基于Document Triage的TF-IDF算法的改进

针对TF-IDF算法在加权时没有考虑特征词本身在文档中重要度的问题,提出利用用户阅读时的阅读行为来改进TF-IDF。将Document Triage引入到TF-IDF中,利用IPM收集用户阅读中行为的相关信息,计算文档评分。由于用户的标注内容往往是文章的重要内容,或者反映了用户的兴趣。因此,赋予用户标注词项更大的权重,将文档评分和用户的标注信息等作为因子引入到TF-IDF中,设计出改进的加权算法DT-TF-IDF。实验结果表明,相对传统TF-IDF算法,DT-TF-IDF的查全率、查准率,以及查准率和查全率的调和均值都有了一定的提高。DT-TF-IDF算法比传统TF-IDF算法更加有效,提高了文本相似度计算的准确性。     

复杂机电产品全三维工艺设计系统研究

针对目前复杂机电产品中高精度、薄壁及异形复杂腔体类零件加工工艺复杂,设 计周期长及后续车间制造检验工人识图不直观等问题,提出并构建了基于MBD 的C/S、B/S 混 合架构全三维工艺设计系统。阐述了系统的体系结构和实施工作流程。详细研究了设计工艺 MBD 模型构建过程中单元信息标识、组合框格标识、三维标注、动态工艺模型构建以及全三维 工艺规程卡构建关键技术。最后,给出了开发与应用实例。研究结果表明,该系统能使设计制 造过程基于统一全三维模型源,有效缩短了传统3D→2D→3D 过程总研制周期,降低了研制成 本。     

图像语义提取方法研究

为解决从图像的低层视觉特征到高层语义特征的＂语义鸿沟＂问题,对当前的语义提取方法进行研究,简单介绍了图像语义层次模型,并根据语义信息的来源不同,归纳总结了图像语义中基于处理范围的方法,基于机器学习的方法,基于人机交互的方法和基于外部信息源的提取方法,这些工作为图像语义提取和图像语义检索等研究提供有益参考。     

Saccharomyces cerevisiae S288C genome annotation: a working hypothesis

The S. cerevisiae genome is the most well-characterized eukaryotic genome and one of the simplest in terms of identifying open reading frames (ORFs), yet its primary annotation has been updated continually in the decade since its initial release in 1996 (Goffeau et al., 1996). The Saccharomyces Genome Database (SGD; www.yeastgenome.org) (Hirschman et al., 2006), the community-designated repository for this reference genome, strives to ensure that the S. cerevisiae annotation is as accurate and useful as possible. At SGD, the S. cerevisiae genome sequence and annotation are treated as a working hypothesis, which must be repeatedly tested and refined. In this paper, in celebration of the tenth anniversary of the completion of the S. cerevisiae genome sequence, we discuss the ways in which the S. cerevisiae sequence and annotation have changed, consider the multiple sources of experimental and comparative data on which these changes are based, and describe our methods for evaluating, incorporating and documenting these new data.     

Annotation of unknown yeast ORFs by correlation analysis of microarray data and extensive literature searches

Changes in the expression of genes were used to elucidate the metabolic pathways and regulatory mechanisms that respond to environmental or genetic modifications. Results from previously published chemostat datasets were merged with novel data generated in the present study. ORFs displaying significant changes in expression that correlated with those of other ORFs were analysed using GO mapping tools and supplemented by literature information. The strategy developed was used to propose annotations for ORFs of unknown function. The following ORFs were assigned functions as a result of this study: YMR090w, YGL157w, YGR243w, YLR327c, YER121w, YFR017c, YGR067c, YKL187c, YGR236c (SPG1), YMR107w (SPG4), YMR206w, YER067w, YJL103c, YNL175C (NOP13) YJL200C, YDL070C (FMP16) and YGR173W.     

A novel method to quantify gene set functional association based on gene ontology

Numerous gene sets have been used as molecular signatures for exploring the genetic basis of complex disorders. These gene sets are distinct but related to each other in many cases; therefore, efforts have been made to compare gene sets for studies such as those evaluating the reproducibility of different experiments. Comparison in terms of biological function has been demonstrated to be helpful to biologists. We improved the measurement of semantic similarity to quantify the functional association between gene sets in the context of gene ontology and developed a web toolkit named Gene Set Functional Similarity (GSFS; http://bioinfo.hrbmu.edu.cn/GSFS). Validation based on protein complexes for which the functional associations are known demonstrated that the GSFS scores tend to be correlated with sequence similarity scores and that complexes with high GSFS scores tend to be involved in the same functional catalogue. Compared with the pairwise method and the annotation method, the GSFS shows better discrimination and more accurately reflects the known functional catalogues shared between complexes. Case studies comparing differentially expressed genes of prostate tumour samples from different microarray platforms and identifying coronary heart disease susceptibility pathways revealed that the method could contribute to future studies exploring the molecular basis of complex disorders.     

基于GB/T 24734 的三维尺寸快速标注技术

针对当前主流CAD 软件提供的三维标注功能局限的现状,结合制造企业 对复杂零件三维模型快速标注的需求,探讨了基于GB/T 24734 的三维尺寸快速标注技术; 设计并实现了三维尺寸快速标注的算法,详细阐述了其相关的技术。该算法涉及标注面自动 构造、尺寸元素计算、显示处理等一系列技术。其中,标注面构造主要涉及标注面分类、光 标点获取等操作。为了便于尺寸的显示与观察,采用了标注文字的正向显示处理技术。以 CATIA V5 系统为平台,实现了上述算法,开发了快速标注模块,通过实例测试验证了算法 的可行性。     

基于决策融合的图像自动标注方法

结合多媒体描述接口（MPEG-7）和MM（Mixture Model）混合模型,实现了基于决策融合的图像自动标注。在图像标注过程中,分别利用颜色描述子和纹理描述子为每个主题下的图像建立MM混合模型,实现低层视觉特征到高层语义空间的映射,利用局部决策融合方式融合在颜色和纹理MM混合模型下的标注结果,实现图像自动标注。通过在corel图像数据集上的实验,表明提出的局部决策融合方式能更充分利用图像的颜色和纹理信息,提高了图像标注性能。     

基于时序概率超图模型的视频多语义标注

在基于语义的视频检索系统中,为了弥补视频底层特征与高层用户需求之间的差异,提出了时序概率超图模型。它将时间序列因素融入到模型的构建中,在此基础上提出了一种基于时序概率超图模型的视频多语义标注框架（TPH-VMLAF）。该框架结合视频时间相关性,通过使用基于时序概率超图的镜头多标签半监督分类学习算法对视频镜头进行多语义标注。标注过程中同时解决了已标注视频数据不足和多语义标注的问题。实验结果表明,该框架提高了标注的精确度,表现出了良好的性能。     

基于熵约简和多核支持向量机的软件语义标注

提出一种基于条件信息熵维度约简和多核支持向量机的程序语义标注方法,相对于传统的本体语义标注,该方法有如下特点：采用机器学习的方式,实现了软件语义的自动标注;通过重采样平衡了正负样本;利用条件信息熵对面向对象程序的模块样本特征进行维度约简,降低了问题的计算复杂度和开销,并给出了代数约简的转化方法;核函数采用多个基核函数线性组合的方式,兼顾了分类的学习能力和泛化性能。标注实例表明,该方法能保证较高的标注准确率,具有较好的实用性和推广性。