysis of the practical application background, this paper proposes a new facial image retrieval scheme. In this scheme, the input query image is firstly transformed by four different methods to generate virtual samples and enlarge the training set. Moreover common vector method is applied to span the feature space for the training set whose images just belong to one class. To prove the feasibility of the scheme, a series of experiments are performed on the ORL face database.     

基于地理空间本体的语义检索相关度研究

以地理信息领域为应用背景,面向地理空间语义检索,基于地球信息科学中的空间拓扑理论,以空间本体为语义检索的概念空间,提出了一种语义相关度的算法。其特点是考虑了传统字面匹配相关度与语义关系相关度两部分的融合,同时引入了本体关系权值的机制控制在不同语义检索应用中本体的关联程度,并体现了其与语义距离的反比关系。通过所作的相关实验,验证了该语义相关度算法在地理空间语义检索应用中可以达到良好的效果,并且也为其他领域应用提供了较好的参考和借鉴价值。     

基于灰关联理论的滚动轴承故障诊断研究

针对实际工程中滚动轴承故障的复杂灰特性以及不确定性问题,提出了基于灰关联理论故障诊断方法。灰关联理论具有"小样本、贫信息、不确定性"问题处理能力强、计算复杂度低等优点。通过对灰关联原理、灰关联系数与分辨系数的关系,以及分辨系数的性质和取值原则的研究,成功地将灰关联理论应用于滚动轴承的故障诊断。仿真实例研究结果表明,灰关联故障诊断方法计算简单、诊断结果与定性分析结论一致,便于形成知识库中的规则,对工程实践具有理论指导作用,且对样本数量及其分布规律没有特殊要求,有较大实用价值。     

基于语义相关度主题爬虫的语料采集方法

针对特定领域语料采集任务,设计了基于语义相关度主题爬虫的语料采集方法.根据选定的主题词,利用页面描述信息,基于维基百科中文语料训练出的词分布式表示综合HowNet计算页面信息相关度,结合URL的结构信息预测未访问URL链指的页面内容与特定领域的相关程度.实验表明,系统能够有效的采集互联网中的党建领域页面内容作为党建领域生语料,在党建领域网站上的平均准确率达到94.87%,在门户网站上的平均准确率达到64.20%.     

基于汉语复句的语义相关度计算及类别的标识

语义相关度计算作为中文信息处理领域中的一项关键技术,在信息检索、语义消岐、文本分类中起着重要的作用。利用汉语复句的句法理论和关系标记搭配理论,以汉语复句语料库以及搜索引擎获取的复句为语料,提出了一种基于汉语复句的语义相关度计算方法——SRCCS。本方法不仅能够计算词语的相关度,而且能够表明相关的性质与类别。与通过短文计算相关度的方法相比,本方法选取的计算对象范围更小,因而结果更准确,计算复杂度更低。在同一测试集上与搜索引擎方法的对比分析证明了基于汉语复句的语义相关度计算方法的有效性与优越性。     

中文语义相关度计算模型研究

现有的中文语义相关度计算模型对相关度的定义并不明确和统一,且计算方法多以相似度计算为基础,导致应用语义相关度存在局限。提出了一个新的语义相关的定义,认为两个词所表达的概念之间,如果存在用类似“知网”的知识描述体系所描述的语义关系,那么这两个概念之间就是语义相关的。通过挖掘这些直接或间接的关系,提出了一种新的语义相关度的计算模型,适用于所有类似知网的知识体系中语义相关度的计算。最后将该计算模型应用于词义排歧,验证了该计算模型的有效性。     

基于文档相关度计算的网页预测模型

基于网络日志挖掘的网页预测系统可以有效地分析用户未来的网络访问请求,从而达到智能推荐、改善网络性能等目的。针对目前的预测模型缺乏有效的语义处理的问题,将词语语义信息和统计语言模型相结合,提出一种基于文档相关度计算的网页统计预测模型。通过词频信息和知网(HowNet)中词的概念计算模型计算网页文档间的主题相关度,再将该语义信息与统计模型计算的条件概率值相结合,以此作为预测的依据。实验表明,该技术使预测模型的性能获得了较大的提高。     

模糊聚类在信息检索中的应用

信息检索是与数据库系统并行发展了很多年的一个领域,它主要研究大量文本的信息组织和检索。典型的信息检索问题是基于用户的输入来定位相关的文本。而文本的相关性是一个模糊的概念,为了对这个模糊的概念以客观的度量,提出了一种新的文本间相关性的计算方法,该方法利用词频矩阵和模糊相似矩阵,在基于相关性检索的一组文档中,使用模糊聚类中的最大树算法,计算出一组文档间的相关度,最后用一个实例加以说明,得到了比较客观的结果。     

Efficient Methodologies to Determine the Relevancy of Hanging Pages Using Stability Analysis

This article presents an algorithm to determine the relevancy of hanging pages in the link-structure-based ranking algorithms. Recently, hanging pages have become major obstacles in web information retrieval (IR). As an increasing number of meaningful hanging pages appear on the Web, their relevancy has to be determined according to the query term in order to make the search engine result pages fair and relevant. Exclusion of these pages in ranking calculation can give biased/inconsistent results, but inclusion of these pages will reduce the speed significantly. Most of the IR ranking algorithms exclude the hanging pages. But there are relevant and important hanging pages on the Web, and they cannot be ignored. In our proposed method, we use anchor text to determine the hanging relevancy, and we use stability analysis to show that rank results are consistent before and after altering the link structure.     

医疗卫生局域网内文件检索及共享系统研究

医疗卫生电子文档文件在局域网内进行文件检索、共享操作已经成为了电子化医疗办公的重要环节。本文首 先论述了FTP 技术与应用开发环境,然后从文件共享分级设计、用户操作客户端、系统支撑服务器端三方面分析了医疗卫生局 域网内文件检索及共享系统开发和功能实现。