WordNet中的综合概念语义相似度计算方法

作为语义异构问题的基础,概念间语义相似度计算已成为研究热点,对此,提出一种基于WordNet的综合概念语义相似度计算方法. 该方法不仅集成了传统的基于语义距离的算法和基于信息内容的算法,而且引入了深度、密度因子和语义重合度来进行综合分析,并针对综合算法中权值难以确定的问题,引入主成分分析改进权值分配方法. 实验结果表明,改进后的方法计算的相似度与人工判断的相似度相关性较高,有效改善了概念语义相似度计算的准确性.     

6PE在IPv4向IPv6网络过渡中的应用研究

分析了6PE技术的工作原理、特点、IPv6网络和IPv4网络间隧道的建立过程、IPv6数据分组通过IPv4网络隧道的封装解封过程,通过MP-BGP实现了IPv6路由和IPv6MPLS标签跨IPv4网络的发布,通过6PE技术设计出了校园网IPv4向IPv6网络过渡的方案,并给出了设备的关键配置步骤,利用现有的IPv4/MPLS网络,通过升级少量网络设备,实现了IPv4向IPv6网络的平滑过渡。     

alt.metadata.health: Ontological Context for Data Use and Integration

Increasingly powerful computers and increased emphasis on evidence based decision making are creating a demand for merging and integrating data from different sources into a single data set. The demand for data is outstripping our ability to ensure data integrity, and sometimes analysis is performed on data that are not appropriate for the purposes they are used for. Here we describe problems that arise when data from different sources are merged, and we suggest that one way to add context to data so that users can make informed decisions about their ontological context is through ontology-based metadata. Examples of the problem are taken from health data with emphasis on difficulties in standardizing Emergency Room wait times. We describe eight fields that can be used to capture contextual metadata. These fields are captured using ethnographic methods from users and database stewards who frequently understand precisely how context and institutional usage have shaped interpretation of semantic fields. We argue that attaching a portable archive of ontological context to travel with data—based on information from users and developers—is a means of ensuring that data are integrated and compared in multiple contexts with greater integrity and more robust results.

基于语义距离的K-最近邻分类方法

最近邻分类方法中对距离机制的研究大都集中在根据何种计算方法将不同属性取值的差异集中起来,而未考虑到同一属性间取值的语义差异所带来的影响;而且传统算法的分类准确率对于不同抽象层次描述的数据集带来的数据不完整性相当敏感.针对这两个问题,提出一种基于语义距离的最近邻分类方法SDkNN(semantic distance based k-nearest neighbor).该方法分析了同一属性内取值的语义差异,说明了如何基于领域本体计算语义距离,并将其应用到kNN算法中.经过在UCI数据集以及实际应用数据集中验证,SDkNN的整体性能要优于传统方法,在数据不完整的情况下效果更为明显,实践证明,SDkNN有较好的应用价值.     

A Framework for the Generation of Adaptive Courses Based on Semantic Metadata

This approach proposes the creation and management of adaptive learning systems by combining component technology, semantic metadata, and adaptation rules. A component model allows interaction among components that share consistent assumptions about what each provides and each requires of the other. It allows indexing, using, reusing, and coupling of components in different contexts powering adaptation. Our claim is that semantic metadata are required to allow a real reusing and assembling of educational component. Finally, a rule language is used to define strategies to rewrite user query and user model. The former allows searching components developing concepts not appearing in the user query but related with user goals, whereas the last allow inferring user knowledge that is not explicit in user model.John Freddy Duitama received his M.Sc. degree in system engineering from the University of Antioquia -Colombia (South America). He is currently a doctoral candidate in the GET – Institut National des Télécommunications, Evry France. This work is sponsored by the University of Antioquia, where he is assistant professor.His research interest includes semantic web and web-based learning systems, educational metadata and learning objects.Bruno Defude received his Ph.D. in Computer Science from the University of Grenoble (I.N.P.G) in 1986. He is currently Professor in the Department of Computer Science at the GET - Institut National des Télécommunications, Evry France where he leads the SIMBAD project (Semantic Interoperability for MoBile and ADaptive applications).His major field of research interest is databases and semantic web, specifically personalized data access, adaptive systems, metadata, interoperability and semantic Peer-to-peer systems with elearning as a privileged application area.He is a member of ACM SIGMOD.Amel Bouzeghoub received a degree of Ph.D. in Computer Sciences at Pierre et Marie Curie University, France.In 2000, she joined the Computer Sciences Department of GET-INT (Institut National des Telecommunications) at Evry (France) as an associate professor.Her research interests include topics related to Web-based Learning Systems, Semantic Metadata for learning resources, Adaptive Learning Systems and Intelligent Tutoring Systems.Claire Lecocq received an Engineer Degree and a Ph.D. in Computer Sciences respectively in 1994 and 1999. In 1997, she joined the Computer Sciences Department at GET-INT (Institut National des Télécommunications) of Evry, France, as an associate professor. Her first research interests included spatial databases and visual query languages. She is now working on adaptive learning systems, particularly on semantic metadata and user models.     

基于HSIC0的类间非线性相关系数度量

常见的相关系数反映变量之间的线性或非线性程度。基于希尔伯特-斯密特独立准则（Hilbert-Schmidt Independence Criterion,HSIC）的有偏估计（HSIC0）,提出了根据类标签划分出的类与类之间的非线性相关关系的度量方法。通过六组真实的、不同类型的数据集,分别选取了线性核、多项式核、RBF核和Sigmoid核函数进行实验。结果表明,该方法具有较好的可行性。     

空洞卷积的多尺度语义分割网络

计算机硬件的发展极大程度地促进了计算机视觉的发展,卷积神经网络在语义分割中取得了令人瞩目的成就,但多卷积层叠加难免造成图像中目标边界信息的丢失。为了尽可能保留边界信息,提高图像分割精度,提出一种多尺度空洞卷积神经网络模型。该模型利用多尺度池化适应图像中不同尺度目标,并利用空洞卷积学习目标特征,在更加准确识别目标的同时,提高目标边界的识别精度,在ISPRS Vaihingen数据集上的实验结果表明,提出的多尺度空洞卷积神经网络对于目标边界的拟合结果较为理想。     

基于编码器-解码器的半监督图像语义分割

基于深度卷积神经网络的图像语义分割方法需要大量像素级标注的训练数据,但标注的过程费时又费力.本文基于生成对抗网络提出一种编码-解码结构的半监督图像语义分割方法,其中编码器-解码器模块作为生成器,整个网络通过耦合标准多分类交叉熵损失和对抗损失进行训练.为充分利用浅层网络包含的丰富的语义信息,本文将编码器中不同尺度的特征输入到分类器,并将得到的不同粒度的分类结果融合,进而优化目标边界.此外,鉴别器通过发现无标签数据分割结果中的可信区域,以此提供额外的监督信号,来实现半监督学习.在PASCAL VOC 2012和Cityscapes上的实验表明,本文提出的方法优于现有的半监督图像语义分割方法.