特殊网络通信行为的数据挖掘与分析

为了挖掘可疑通信的行为模式,定位发生了可疑通信行为的上网账户,本文首先分析了可疑通信行为特点。然后针对已有关联规则挖掘算法不能同时满足多层次数据挖掘和加权关联规则挖掘的问题,分析对比两种典型的基本关联规则算法,以FP-tree为基础,提出了ML-WFP多层次加权关联规则挖掘算法。针对算法中数据项权重的确定问题,由用户设置数据项间的重要性比较关系,借鉴模糊一致矩阵的概念,利用模糊层次分析法计算数据项的权重。最后将该算法应用于可疑通信行为的挖掘。实验测试结果表明可疑通信行为挖掘方案合理有效。     

基于新型距离测度的概率犹豫模糊多属性群决策方法

研究属性权重已知、专家权重未知条件下的概率犹豫模糊多属性群决策问题.首先,针对传统概率犹豫模糊距离测度的不足,提出改进的新型距离测度,并对其有效性和合理性进行数学证明;其次,在属性权重向量已知的前提下,通过加权算术平均的方式实现单个专家视角下的概率犹豫模糊信息初次集结,并基于分差最大化准则构建专家权重向量求解模型,采用...     

基于直觉模糊集和证据理论的群决策方法

针对属性值和权重均为直觉模糊数的多属性决策问题,提出一种基于直觉模糊集和证据理论的群决策方法.首先,对专家给出的每个方案的属性值和属性权重进行证据合成,在此基础上合成每个方案的所有属性值;然后,基于直觉模糊集相似度确定专家的相对权重,修正方案证据,并合成所有专家证据,得到方案的信任区间,根据信任区间的大小对方案进行排序;最后,通过数值案例验证了所提出方法的有效性和合理性.     

基于层次灰色关联分析的舱室内环境HRA评价

舱室是操作者操纵和执行任务的工作空间,其内环境直接影响到操作者的工作状态和工作效率。为了在安全性要求较高的舱室设计中进行HRA（Ｈuman Reliability Analysis）分析,以人机工程学和认知心理学为基础,分析了影响人机交互效率的主要因素和认知失误原因,建立了人机交互综合认知模型,在此基础上改进了CPC（Common Performance Condition）评价因子,并采用层次分析法确定其权重。运用灰色关联分析改进CREAM（Cognitive Reliability and Error Analysis Method）方法计算出认知失误概率,实现了舱室内环境人因可靠性的定量评价。最后设计并编制了评价系统,使得评价决策过程数字化,并以石油钻机司钻控制室设计方案评价为例作为验证。     

属性权重未知picture模糊多属性决策方法及其应用

针对属性权重未知的picture模糊多属性决策问题,提出一种基于picture模糊熵和picture模糊加权对称交叉熵的多属性决策方法.首先,基于余弦函数提出一类新的picture模糊熵,并验证该熵值满足picture模糊熵的公理化定义;其次,针对标准化处理后的picture模糊决策矩阵,以picture模糊熵确定各属性权重,同时确定正、负理想方案;再次,分别计算各方案与正、负理想方案的picture模糊加权对称交叉熵,考虑决策者的主观评价倾向以模糊折中值得到各备选方案的排序结果;最后,将所提多属性决策方法应用于河南自贸试验区郑州片区创新型项目遴选,并通过对比分析验证该决策方法的有效性与合理性.     

基于可信度的基本不确定区间犹豫模糊广义TODIM应急群决策方法

针对应急决策环境所存在的信息不完备、认知不足等问题,区间犹豫模糊集能充分表达决策者在信息评价时的犹豫性和模糊性,但随着研究的深入,发现其存在无法保证信息质量的缺陷.为此,提出更符合实际决策需求、信息表达更加灵活的基本不确定区间犹豫模糊集,其为包含区间犹豫模糊集和确定度的二维信息集.在此基础上,定义基本不确定区间犹豫模糊加权平均算子、犹豫度及可信度,提出基于可信度的专家权重调整方法和属性权重确定方法,充分考虑了决策专家提供评价信息的可靠程度.最后,将广义TODIM方法拓展到基本不确定区间犹豫模糊环境,通过应急决策案例验证所提方法的可行性,并利用灵敏度分析和对比分析验证该方法的稳定性和有效性.     

基于前景理论及云模型风险型多准则决策方法

针对具有语言评价信息、准则权系数部分已知的多准则决策问题,提出一种基于前景理论及云模型的决策方法。首先,通过给出一种改进的云模型生成方法将语言评价值转化为云模型;然后,通过定义云模型距离和可能度给出云前景价值,并以其他备选方案为动态参考点,构建云前景决策矩阵;最后,在依据离差最大化得出最优权系数的基础上,通过各方案综合前景值对其进行排序。算例验证了所提出方法的合理性和可靠性。     

A hybrid evaluation method for human error probability by using extended DEMATEL with Z-numbers: A case of cargo loading operation

Human error probability (HEP) evaluation and prediction is one of the most significant tasks to enhance human reliability in marine industry. Among various kinds of HEP evaluation techniques, the Human Error Assessment and Reduction Technique (HEART) technique is regarded as an effective and empirical tool that has been widely adopted in various fields. However, current HEART techniques are insufficient to address HEP evaluation problem in which the self-assurance of expert's judgment and inter-dependencies between Error-producing conditions (EPCs) are considered. Therefore, the purpose of this paper is to develop a hybrid HEART framework (H-HEART-F) to address this problem by integrating Z-numbers and the decision-making trial and evaluation laboratory (DEMATEL) method. First, the Z-numbers are introduced to model the uncertainty and self-assurance of evaluation information from various experts. Then, the Z-number power weighted average (Z-PWA) operator is proposed to aggregate the individual evaluation information into a group direct influenced matrix. Next, an extended DEMATEL method based on possibility degree measure is constructed to determine the proportion of effect of each EPC by considering the self-assurance of expert's judgment and inter-dependencies between EPCs. Finally, the HEP estimation for the cargo loading operation in oil or chemical tanker ship is presented to demonstrate the availability and feasibility of the H-HEART-F. After that, the sensitivity analysis and comparison study are conducted to further illustrate the reasonableness and effectiveness of the proposed method.     

基于概率犹豫模糊熵的多属性决策方法

针对概率犹豫模糊元的多个隶属度和其概率各不相同的特点,提出基于概率犹豫模糊熵的多属性决策方法.首先,定义3种新的概率犹豫模糊熵:模糊熵、犹豫熵和总熵,以分别测量概率犹豫模糊元的模糊性、犹豫性和整体不确定性;然后给出3种熵测度的公理化定义和表达式;最后,根据概率犹豫模糊元的3种熵,构建能够解决属性权重完全未知的多属性决策模型,并通过案例和对比分析验证所提模型的有效性和合理性.     

Quantitative relationship between time margin and human reliability

Operator reliability in complex systems is influenced by various performance shaping factors (PSFs). Time is a particularly important PSF; however, empirical studies of human reliability analysis (HRA) are rarely focused on modeling the effect of time PSF on human error probability (HEP). This study contributes to HRA literature by investigating the empirical relationship between time margin and HEP. Time margin is defined as the difference between the time available to complete a task and the time required to successfully complete the task, divided by the required time. We investigate and compare two models (logistic and linear) to explain HEP based on time margin. The empirical HEP data for model testing were extracted from a microworld simulator (Study 1) and a full-scope simulator (Study 2) in two existing studies relevant to procedural tasks in nuclear power plants. For Study 1, both models exhibited an acceptable, equivalent explanatory power; for Study 2, although both models exhibited an acceptable explanatory ability, the logistic model explained more variance in HEP. Our findings indicate the potential of the logistic model in explaining and predicting HEP based on time margin in time-critical tasks.     

基于递阶遗传算法模糊加权神经网络的模糊规则自动获取

针对模糊规则的自动获取一直是模糊系统的一个瓶颈问题,提出一种基于递阶结构的混合编码遗传算法与进化规划相结合的模糊加权神经网络学习新算法,利用该算法同时优化模糊加权神经网络的结构和参数,最后说明了从网络中提取模糊规则的方法,从而自动获得最优的模糊规则。分析和实验结果表明,本文方法在规则提取和分类准确性等方面比其他方法更好。     

基于感知推理方法的语言动力系统性质及数据驱动设计研究(英文)

The linguistic dynamic systems(LDSs) based on type-1 fuzzy sets can provide a powerful tool for modeling, analysis,evaluation and control of complex systems. However, as pointed out in earlier studies, it is much more reasonable to take type-2fuzzy sets to model the existing uncertainties of linguistic words. In this paper, the LDS based on type-2 fuzzy sets is studied, and its reasoning process is realized through the perceptual reasoning method. The properties of the perceptual reasoning method based LDS(PR-LDS) are explored. These properties demonstrated that the output of PR-LDS is intuitive and the computation complexity can be reduced when the consequent type-2 fuzzy numbers in the rule base satisfy some conditions. Further, a data driven method for the design of the PR-LDS is provided. At last, the effectiveness and rationality of the proposed data-driven method are verified by an example.     

基于改进模糊熵和证据推理的多属性决策方法

针对证据推理方法框架下属性权重难以获取的问题,提出一种基于改进模糊熵和证据推理的多属性决策方法。首先,定义证据推理信度决策矩阵框架下的三角函数模糊熵公式,并证明了其满足熵的四个公理化定义。其次,所提方法能够同时处理属性权重完全未知和属性权重信息部分已知两种情况：当属性权重完全未知时,基于信度框架下的改进模糊熵和熵权法的基本思想计算属性权重;当属性权重信息部分已知时,定义加权模糊熵,建立期望模糊熵最小的线性规划模型求解最优属性权重。最后,利用证据推理算法融合方案属性值,结合期望效用理论得到方案排序结果。通过实例计算,并与传统模糊熵计算方法进行比较分析,验证了所提方法能够更加充分地反映原始决策信息,更具客观性和一般性。     

模糊联想记忆网络的增强学习算法

针对 Kosko提出的最大最小模糊联想记忆网络存在的问题 ,通过对这种网络连接权学习规则的改进 ,给出了另一种权重学习规则 ,即把 Kosko的前馈模糊联想记忆模型发展成为模糊双向联想记忆模型 ,并由此给出了模糊快速增强学习算法 ,该算法能存储任意给定的多值训练模式对集 .其中对于存储二值模式对集 ,由于其连接权值取值 0或 1,因而该算法易于硬件电路和光学实现 .实验结果表明 ,模糊快速增强学习算法是行之有效的 .     

基于概率犹豫信息集成方法的群决策模型*

现有犹豫模糊集在描述决策信息时会导致决策信息大量损失,因此文中基于概率犹豫模糊信息集成算子,构建多属性群决策模型.首先在概率犹豫模糊环境下引入Archimedean范数,定义概率犹豫模糊运算法则.基于该运算法则,提出广义概率犹豫模糊有序加权平均(GPHFOWA)算子和广义概率犹豫模糊有序加权几何(GPHFOWG)算子,并讨论它们的基本性质.然后分析GPHFOWA算子和GPHFOWG算子的常见形式和相互关系.最后运用提出的2类算子构建概率犹豫模糊多属性群决策模型,并且通过供应商的选择实例验证决策模型的可行性和有效性.     

一种基于模糊加权型推理法的模糊神经网络

本文在Ｍａｍｄａｎｉ模糊推理法的基础上,给出了改进的模糊加权型推理法－广义模糊加权型推理法。     

基于直觉模糊熵的直觉语言多准则决策方法

针对现有直觉模糊熵方法中存在的一些问题,提出一种新的直觉模糊熵,并将其与现有的几种直觉模糊熵计算结果进行比较.针对准则权重信息不完全且准则值为直觉语言数的多准则决策问题,通过建立基于模糊熵的决策模型来求解准则的最优权系数,并利用直觉语言加权算数平均算子(IL-WAA)求出方案的综合准则值,进而由直觉语言数的记分函数确定方案的排序.最后,通过算例分析验证了该方法的有效性和合理性.     

大群体应急决策中考虑属性关联的偏好信息融合方法

针对大群体应急决策中属性之间相互关联的问题,提出一种新的偏好信息融合方法.首先,利用最优离散拟合模型测度专家的风险偏好,提出一种考虑专家风险偏好的犹豫模糊元补充方法;其次,运用TF-IDF算法获得相互关联的事件属性集;再次,结合传统的主成分分析法与误差理论,提出基于犹豫模糊语言的主成分分析模型,获得几个互不关联的主属性及其权重,进而进行信息集结和方案择优;最后,通过广西洪涝灾害事件验证所提方法的可行性和有效性.     

A method based on preference degrees for handling hybrid multiple attribute decision making problems

In this paper, we investigate hybrid multiple attribute decision making problems with various forms of attribute values (real numbers, linguistic labels, interval numbers, intuitionistic fuzzy numbers and interval intuitionistic fuzzy numbers). We propose a method based on preference degrees which may take the forms of fuzzy numbers, intuitionistic fuzzy numbers and interval intuitionistic fuzzy numbers. The method first normalizes various forms of attribute values into preference degrees, and then uses a preference degree-based weighted averaging operator to aggregate the normalized preference degrees. Meanwhile, for convenience of calculation, a new linguistic representation model is presented, whose feasibility is verified by comparing it with the traditional 4-tuple linguistic representation model, and from our model, the mapping relationship between interval intuitionistic fuzzy numbers and linguistic labels can be constructed. Finally, we illustrate the rationality and practicality of the proposed method by an application example.