径向基函数（RBF）神经网络的一种极大熵学习算法

RBF神经网络中心向量的确定是整个网络学习的关键,该文基于信息论中的极大熵原理构造了训练中心向量的极大熵聚类算法,由此给出了网络的极大熵学习算法。文中最后分别用一个时间序列预测和系统辨识问题验证了该学习算法的有效性,同RBF网络和多层感知机的误差回传算法相比,该算法不仅在学习精度和泛化推广能力上有一定程度的提高,而且学习时间有显著的降低。     

面向医学图像分割的直线截距直方图倒数交叉熵方法

为了进一步 提高医学图像分割的速度和准确度,为临床诊断和辅助治疗提供更为充分有效的依据,本文 提出了一种基于直线截距直方图的倒数交叉熵图像阈值分割方法。首先定义了直线截距直方 图;然后根据医学图像的二维信息,建立该图像的直线截距直方图;最后,推导出基于该直 方图的倒数交叉熵阈值选取准则,并以此对医学图像进行分割。实验结果表明,与基于 混沌小生境粒子群优化(Niche chaotic mutation particle swarm optimization, NCPSO) 的二维倒数熵法、基于分解的二维指数灰度熵法、基于斜分的二维对称交叉熵法及基于粒子 群优化(Particle swarm optimization, PSO)的二维Tsallis交叉熵法相比,本文方法分割 后的图像中目标区域完整准确,边缘细节清晰丰富,且所需运行时间大幅减少,是医学影像 研究中可选择的一种快速有效的图像分割方法。     

直觉模糊集新的熵公式及应用

针对直觉模糊集的熵的公理化定义中存在的问题,修正了直觉模糊熵的公理化定义,给出了一个新的直觉模糊集的熵的计算公式,证明了其正确性。给出了一个基于直觉模糊数的熵的多属性决策算法,应用实例表明其合理性和有效性。     

关于“Vague集的新模糊熵”的注记

指出了“Vague集的新模糊熵”中模糊熵定义的错误,给出了修正后的模糊熵定义,提出了一种新的Vague集模糊熵的计算方法,并证明了该方法的有效性。     

Relative Entropies and Irreversible Thermodynamics

A critical discussion is given of the idea that the relation between microscopic dynamics and thermodynamics can be based on the concept of relative entropy. It is shown how dissipation can be treated in the response theory under certain conditions. A thermodynamic interpretation of the dynamical semigroup theory for a system interacting with its surroundings is given. By utilizing the method of maximum entropy with the well specified set of relevant observables, the construction of thermodynamic entropy is demonstrated. It is argued that the statistical (say, information) entropy cannot be identified with the thermodynamic entropy and that the relation between the two entropies is written in terms of the relative entropy. In this form, the distinction between the H-theorem and the second law of thermodynamics is easily made. It should be kept in mind that the H-theorem is for the kinetic stage while the second law is for the thermodynamic (or, hydrodynamic) stage.     

一种高速OFDM电力线通信终端的设计

宽带电力线通信技术(PLC)在家庭网络中具有很好的应用前景。OFDM是在低压电力线上实现高速数据通信的最合适的调制/解调方案。本文介绍了一种以基于OFDM技术的高速PLC物理层芯片SPC-200E为核心的PLC调制/解调器的物理层和MAC层的设计与实现,并给出了该Modem在室内低压PLC实验中的实验结果。     

随机信息系统属性相关性及在知识约简中的应用

引入随机信息系统的属性的信息熵,利用属性的信息熵来刻画随机信息系统的属性之间的相关性。提出一种利用属性相关性来进行随机信息系统知识约简的方法并给出基于该方法进行知识约简的算法。     

基于联合熵的多属性匿名度量模型

提出了基于联合熵的多属性匿名度量模型，该模型基于识别性、连接性、跟踪性等匿名属性．鉴于匿名的随机性和模糊性特点，提出了基于联合熵和最小加权广义距离的模糊模式识别方法，实现了系统匿名等级隶属度向量的离散化．给出了联合熵和加权广义距离之间平衡参数的确定方法．分析表明，该模型优于现有的单属性Shannon熵模型，平衡参数是从系统的角度惟一求解．因此，联合熵可以作为匿名等级的评价指标．     

A compact and accurate model for classification

We describe and evaluate an information-theoretic algorithm for data-driven induction of classification models based on a minimal subset of available features. The relationship between input (predictive) features and the target (classification) attribute is modeled by a tree-like structure termed an information network (IN). Unlike other decision-tree models, the information network uses the same input attribute across the nodes of a given layer (level). The input attributes are selected incrementally by the algorithm to maximize a global decrease in the conditional entropy of the target attribute. We are using the prepruning approach: when no attribute causes a statistically significant decrease in the entropy, the network construction is stopped. The algorithm is shown empirically to produce much more compact models than other methods of decision-tree learning while preserving nearly the same level of classification accuracy.     

基于小波奇异信息熵的10 kV供电系统故障选线研究与仿真

针对现有的供电系统中接地故障选线精度不足、反应速率较慢的问题,提出一种利用小波分析、奇异值分解和信息熵的融合的供电系统接地故障选线新方法.充分利用小波变换良好信号时频分析特点,奇异值分解维数压缩、特征提取能力,信息熵测度强大的系统状态、特征信号的定量描述、对比、研究特点,在系统故障后的故障选线中,克服单一方法对系统接地故障的失判或误判.通过Matlab与Simulink软件建立供电系统模型,对基于小波奇异信息熵的供电系统接地故障选线方法进行多方位的测试,实验结果表明该方法对供电系统接地故障能够快速、准确地诊断选线,是一种新的行之有效的供电系统接地故障选线方法.     

基于信息熵的改进模糊综合评价方法

将信息熵理论与模糊数学方法相结合,建立基于熵权的改进模糊综合评价方法。引用熵权所反应的数据本身的效用值来修正指标的权重系数,通过设定有效度指标来判断评价结果的有效性,采用基于贴近度的择近原则对失效结果做出新的评价。以水质评价为对象,通过实例计算并进行对比分析,发现其结果与其他评价方法的结果基本一致甚至更合理,表明该方法不但结构严谨,而且可信度较高,能有效提高模糊综合评价方法的工程实用性。     

基于信息熵的PCP综合决策模型研究

对信息熵理论进行了概述,提出了客观熵权(OEW)的概念,并给出了OEW的构造方法,进而建立了主成分投影(PCP)的综合决策模型,并在土地质量综合决策中进行了应用.结果表明,提出的方法是有效的、合理的.     

基于颜色和纹理特征的彩色图像检索

提出了一种基于颜色和纹理特征的图像检索方法。在对HSV颜色模型量化处理的基础上,提取颜色直方图作为图像的颜色特征。在提取纹理特征时,结合颜色量化结果,设计了反映图像纹理变化的状态转移概率矩阵,在此基础上,提出采用颜色相关熵来描述图像的纹理特征。由于综合利用了图像的颜色及纹理特征,实验结果表明,该方法取得了较好的检索效果。     

A least biased fuzzy clustering method

A new operational definition of cluster is proposed, and a fuzzy clustering algorithm with minimal biases is formulated by making use of the maximum entropy principle to maximize the entropy of the centroids with respect to the data points (clustering entropy). The authors make no assumptions on the number of clusters or their initial positions. For each value of an adimensional scale parameter β', the clustering algorithm makes each data point iterate towards one of the cluster's centroids, so that both hard and fuzzy partitions are obtained. Since the clustering algorithm can make a multiscale analysis of the given data set one can obtain both hierarchy and partitioning type clustering. The relative stability with respect to β' of each cluster structure is defined as the measurement of cluster validity. The authors determine the specific value of β' which corresponds to the optimal positions of cluster centroids by minimizing the entropy of the data points with respect to the centroids (clustered entropy). Examples are given to show how this least biased method succeeds in getting perceptually correct clustering results     

概率不确定语言熵及其多属性群决策

针对概率不确定语言集的多个不确定语言术语和其概率各不相同的特点,提出基于概率不确定语言熵的多属性决策方法。定义四种新的概率不确定语言熵：模糊熵、犹豫熵、不完全信息熵和总熵,以分别测量概率不确定语言集的模糊性、犹豫性、信息不完全性和整体不确定性。给出了四种熵测度的公理化定义和表达式,根据概率不确定语言集的四种熵,构建能够解决属性权重未知的多属性决策模型,并通过案例和对比分析验证了该模型的有效性和合理性。     

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.     

Development of PML absorbing boundary conditions for computational aeroacoustics: A progress review

Recent advances in the development of perfectly matched layer (PML) as absorbing boundary conditions for computational aeroacoustics are reviewed. The PML methodology is presented as a complex change of variables. In this context, the importance of a proper space-time transformation in the PML technique for Euler equations is emphasized. A unified approach for the derivation of PML equations is offered that involves three essential steps. The three-step approach is illustrated in details for the PML of linear and non-linear Euler equations. Numerical examples are also given that include non-reflecting boundary conditions for a ducted channel flow and mixing layer roll-up vortices.     

An entropy-theoretic classification of normal states

A theorem on the representation of normal states characterized by the dominant exponent is given. This theorem is applied to a classification of those states in terms of Ohya's entropy.     

基于样本分布与熵的数值型属性离散化

连续属性的离散化是数据预处理的重要工作。论文分析了基于熵的离散化方法的不足,从估计训练样本的概率分布的角度出发,提出基于样本分布与熵相结合的处理数值型属性的方法。基于UCI数据的实验结果表明,该方法不仅具有比较好的判决精度,而且具有更快的计算速度。