动态特征选择算法对恶意行为检测的优化研究

针对互联网中存在的恶意行为,特别是社交网络应用中的在线恶意行为,通常使用基于用户多维特征的聚类分析算法进行检测。提出一种动态特征选择算法(DFSA),使用具有特征加权熵的模糊C均值目标函数,首先为参数构建一个学习模式,自动计算每个特征权重,并剔除权重小于阈值的特征,动态选择重要的特征,迭代地更新隶属函数、簇中心和特征权重直到最优化为止,最后识别出具有高精度的恶意用户行为簇。仿真结果表明,对比SDAFS算法、ELAFC算法和NADMB算法,DFSA算法在Rand指数、Jaccard指数和归一化互信息量3个主要性能指标上均有改善。     

基于ANFIS的长期电力负荷预测模型

某电力公司的长期负荷预测模型,利用自适应神经网络模糊推理系统(ANFIS)建立.其结构分为计算输入的模糊隶属度、每条规则适用度、适用度归一化、每条规则输出及模糊系统输出5层.系统网络中含14个待定的前件和后件参数.采用Matlab编程,通过Sugeno和evalfis函数训练ANFIS,按指定指标得到这些参数,实现模糊预测.     

基于AHP和改进模糊理论的某艇C3I系统效能评估

在AHP与模糊理论结合的方法对系统效能进行评估基础上,通过对模糊理论中隶属度计算方法进行改进,克服了一般模糊理论计算中隶属度转换过程中存在的对目标影响不起作用的冗余数据也参与运算的缺点.同时C3I系统效能评估为指挥人员及科研人员对舰艇作战能力了解有了初步依据.     

发动机技术状况的模糊关联度判断

本文依据模糊集理论和灰色系统理论的基本观点,建立了判断发动机技术状况的模糊加权关联度模型,给出了应用实例.     

岩体移动参数反分析的模糊数学方法

在采矿和岩土工程问题中,岩土移动变形及工程参数分析是该领域的重要工程研究课题.本文针对地下工程开挖而导致的岩体移动变形分析问题,根据模糊数学理论建立了模型,对工程参数确定给出了反分析方法.分析结果表明,理论结果与现场实测资料吻合较好,表明本文所建立的模糊数学模型适用于分析实际工程问题.     

AN ALTERNATIVE PERSPECTIVE ON FUZZY SET-BASED APPROXIMATE REASONING

Abstract

On the subject of fuzzy set-based approximate reasoning, this paper attempts to present a perspective that is both rigorously stated and different from the standard approach as stated by Mamdani and many others. Functionally speaking, this alternative perspective produces results essentially the same as the standard one, and in fact we intend to prove that subject to certain assumptions the results will be exactly die same. We feel however that the alternative perspective offers advantages in that it makes a more appropriate and more understandable use of such concepts as fuzzy relations, the extension principle, and fuzzy composition. If indeed it can lead to a clearer and more widespread understanding of the approximate reasoning formalism then this could conceivably spark broader interest in fuzzy control and other applications.     

LINGUISTIC FUZZY SYSTEMS AND THEIR APPLICATIONS IN ECONOMETRICS

This paper gives a brief summary of the linguistic fuzzy systems iheory and describes its possible application in econometric modelling. The essential feature of the used approach is a transformation of if-then rale bases into approximative deterministic behavior functions of considered economic systems.     

ENTROPY AND SPECIFICITY IN A MATHEMATICAL THEORY OF EVIDENCE

Abstract

We review Shafer's theory of evidence. We then introduce the concepts pf entropy and specificity in the framework of Shafer's theory. These become complementary aspects in the indication of the quality of evidence.     

Technology evaluation through the use of interval type-2 fuzzy sets and systems

Even though fuzzy logic is one of the most common methodologies for matching different kind of data sources, there is no study which uses this methodology for matching publication and patent data within a technology evaluation framework according to the authors’ best knowledge. In order to fill this gap and to demonstrate the usefulness of fuzzy logic in technology evaluation, this study proposes a novel technology evaluation framework based on an advanced/improved version of fuzzy logic, namely; interval type-2 fuzzy sets and systems (IT2FSSs). This framework uses patent data obtained from the European Patent Office (EPO) and publication data obtained from Web of Science/Knowledge (WoS/K) to evaluate technology groups with respect to their trendiness. Since it has been decided to target technology groups, patent and publication data sources are matched through the use IT2FSSs. The proposed framework enables us to make a strategic evaluation which directs considerations to use-inspired basic researches, hence achieving science-based technological improvements which are more beneficial for society. A European Classification System (ECLA) class – H01-Basic Electric Elements – is evaluated by means of the proposed framework in order to demonstrate how it works. The influence of the use of IT2FSSs is investigated by comparison with the results of its type-1 counterpart. This method shows that the use of type-2 fuzzy sets, i.e. handling more uncertainty, improves technology evaluation outcomes.     

L2–L∞ fuzzy control for Markov jump systems with neutral time-delays

The L₂–L_∞ fuzzy control problem is considered for nonlinear stochastic Markov jump systems with neutral time-delays. By means of Takagi–Sugeno fuzzy models, the fuzzy controller systems and the overall closed-loop fuzzy dynamics are constructed. A sufficient condition is firstly established on the stochastic stability using stochastic Lyapunov–Krasovskii functional. Then in terms of linear matrix inequalities techniques, the sufficient conditions on the existence of mode-dependent state feedback L₂–L_∞ fuzzy controller are presented and proved respectively for constant and time varying case. Finally, the design problems are formulated as optimization algorithms. Simulation results are exploited to illustrate the effectiveness of the developed techniques.