基于多变体的控制软件异构冗余与动态重构技术研究

针对控制软件的防篡改问题,从工控安全角度出发,提出了一种利用多变体技术和虚拟化技术构建控制软件动态目标防御体系的新方法;通过多变体的异构冗余、动态重构和多模表决实现了软件层面的主动防御和安全态势感知,通过虚拟化技术实现了多变体执行环境的快速构建;着重介绍了技术路线、系统架构、动态重构策略、表决算法和同步机制;研究结果表明,该技术在提高控制系统可靠性的同时,使其具备了较强的主动安全防御能力。     

A model-driven approach to semi-structured database design

Recently XML has become a standard for data representation and the preferred method of encoding structured data for exchange over the Internet. Moreover it is frequently used as a logical format to store structured and semi-structured data in databases. We propose a model-driven and configurable approach for modeling hierarchical XML data using object role modeling (ORM) as a flat conceptual model. First a non-hierarchical conceptual schema of the problem domain is built using ORM and then different hierarchical views of the conceptual schema or parts of it are specified by the designer using transformation rules. A hierarchical modeling notation called H-ORM is proposed to show these hierarchical views and model more complex semi-structured data constructs and constraints. We also propose an algorithm to map hierarchical H-ORM views to XML schema language.     

本体学习研究综述

近年来,本体学习技术逐渐成为计算机科学领域的一个研究热点.根据数据源的结构化程度(结构化、半结构化、非结构化)以及本体学习对象的层次(概念、关系、公理),将本体学习问题划分为9类子问题.分别阐述了这9类问题的基本特征、常用的方法和最新的研究进展,并在此分析框架下进一步介绍和比较了现有的本体学习工具.最后,讨论了存在的问题,指出了未来的研究方向.     

RE-OEM：一种半结构化生物数据的信息抽取模型*

在分析半结构化生物数据特点的基础上,提出了一种新的半结构化数据抽取模型RE-OEM。它将OEM数据模型和正则表达式有机地结合起来,不但能够灵活方便地表示各种数据结构,而且能够非常方便地进行模式匹配和数据的定位,为半结构化生物数据的抽取打下坚实基础。     

半结构化脆弱性数据处理技术研究

文章以“脆弱性数据集成管理环境”项目为背景,依托脆弱性数据处理子系统的研制,研究半结构化脆弱性数据处理技术,以面向对象程序设计方法设计脆弱性数据处理算法,实现半结构化脆弱性数据到结构化脆弱性数据的转化。最后,简要介绍算法实现技术要点。     

针对混合污染的结构化鲁棒低秩恢复算法在人脸识别中的应用

传统的低秩恢复算法在识别有混合污染的人脸图像时,通常只对污染部分进行一种类型的约束,并不能很好地恢复出干净的样本。针对这种情况,提出结构化鲁棒低秩恢复算法（structured and robust low-rank recovery for mixed contamination,SRLRR）。SRLRR算法利用对二维误差图像的低秩约束移除样本中的连续污染部分,同时利用稀疏约束分离样本中服从拉普拉斯分布的噪声。另外,为了学习到更具有鉴别性的低秩表示,该算法对表示系数进行了块对角结构化约束。在三个常用数据库上的实验证明了SRLRR算法的有效性和鲁棒性。     

Odor classification using similarity-based representation

In this paper a new approach to odor classification is presented, founded on the similarity-based representation paradigm. The proposed approach builds a new representation space, called similarity space, in which each object is not represented by features, but by its similarities with respect to other objects in the data set. The classification step is performed using support vector machines, a technique introduced in the statistical learning theory context. One of the major drawbacks of the similarity-based representation paradigm is the dimensionality of the similarity space: a method for addressing this problem has been introduced in this paper, based on a notion of the unsupervised classification (clustering) theory, namely the medoid concept. The approach outperforms standard features-based representations on tests regarding data gathered from a chemical sensors array electronic nose.     

基于隐马尔可夫模型的招聘网络信息抽取

网络信息抽取是从半结构化的Web海量数据中,按用户要求抽取且形成相关的有效的结构数据处理过程。论文以隐马尔科夫模型（HMM）进行数据抽取中的若干关键问题进行研究,提出了基于数据挖掘聚类的模型合并方法生成隐马尔可夫模型,即可根据数据自动生成HMM,同时对一般的隐马尔可夫模型进行了扩展,为每个抽取域生成一个隐马尔可夫模型,用于获取更多的有用信息。     

基于抽象语法树的智能化漏洞检测系统

源代码漏洞的自动检测是一个重要的研究课题。目前现有的解决方案大多是基于线性模型,依赖于源代码的文本信息而忽略了语法结构信息,从而造成了源代码语法和语义信息的丢失,同时也遗漏了许多漏洞特征。提出了一种基于结构表征的智能化漏洞检测系统Astor,致力于使用源代码的结构信息进行智能化漏洞检测,所考虑的结构信息是抽象语法树（Abstract Syntax Tree,AST）。首先,构建了一个从源代码转化而来且包含源码语法结构信息的数据集,提出使用深度优先遍历的机制获取AST的语法表征。最后,使用神经网络模型学习AST的语法表征。为了评估Astor的性能,对多个基于结构化数据和基于线性数据的漏洞检测系统进行比较,实验结果表明Astor能有效提升漏洞检测能力,降低漏报率和误报率。此外,还进一步总结出结构化模型更适用于长度大,信息量丰富的数据。     

面向多变体系统的执行体多样性度量方法

近年来,以内生安全为主要技术机制的多变体系统在防御零日漏洞攻击中表现出了巨大的潜力.但是现有研究很少涉及多样性和安全性之间的量化评估.对此,提出面向多变体系统的执行体多样性度量方法,该方法通过执行体属性和属性类型构建执行体属性矩阵,结合属性多样性和局部多样性综合评估执行体集的空间多样性,并针对矩阵参数及其多样性权重进行分析以达到系统最大多样化.构建了一个典型的多变体系统及零日攻击模型来评估该指标的有效性,评估结果表明,该多样性度量方法能有效衡量多变体系统中执行体间的异构性,并根据执行体异构性和系统攻击成功率的关系,间接评估出多变体系统的整体安全性.根据结论,该方法为构建更加多样化和安全的系统方面提供了一些指导.     

结构图正则低秩子空间聚类

针对结构稀疏子空间聚类中不能很好地保证相似度矩阵连接性的问题,给出了一个新的统一优化模型。首先,引入了表示系数矩阵的子空间结构范数,增加了低秩表示来揭示高维数据的全局结构。其次,为了使相似度矩阵具有类内统一,类间稀疏的作用,还定义了分组效应来捕获数据的内部几何结构,提出了结构图正则低秩子空间聚类模型。最后使用自适应惩罚的线性化交替法（LADMAP）来得到最优解。实验结果表明,该模型不但可以捕获数据的全局结构,而且还可以捕获数据的内在几何结构,迫使相关数据紧密结合,不相关数据松散分离,从而使得相似度矩阵与分割矩阵变得更加一致。     

Theory and applications of granular labelled partitions in multi-scale decision tables

Granular computing and acquisition of if-then rules are two basic issues in knowledge representation and data mining. A formal approach to granular computing with multi-scale data measured at different levels of granulations is proposed in this paper. The concept of labelled blocks determined by a surjective function is first introduced. Lower and upper label-block approximations of sets are then defined. Multi-scale granular labelled partitions and multi-scale decision granular labelled partitions as well as their derived rough set approximations are further formulated to analyze hierarchically structured data. Finally, the concept of multi-scale information tables in the context of rough set is proposed and the unravelling of decision rules at different scales in multi-scale decision tables is discussed.     

源于信息挖掘的新型智能化决策支持系统

阐述了以结构化数据和复杂类型数据挖掘为主要内容的信息挖掘技术。采用7库(模型库、综合知识库、数据库、方法库、文本库、日志库、多媒体库)与双网(Internet、Intranet)相结合的体系结构,以信息挖掘技术为核心,提出源于信息挖掘的新型智能化决策支持系统(IDSSIM)。旨在解决决策支持系统对半结构化数据、非结构化数据的挖掘处理能力,使之适应目前信息源的多样型和动态变化性的特点,提供更加丰富的决策信息。     

Object-oriented knowledge frameworks

This paper introduces a strategy for the construction of object-oriented knowledge frameworks. Global control programs, which are traditionally used for manipulating structured representations, have been replaced by domain-specific resources. This new approach offers increased efficiency and simplified development of knowledge-based expert systems for problem domains that deal with a variety of complex structured information.A theoretical foundation is laid for the representation of knowledge, starting with the adoption of a simple schema for structuring stereotypical information. Data and method abstraction is achieved by installing knowledge frames into part of an object-oriented class system that supports procedural attachment and object communication. This allows frame specialization using domain-specific resources and subsequent construction of modular systems with these specialist frames. Editors are introduced for the alteration of data primitives used in declarative representation. Algorithms, which operate on these data primitives, are given for frame instantiation, data access, and user-directed inference.Examples from structural engineering are used throughout the paper to illustrate the practical application of object-oriented knowledge frameworks.     

一种结构化数据和半结构化数据的统一集成模型

结构化和半结构化数据的统一集成和访问是目前Web数据访问中急需解决的问题。文章提出了一种半结构化数据表示模型———层次数据图(HDG),给出了结构化数据向HDG的转换方法,并就不同结构HDG的统一集成问题进行了探究。     

Can structured representation enhance students' thinking skills for better understanding of E-learning content?

This paper proposes an e-learning model to assess the effects of online structured representation of content on learners' understanding. We designed a structured representation based on the theory of distributed cognition that provides seven segments for reading research articles. The study hypothesized that motivation, attention, and interactivity are essential factors that affect students' thinking skills for understanding e-learning content. To investigate and confirm the effect of these factors on the students' thinking skills, we designed a survey and analyzed the responses of 210 university students concerning the proposed structured representation. The results revealed that motivation, attention, and interactivity did contribute to the students' thinking skills. They also demonstrated that the structured representation helped students achieve an adequate level of thinking skills as they read research articles, which had a positive effect on their understanding. This finding demonstrates that structured representation has significant potential as a learning tool and that structure-based e-learning can influence students' metacognitive activities and facilitate their understanding.     

A Type-Safe Embedding of XDuce into ML

We consider the problem of integrating XDuce into ML. This is difficult because of incompatible type and value representations. Our solution is a type-driven translation scheme from XDuce to ML based on a structured representation of XDuce values. XDuce type inference guides the insertion of appropriate coercion functions to translate regular expression pattern matching and uses of semantic subtyping. We can extend our translation scheme to include ML function calls and patterns into XDuce. Thus, we can embed XDuce into ML. Our results allow to enrich the ML language with support for dealing with semi-structured data.     

复杂结构归纳学习研究

复杂结构归纳学习的需求近年来快速增长。复杂结构归纳学习方法按照知识表示方式不同分为基于逻辑的方法与基于数学图的方法。阐述了复杂结构归纳学习研究的历史沿革,介绍、分析和对比了不同知识表示方式下的学习方法,给出了复杂结构归纳学习将来发展面临的挑战和需重点解决的问题。     

基于特征提取的网络热点事件挖掘算法

为有效从网络中挖掘出民众关注的热点事件和话题,提高数据分类能力、热点追踪和检测正确率,在分析目前采用非结构化传统挖掘算法所存在问题的基础上,提出一种基于结构化分割的挖掘算法。首先通过分析热点事件挖掘处理流程,设计一种对热点事件数据挖掘的半结构化特征提取算法,对半结构化数据进行特征分割,生成大量请求,进而得到热点事件数据的分配因子,从而提高挖掘性能。仿真结果表明,该算法运行效率较高,精度较好,具有较高的稳健性。