一种判定程序复杂性标准优劣的方法

本文提出了一种统计方法,对程序复杂性标准的优劣进行评定,对新标准和新方法的开发提供一种验证手段,对McCabe,Woodward等经典标准的分析度量表明,本文提出的方法是行之有效的。     

Efficient Leave-One-Out Strategy for Supervised Feature Selection

Feature selection is a key task in statistical pattern recognition. Most feature selection algorithms have been proposed based on specific objective functions which are usually intuitively reasonable but can sometimes be far from the more basic objectives of the feature selection. This paper describes how to select features such that the basic objectives, e.g., classification or clustering accuracies, can be optimized in a more direct way. The analysis requires that the contribution of each feature to the evaluation metrics can be quantitatively described by some score function. Motivated by the conditional independence structure in probabilistic distributions, the analysis uses a leave-one-out feature selection algorithm which provides an approximate solution. The leave-one- out algorithm improves the conventional greedy backward elimination algorithm by preserving more interactions among features in the selection process, so that the various feature selection objectives can be optimized in a unified way. Experiments on six real-world datasets with different feature evaluation metrics have shown that this algorithm outperforms popular feature selection algorithms in most situations.     

A New Framework for Focused Web Crawling

Focused crawlers are important tools to support applications such as specialized Web portals, online searching, and Web search engines. A topic driven crawler chooses the best URLs and relevant pages to pursue during Web crawling. It is difficult to deal with irrelevant pages. This paper presents a novel focused crawler framework. In our focused crawler, we propose a method to overcome some of the limitations of dealing with the irrelevant pages. We also introduce the implementation of our focused crawler and present some important metrics and an evaluation function for ranking pages relevance. The experimental result shows that our crawler can obtain more ＂important＂ pages and has a high precision and recall value.     

基于视觉特征度量的模型简化算法

人的视觉系统通常对模型的高曲率变化区域、尖角、边界轮廓等几何特征格外敏感。基于视觉特征度量的模型简化算法,在简化过程中通过调整网格顶点的简化误差来改变边折叠的次序,优先保留模型视觉敏感区域的网格;从而解决了模型网格的各部分简化力度趋于均衡的问题,最大限度地保留了原模型的视觉冲击。经实验,在同等简化力度下得到的简化结果能够突出原模型的视觉特征,具有明显优势。     

基于可用带宽的QoS多播路由算法

设计了一种基于时延、时延抖动和包丢失率3个QoS约束下的最大可用带宽多播树求解模型，将可用带宽作为主度量参数来构建多播树。能够针对特定的服务需求对各个QoS度量的重要性进行灵活调整。其算法具有多项式复杂度，并通过仿真证明了算法的有效性。     

Implementation Study of Dynamic Load Balancing Algorithm of Parallel Tree Computation on Clusters of Heterogeneous Workstation

Introduction Inthe1980sresearchersbelievedthatthebestwayto improvecomputerperformancewasbycreatingfasterand momefficientprocessors.Thisideawaschallengedby parallelprocessingwhichinessencemeanslinkingtogether twoormorecomputerstosolvejointlyacomputational problem.Inearly1990sthetrendwastomoveawayfrom expensiveandspecializedproprietarysupercomputers towardsnetworkofworkstations,producinganew computingplatformcalledCOW.[1]Theemergenceof COWhasbeenfosterednotonlybyrecentadvancesin computerhardw…     

Statistical analyses of metric data of hominoid teeth found in Yuanmou of China

Mesial-distal and buccal-lingual dimensions of 1 266 hominoid teeth found in Yuanmou of Yunnan Province during the period of 1986 and 1988 have been measured. The statistical analyses of the metric data show that the tooth sizes of Yuanmou hominoid can be divided into big and small two types, and most tooth dimensions display obvious bimodalities in both histograms and 2 dimensional plots. The coefficients of variance (CV) reveal that the CVs of Yuanmou hominoid tooth sizes are within or close to the CV ranges ofLufengpithecus and extant great apes. The comparisons of tooth sizes and their proportions indicate that Yuanmou hominoids have close affinities with Lefeng and Kaiyuan hominoids, and have obvious differences with Gorilla, Chimpanzee and Orangutan. The authors believe that the hominoid fossils found in Yuanmou in the past 10 years represent a single species with highly sexual dimorphism in morphology and this species may have a close evolutionary relationship with the hominoids found in Kaiyuan and Lufeng.     

基于组合质量评估参数的音频信息隐藏盲检测方法与仿真

描述了一种基于组合质量评估参数及支持向量机的音频隐藏信息盲检测方法.该方法对一系列音频质量评估参数进行组合,用多维特征选取的方法选择组合质量评估参数的种类和数量,生成支持向量机盲检测仿真模型,可对可疑的音频进行隐藏信息盲检测.该方法经计算机仿真,对DSSS和常用的变换域信息隐藏方法有较好的检测效果.     

度量空间的概率近似算法

通过改进FRT算法,得到随机最小序分割算法(random minimum order partition, RMOP)。在度量空间G中,对点列V进行随机排序(设序列为π),随机选取点u∈V后,获得下标Jr(u)=inf｛j∈N:d(πj,u)≤r,πj,u∈V｝,再以点πJr(u)为球心r为半径,对度量空间G进行递归分割,进而形成一棵分层良分割树(hierarchically well separated tree, HST);同时得到E(dT(u,v))≤O(logn)d(u,v)。在RMOP算法与FRT算法具有相同的π时,RMOP算法能保证点u落入特定分割子集B(πJr(u),r)的概率最大。     

软件工程视域下的软件复杂性研究

从软件工程的视角对软件复杂性进行了初步研究,讨论了软件复杂性的基本定义,分析了软件复杂性产生的原因及软件度量方法,最后提出了未来适应软件复杂性的几种技术解决方案.