一种新型的克隆选择算法*

针对克隆选择算法自适应能力较弱的缺陷,给出了一种基于危险理论的自适应克隆选择算法。设计了危险信号操作算子,该算子将种群浓度的变动作为环境因素,以抗体—抗原亲和力为依据计算各个抗体在该环境因素下的危险信号,最终通过危险信号自适应地引导免疫克隆、变异和选择等后续免疫应答。实验结果表明本文算法具有较好的自适应能力和多值搜索能力。     

结合危险理论的故障检测免疫模型

为了实现快速准确的网络故障检测与诊断,将危险理论与动态克隆选择算法相结合,提出了用于网络故障检测的危险理论免疫模型;并针对网络故障特点,对危险理论与动态克隆选择算法进行了改进;首先采用危险理论模型对抗原进行危险信号浓度识别,并利用成熟检测器检测已知故障类型,其次用改进的动态克隆选择算法对未知故障进行有效的学习;通过对多种网络故障类型检测的仿真实验,证明了新模型不仅具有更好的检测效果和动态适应性,而且能够提高检测效率与准确率。     

人工免疫系统中危险信号的云方法定义

对“危险”的定义是将危险理论用于人工免疫系统所需要解决的核心问题。云模型是一种定性与定量之间相互转换的有效工具。论文借鉴云模型的概念对计算机系统中系统变量的变化进行判定,从而给出危险信号的定义;综合多种危险信号,进而给出“危险”的定义。最后,提出了利用“危险”和nonself的识别共同激发免疫响应的协同识别模型框架。     

受危险理论启发的网络安全评估方法

危险理论在人工免疫系统（AIS）领域是一个相，对较新的研究方向。该理论提出了不同于传统自我一非我模型的新观点。它解释了传统人类免疫系统（HIS）理论中存在的问题，促进了人工免疫系统的发展。介绍了危险理论涉及的内容及其应用，然后构建了一个用于安全评估的多Agent融合模型，并将危险理论应用于安全评估中。     

计算机免疫危险理论中危险信号的提取方法研究

危险理论是人工免疫系统的一个重要研究分支,它从危险的角度出发对免疫系统的工作原理进行了新的阐述,目前已广泛应用于入侵检测、机器学习和数据挖掘等领域。建立危险理论模型的首要问题是如何自适应地提取危险信号。从变化导致危险这一思想出发,建立了一套基于变化特征的危险信号自适应提取模型;针对不同类型系统资源的特点,设计了基于值变化和特征变化的两种危险信号提取方法。同时,通过实验验证了该模型在不依赖先验知识的情况下,能够自适应地提取危险信号。     

利用人工免疫系统防范网络入侵与攻击

人工免疫系统是一个相对年轻的研究领域,在不同领域得到了广泛应用。本文以人工免疫算法为线索,介绍人工免疫系统在信息安全中研究现状和应用。首先介绍基于传统算法的免疫安全系统,包括反病毒系统、多Agent入侵检测和网络入侵检测。然后总结否定算法及其特点和基于否定算法的网络免疫系统。随后对危险理论基本原理及其在信息安全领域的应用进行系统综述。最后分析了人工免疫系统方法存在的问题,并指出进一步研究方向。     

基于危险理论的多代理异常入侵检测研究

为了提高分布式网络中异常入侵检测的效率,在对危险理论和人工免疫技术的研究基础之上,提出了一种基于危险理论的多代理异常人侵检测模型,对模型架构和工作原理进行了详细的描述.模型分为三层,在识别"非我"之前,先对主机和网络资源实时监控并进行数据采集,利用云模型对危险进行判定,由危险信号激活免疫识别.该模型能根据定义的危险级别有效地识别出"有害的非我",保障系统的可用性,在一定程度上改善伪肯定和伪否定现象,提高检测系统性能.     

人工免疫危险理论中的平衡机制研究及应用

危险理论作为人工免疫学的新兴研究方向,其主要思想是通过危险信号的发现和融合来检测异常,危险信号的自适应感知是人工免疫危险理论需要解决的首要问题；从生物免疫系统保障机体生理平衡这一机理出发,将免疫系统中的平衡思想引入危险理论中,通过寻找导致信息系统失衡的变化因素,来实现危险行为的自适应发现；从机体免疫平衡理论出发,借鉴数学中的微分方法对信息系统各种行为发生时资源的占用特征进行形式化描述；从信息系统资源指标占用特征入手,实现对信息系统中各种平衡的描述,通过对失衡状态的判定来进行危险的发现,并对其实现方法和步骤做出了解释；最后以僵尸程序(SpyBot)为实验对象验证了所提出的利用免疫平衡理论检测危险方法的有效性。     

多维云模型定义的危险信号产生机制

危险信号的产生机制是危险理论的核心问题。云模型是描述不确定性概念的工具。本文借鉴多维云模型的思想来判定计算机系统参数的变化,产生危险信号并构造多概念云,用以划分危险等级。最后,我们综合危险信号与现有AIS识别机制构造了协同免疫识别模型。     

基于危险理论的入侵检测系统的研究

入侵检测系统的首要功能就是能够区分正常行为和异常行为(活动)的不同.传统的基于自体-非自体思想的人工免疫系统存在许多弊端和错误,危险理论指出机体实际上更多关注有威胁的入侵,基于这种最新免疫理论,本文提出了一种入侵检测系统的模型.     

Deterministic and Stochastic Fixed-Time Stability of Discrete-time Autonomous Systems

This paper studies deterministic and stochastic fixed-time stability of autonomous nonlinear discrete-time (DT) systems. Lyapunov conditions are first presented under which the fixed-time stability of deterministic DT systems is certified. Extensions to systems under deterministic perturbations as well as stochastic noise are then considered. For the former, sensitivity to perturbations for fixed-time stable DT systems is analyzed, and it is shown that fixed-time attractiveness results from the presented Lyapunov conditions. For the latter, sufficient Lyapunov conditions for fixed-time stability in probability of nonlinear stochastic DT systems are presented. The fixed upper bound of the settling-time function is derived for both fixed-time stable and fixed-time attractive systems, and a stochastic settling-time function fixed upper bound is derived for stochastic DT systems. Illustrative examples are given along with simulation results to verify the introduced results.      

Discriminative training of HMMs for automatic speech recognition: A survey

Recently, discriminative training (DT) methods have achieved tremendous progress in automatic speech recognition (ASR). In this survey article, all mainstream DT methods in speech recognition are reviewed from both theoretical and practical perspectives. From the theoretical aspect, many effective discriminative learning criteria in ASR are first introduced and then a unifying view is presented to elucidate the relationship among these popular DT criteria originally proposed from different viewpoints. Next, some key optimization methods used to optimize these criteria are summarized and their convergence properties are discussed. Moreover, as some recent advances, a novel discriminative learning framework is introduced as a general scheme to formulate discriminative training of HMMs for ASR, from which a variety of new DT methods can be developed. In addition, some important implementation issues regarding how to conduct DT for large vocabulary ASR are also discussed from a more practical aspect, such as efficient implementation of discriminative training on word graphs and effective optimization of complex DT objective functions in high-dimensionality space, and so on. Finally, this paper is summarized and concluded with some possible future research directions for this area. As a technical survey, all DT techniques and ideas are reviewed and discussed in this paper from high level without involving too much technical detail and experimental result.     

Evaluating Six Candidate Solutions for the Small-Disjunct Problem and Choosing the Best Solution via Meta-Learning

A set of classification rules can be considered as a disjunction of rules, where each rule is a disjunct. A small disjunct is a rule covering a small number of examples. Small disjuncts are a serious problem for effective classification, because the small number of examples satisfying these rules makes their prediction unreliable and error-prone. This paper offers two main contributions to the research on small disjuncts. First, it investigates six candidate solutions (algorithms) for the problem of small disjuncts. Second, it reports the results of a meta-learning experiment, which produced meta-rules predicting which algorithm will tend to perform best for a given data set. The algorithms investigated in this paper belong to different machine learning paradigms and their hybrid combinations, as follows: two versions of a decision-tree (DT) induction algorithm; two versions of a hybrid DT/genetic algorithm (GA) method; one GA; one hybrid DT/instance-based learning (IBL) algorithm. Experiments with 22 data sets evaluated both the predictive accuracy and the simplicity of the discovered rule sets, with the following conclusions. If one wants to maximize predictive accuracy only, then the hybrid DT/IBL seems to be the best choice. On the other hand, if one wants to maximize both predictive accuracy and rule set simplicity -- which is important in the context of data mining -- then a hybrid DT/GA seems to be the best choice.     

基于双字耦合度的中文分词交叉歧义处理方法

本文提出了一种利用双字耦合度和t-测试差解决中文分词中交叉歧义的方法: 首先利用词典找出所有的交叉歧义,然后用双字耦合度和t-测试差的线性叠加值来判断各歧义位置是否该切分。实验结果表明,双字耦合度和t-测试差的结合要优于互信息和t-测试差的结合,因此,用双字耦合度和t-测试差的线性叠加值来消除交叉歧义是一种简单有效的方法。     

Unraveling the capabilities that enable digital transformation: A data-driven methodology and the case of artificial intelligence

Digital transformation (DT) is prevalent in businesses today. However, current studies to guide DT are mostly qualitative, resulting in a strong call for quantitative evidence of exactly what DT is and the capabilities needed to enable it successfully. With the aim of filling the gaps, this paper presents a novel bibliometric framework that unearths clues from scientific articles and patents. The framework incorporates the scientific evolutionary pathways and hierarchical topic tree to quantitatively identify the DT research topics’ evolutionary patterns and hierarchies at play in DT research. Our results include a comprehensive definition of DT from the perspective of bibliometrics and a systematic categorization of the capabilities required to enable DT, distilled from over 10,179 academic papers on DT. To further yield practical insights on technological capabilities, the paper also includes a case study of 9,454 patents focusing on one of the emerging technologies - artificial intelligence (AI). We summarized the outcomes with a four-level AI capabilities model. The paper ends with a discussion on its contributions: presenting a quantitative account of the DT research, introducing a process-based understanding of DT, offering a list of major capabilities enabling DT, and drawing the attention of managers to be aware of capabilities needed when undertaking their DT journey.     

基于多相关HMT模型的DT CWT域数字水印算法

本文以双树复数小波变换(Dual-tree complex wavelet transform, DT CWT)及隐马尔科夫树(Hidden Markov tree, HMT)理论为基础, 提出了一种基于Weibull向量HMT模型的DT CWT域数字音频盲水印算法. 原始数字音频首先进行DT CWT, 然后利用局部信息熵刻画音频内容特征并据此确定出重要DT CWT系数段, 进而将水印信息乘性嵌入到重要DT CWT高频系数幅值内. 水印检测时, 首先根据DT CWT系数幅值的边缘分布及系数间的多种相关性(包括子带内、尺度间、分解树间等相关性), 构造出Weibull混合向量HMT统计模型, 并估计出其统计模型参数; 然后, 利用局部最大势能(Locally most powerful, LMP)检验理论构造出局部最优检测器(Locally optimum decoder, LOD)以盲提取水印信息. 仿真实验结果表明, 本文算法可以较好地获得不可感知性、鲁棒性、水印容量之间的良好平衡, 其总体性能优于现有同类音频水印算法.     

Output feedback passification of saturated switched systems

This paper addresses the passivity and feedback passification of the saturated switched systems. A switching law and output feedback controllers are designed such that the corresponding closed-loop systems are with the passivity and disturbance tolerance capacity. The switching law satisfies a maximal dwell time (DT) condition, which avoids too high switching frequency. More importantly, under the switching law, the storage function is allowed to be increased during the DT and then decreased due to the drop of itself at the mixed time/state-dependent switching instants. This releases the performance requirement of existing results where the storage function must be non-increasing all the time. Finally, the existence of the upper bound of DT and output feedback controllers is guaranteed by solving some linear matrix inequalities. Two examples are given to show the effectiveness of the proposed method.     

A hybrid particle swarm optimization based fuzzy expert system for the diagnosis of coronary artery disease

This paper presents a particle swarm optimization (PSO)-based fuzzy expert system for the diagnosis of coronary artery disease (CAD). The designed system is based on the Cleveland and Hungarian Heart Disease datasets. Since the datasets consist of many input attributes, decision tree (DT) was used to unravel the attributes that contribute towards the diagnosis. The output of the DT was converted into crisp if–then rules and then transformed into fuzzy rule base. PSO was employed to tune the fuzzy membership functions (MFs). Having applied the optimized MFs, the generated fuzzy expert system has yielded 93.27% classification accuracy. The major advantage of this approach is the ability to interpret the decisions made from the created fuzzy expert system, when compared with other approaches.     

Framing Design Thinking: The Concept in Idea and Enactment

The concept of design thinking (DT) has emerged in management debates as promising innovation inspired by the way designers work. Despite the growing interest in DT, it is a difficult concept to study due to the lack of coherence between what DT ‘is’ in academic and practical terms. While there are numerous normative and often process‐focused depictions of DT, they seem limited in their ability to account for what occurs in practice. Given the discussion of DT as a concept, and emerging discussion of its enactment, a framing is needed that acknowledges both aspects. This paper proposes a framing of DT that makes it researchable in both theory and practice, and discusses commonalities and discrepancies in how the concept is usually portrayed in the literature. The paper builds on an empirical interview study in six large organizations, which led to the development of a framework structure and the identification of five themes characterizing DT: User focus, Problem framing, Visualization, Experimentation and Diversity. Each theme is associated with specific principles/mindsets, practices and techniques. The main contribution of this paper is to propose a framework that includes DT both as an idea and as the enactment of the idea, inspired by the works of Latour.     

基于机器学习的小目标检测与追踪的算法研究*

本文提出了基于机器学习的小目标检测与追踪算法DT。算法首先使用多结构闭运算重构对图像进行预处理,然后利用Harris角点检测与改进的多cell、多block的HOG (Histogram of Oriented Gradient)算法结合SVM(Support Vector Machine)对视频帧中的小目标进行检测,最后采用基于改进的孪生网络的追踪算法对检测到的目标进行追踪。实验证明,该方法不仅适用于天空背景,在相对均匀的地面背景下也有一定的追踪能力。而且该算法对于小目标的尺度变化、消失重现等问题具有很好的鲁棒性。