搜索引擎定量评价模型研究

搜索引擎性能的评价一般采用定性或定量的方法,在确定搜索引擎评价指标体系的基础上,本文利用模糊多属性决策研究了搜索引擎定量评价问题,为定量评价搜索引擎提供了一种途径.     

搜索引擎综合评价模型研究

首先给出了搜索引擎评价指标体系及计算公式 ,然后讨论了各指标权重的确定方法 ,在此基础上 ,利用多目标决策理论建立起搜索引擎综合评价数学模型 ,并通过具体实例说明了模型的使用     

基于模糊数学和灰色理论的多层次综合评价方法及其应用

针对多层次指标体系的综合评价问题,在模糊综合评判方法的基础上,结合灰色理论,提出了一种新的定量综合评价方法—多层次模糊灰关联聚类分析综合评价方法.应用该方法对油气钻井技术进行综合评价,取得了满意的结果.     

人机界面的模糊多层次综合评价

人机界面(HCI)是影响多媒体软件设计质量的重要因素之一。由于人机界面设计本身的复杂性,使得对它的评价具有一定的难度。本文提出了采用定性和定量相结合的模糊多层次综合评价方法对软件的人机界面进行评价,并讨论了基于模糊语言的单因素定量评价方法和利用层次分析法(AHP)确定各评价因素的权重。     

偏好约束锥DEA模型在工业企业创新效率评价中的应用

为解决工业企业创新活动中的创新效率评价方法不能同时兼顾定量与定性分析的问题,结合现有的创新效率评价的方法,以及评价中既要依赖客观数据又要反映决策者偏好的评价准则特点,构建了带有偏好锥的DEA模型,并建立了相应的创新效率投入产出指标体系.利用该模型和体系对创新效率评价方法进行了研究,最后以重庆市2007年工业企业创新统计数据为依据,对8个不同类型企业的创新效率进行了评价.研究表明:该方法能反映决策者的偏好,解决了定量与定性分析相结合的问题.     

基于多元统计的居民消费水平评价模型及应用

为解决传统主成分分析在消费水平评价应用中的局限性,对传统主成分方法作了改进,建立一种新的评价模型,利用此模型对青海城镇居民消费水平进行评价.结果表明:这是一种适合于居民消费水平综合定量评价且切实有效的方法模型,有较强的实践价值.     

投资环境的多层次灰色评价方法研究

针对投资环境评价问题 ,应用定性与定量相结合的分析方法 ,通过建立投资环境综合评价的指标体系 ,给出了一个投资环境评价的多层次灰色评价方法 .最后给出一个实例     

企业竞争力综合评价物元模型与可拓评价方法

本用可拓学的思想方法建立了企业竞争力综合评价物元模型，给出了基于关联函数的可拓评价方法，对企业竞争力的定性，定量综合评价方法进行了创新性研究。     

求解PageRank问题的GMRES重启的松弛两步分裂法

正1引言随着互联网信息的快速发展,网络搜索引擎是人们通过互联网获取信息的重要工具.搜索引擎的关键技术就是网页排序,其核心是搜索引擎算法的设计.斯坦福大学的Larry和Sergey Brin在1996年提出的PageRank算法,主要是用于网页评级的系统,该算法在Google搜索引擎中取得了很大的成功.所谓PageRank问题就是求解Google矩阵A的首特征值1所对应的特征向量,即线     

熵权法在炮兵战场目标价值评价中的应用

建立了战场目标目标的战术重要性、威胁程度、打击紧迫性等三个方面的评价体系,按定量与定性相结合的原则,采用熵权法的评价方法建立了评价模型,并对目标价值评价进行了实例分析.     

Multiple factor hierarchical clustering algorithm for?large scale web page and search engine clickstream data

The developments in World Wide Web and the advances in digital data collection and storage technologies during the last two decades allow companies and organizations to store and share huge amounts of electronic documents. It is hard and inefficient to manually organize, analyze and present these documents. Search engine helps users to find relevant information by present a list of web pages in response to queries. How to assist users to find the most relevant web pages from vast text collections efficiently is a big challenge. The purpose of this study is to propose a hierarchical clustering method that combines multiple factors to identify clusters of web pages that can satisfy users?? information needs. The clusters are primarily envisioned to be used for search and navigation and potentially for some form of visualization as well. An experiment on Clickstream data from a processional search engine was conducted to examine the results shown that the clustering method is effective and efficient, in terms of both objective and subjective measures.     

On the feasibility of applying capture–recapture experiments for web evolution estimations

This paper proposes a novel application for estimating the size and evolution of web page populations, based on the capture–recapture methodology, which is mainly used in wildlife biological studies. Firstly, we present the necessary modifications and amendments needed for the web capture–recapture paradigm, and then we discuss the limitations confronted. The paper provides the implementation details of the proposed web capture recapture model along with its initial assessment. The anticipated outcome was to examine whether we can conduct capture–recapture experiments on the web (or a web sub-universe such as an Internet search engine directory), in order to further estimate evolution rates in web page populations.     

A Power–Arnoldi algorithm for computing PageRank

The PageRank algorithm plays an important role in modern search engine technology. It involves using the classical power method to compute the principle eigenvector of the Google matrix representing the web link graph. However, when the largest eigenvalue is not well separated from the second one, the power method may perform poorly. This happens when the damping factor is sufficiently close to 1. Therefore, it is worth developing new techniques that are more sophisticated than the power method. The approach presented here, called Power–Arnoldi, is based on a periodic combination of the power method with the thick restarted Arnoldi algorithm. The justification for this new approach is presented. Numerical tests illustrate the efficiency and convergence behaviour of the new algorithm. Copyright © 2007 John Wiley & Sons, Ltd.     

基于主成分分析的网络搜索数据合成方法研究

针对利用网络搜索数据合成各类指数时难以消除共线性、难以合理确定各指标权重等问题,基于数据降维的思想构建了以主成分分析法为核心的指数合成方法,并以利用网络搜索数据合成消费者物价指数为例,将提出的方法与当前主流的逐步回归法做出比较研究.研究结果表明,基于主成分分析法的数据合成方法可以得到稳定性和拟合度更高的指数.     

CFD-based optimization of fuel injection strategies in a diesel engine using an adaptive gradient method

A computationally efficient computational fluid dynamics (CFD)-based optimization method with the capability of finding optimal engine operating conditions with respect to emissions and fuel consumption has been developed. The approach taken uses a steepest descent method for an adaptive cost function, where the line search is performed with a backtracking algorithm. The backtracking algorithm utilizes quadratic and cubic polynomials to accelerate the convergence, and the initial backtracking step employs an adaptive step size mechanism which depends on the steepness of the search direction. The adaptive cost function is based on the penalty method such that the penalty term is stiffened after every line search. The engine simulations are performed with a KIVA-3-based CFD code which is equipped with well-established spray, combustion and emission models. The application of this optimization tool is demonstrated for a non-road, medium-speed DI diesel engine which, for these simulations, utilizes a multi-orifice, asynchronous injection system. It has been demonstrated that this new injection method has a large potential for reducing emissions while maintaining a low fuel consumption. In addition, this optimization approach is computationally very efficient when good enough initial values are available.     

Theoretical game analysis of position auctions according to the Vickrey–Clarke–Groves mechanism with two-stage ranking

Different types of position auctions are considered. A position auction is a mechanism for the allocation of advertising space in search engine results to a user-defined query. Advertisers make bids they are willing to pay the search engine for a click to their website. The search engine determines whose advertisements will get to the page and in what position, based on the bids of all the advertisers. Different types of such auctions are discussed using the example of the Yandex search engine based on the Vickrey–Clarke–Grovesmechanism. The main result is a formalization of the concept of an auction with two-stage ranking and its balance test.     

A fully adaptive hybrid optimization of aircraft engine blades

A new fully adaptive hybrid optimization method (AHM) has been developed and applied to an industrial problem in the field of the aircraft engine industry. The adaptivity of the coupling between a global search by a population-based method (Genetic Algorithms or Evolution Strategies) and the local search by a descent method has been particularly emphasized. On various analytical test cases, the AHM method overperforms the original global search method in terms of computational time and accuracy. The results obtained on the industrial case have also confirmed the interest of AHM for the design of new and original solutions in an affordable time.     

求解PageRank问题的重启GMRES修正的多分裂迭代法

PageRank算法已经成为网络搜索引擎的核心技术。针对PageRank问题导出的线性方程组,首先将Krylov子空间方法中的重启GMRES(generalized minimal residual)方法与多分裂迭代(multi-splitting iteration,MSI)方法相结合,提出了一种重启GMRES修正的多分裂迭代法;然后,给出了该算法的详细计算流程和收敛性分析;最后,通过数值实验验证了该算法的有效性。