Fast recursive algorithm for two-dimensional Tsallis entropy thresholding method

Recently, a two-dimensional （2-D） Tsallis entropy thresholding method has been proposed as a new method for image segmentation. But the computation complexity of 2-D Tsallis entropy is very large and becomes an obstacle to real time image processing systems. A fast recursive algorithm for 2-D Tsallis entropy thresholding is proposed. The key variables involved in calculating 2-D Tsallis entropy are written in recursive form. Thus, many repeating calculations are avoided and the computation complexity reduces to O（L2） from O（L4）. The effectiveness of the proposed algorithm is illustrated by experimental results.

多向加权Tsallis熵最大化导向的自动阈值分割方法

受噪声或随机细节、目标和背景的大小比例、成像时的点扩散等不同因素的影响,许多图像的灰度直方图呈现为无模态、单模态、双模态或者多模态样式.为了在统一框架内处理这4种不同模态情形下的自动阈值选择问题,本文提出了一种多向加权Tsallis熵最大化导向的自动阈值分割方法(Multi-directional Weighted Tsallis Entropy,MWTE).基于新设计的反正切方向性卷积核的多尺度乘积效应,该方法将不同模态的灰度直方图转化为统一的单模态右偏灰度直方图.在4个不同方向上提取出这种特殊的单模态右偏灰度直方图后,通过多向加权策略构建出与原始图像灰度值紧密相关的加权Tsallis熵目标函数,并以该目标函数取最大值时对应的灰度值作为最终分割阈值.本文将提出的方法和3个阈值分割方法、1个软分割方法、1个活动轮廓分割方法以及1个自动聚类分割方法进行了比较.在4种不同模态情形下的4幅合成图像和50幅真实世界图像上的实验结果表明,本文提出的方法虽然在计算效率方面不占有优势,但它对不同模态的测试图像具有更稳健的分割适应性,且在量化分割精度所用的马修斯相关系数方面优于其他6个分割方法.

Image Thresholding Using Two-Dimensional Tsallis Cross Entropy Based on Either Chaotic Particle Swarm Optimization or Decomposition

The segmentation effect of Tsallis entropy method is superior to that of Shannon entropy method, and the computation speed of two-dimensional Shannon cross entropy method can be further improved by optimization. The existing two-dimensional Tsallis cross entropy method is not the strict two-dimensional extension. Thus two new methods of image thresholding using two-dimensional Tsallis cross entropy based on either Chaotic Particle Swarm Optimization (CPSO) or decomposition are proposed. The former uses CPSO to find the optimal threshold. The recursive algorithm is adopted to avoid the repetitive computation of fitness function in iterative procedure. The computing speed is improved greatly. The latter converts the two-dimensional computation into two one-dimensional spaces, which makes the computational complexity further reduced from O(L2) to O(L). The experimental results show that, compared with the proposed recently two-dimensional Shannon or Tsallis cross entropy method, the two new methods can achieve superior segmentation results and reduce running time greatly.

Tsallis相对熵引导的包裹相位修补

齿轮齿面形貌激光干涉测量中,由于容易受到多种噪声干扰,采集到的包裹相位图中会存在相位质量差的区域,解包路径经过这些区域会造成解包裹错误,降低测量精度。针对这一问题,根据干涉条纹图像的概率分布特点,本文提出一种基于Tsallis相对熵质量评价的包裹相位修补方法。该方法先利用高斯分布拟合阈值处理后的图像,再由Tsallis相对熵评价相位质量,最后修补质量较差的区域以提高相位解包裹质量。设计对比实验验证本方法的有效性,实验结果表明,该方法可以减少40%的相位残差点,并且有效提高了相位质量。该方法使用简单,准确率高,同样适用于其他移相光学领域。

基于多尺度多方向Gabor变换的Tsallis熵阈值分割方法

为了能在统一框架内处理无模态、单模态、双模态或者多模态直方图情形下的自动阈值选取问题,该文提出一种基于多尺度多方向Gabor变换的Tsallis熵阈值分割方法(MGTE)。该方法先通过Gabor变换得到多尺度乘积图像,然后利用内外轮廓图像从多尺度乘积图像中重构1维直方图,并在重构1维直方图上采用Tsallis熵计算模型来选取4个方向Tsallis熵取最大值时对应的阈值,最后对4个方向的阈值进行加权求和作为最终分割阈值。将提出的方法和5个分割方法在4幅合成图像和40幅真实世界图像上进行了实验。结果表明提出的方法虽然计算效率不占优势,但它的分割适应性和分割精度有明显的提高。

基于Tsallis相对熵的DEMATEL阈值确定研究

目前现有的决策试行与评价实验室(DEMATEL)中阈值的确定存在着主观随意性强、阈值偏大、阈值求解不稳定等缺陷,为解决上述问题,提出了基于Tsallis相对熵的DEMATEL阈值确定新方法。首先基于质量控制理论对专家打分表进行了筛选。然后利用证据理论融合专家意见,从众影响关系中选出最重要的影响因素,并将其影响关系的大小作为阈值上限。最后利用区间对矩阵元素信息的概率分布进行了定义,并选取Tsallis相对熵最小时对应的分割阈值作为最终阈值。通过与其他方法的对比分析,基于Tsallis相对熵的阈值确定方法能有效去除系统中的冗余信息,且使用时更具有一般性,实例计算也验证了整个阈值确定流程的可操作性。

快速二维累积剩余Tsallis熵阈值分割方法

对灰度直方图呈现为双峰的图像,传统的二维直方图阈值分割方法虽然比较有效,但在灰度直方图呈现为无峰、单峰或多峰模式时,它们的分割结果较差。考虑到经过二维直方图映射得到的二维生存函数存在密度连续和形态统一等优点,本文基于图像二维生存函数提出一种快速二维累积剩余Tsallis熵阈值分割方法。该方法首先基于二维直方图构造二维生存函数,然后在二维生存函数的基础上定义计算分割阈值的二维累积剩余Tsallis熵目标函数。通过递推算法将计算目标函数的时间复杂度降为O(L^(2))。最后,基于递推形式的二维累积剩余Tsallis熵准则得到最优阈值向量以进行阈值分割。在26幅合成图像和76幅真实世界图像上将提出的方法与2种快速二维阈值分割方法、2种聚类分割方法以及1种活动轮廓分割方法分别在时间和误分类率(Misclassification Error,ME)2个指标下进行了比较。实验结果表明,在合成图像和真实世界图像中,相比于性能第2的方法,本文方法的时间平均缩短0.013 s,ME值平均降低0.051~0.089。提出的快速二维累积剩余Tsallis熵阈值分割方法不仅在计算效率方面优于对比的5种方法,而且在分割适应性和分割精度方面具有明显优势。

基于Tsallis熵的近似差分隐私K-means算法

利用K-means算法对用户信息进行聚类时,存在隐私泄露的风险。差分隐私保护技术可提供严格的隐私保护,但目前大多数满足差分隐私的K-means算法在处理多维数据时,存在随机选择质心和噪声添加不均衡的问题,因而导致聚类结果不理想。为此,本文提出一种基于Tsallis熵的近似差分隐私K-means算法。针对质心选择的随机性问题,提出Tsallis熵对属性赋权的策略来优化对象间的欧氏距离,然后对比各对象到唯一随机初始质心的赋权欧式距离来确定其余初始质心,使算法在减少随机选择初始质心的同时,提高模型准确率;在此基础上,针对噪声添加不均衡的问题,提出一种能够平衡信噪比的隐私预算分配策略,然后对迭代质心加入高斯扰动,使算法在不增加计算复杂度的情况下满足(ε,δ)-差分隐私保护,同时提升扰动结果的准确性;最后在四个真实数据集上对算法进行有效性评价。实验结果表明,所提出的算法能够在保证用户隐私安全的同时实现高效用的聚类。

基于多尺度小波和Tsallis熵的水下图像边缘检测

针对水下图像对比度低和边缘模糊的问题,提出一种基于多尺度小波和Tsallis熵的水下图像边缘检测算法。首先,结合多尺度小波分解特性,采用开放暗通道模型移除低频雾霾现象和软阈值操作降低高频噪声;其次,采用二维高斯函数构造高斯尺度空间进行背景估计,以区分背景与目标信息;最后,结合信息熵和Tsallis熵求得最优阈值,从而得到边缘检测图像。实验结果表明,该算法能有效检测出退化水下图像的边缘轮廓信息,去除虚假边缘情况,准确提取图像的特征边缘。同时应用测试显示,该算法在大气雾霾图像的边缘检测方面表现出色。

基于Tsallis熵的两点法确定明渠断面流速分布及数值模拟验证

在现代农业灌溉中,为了得到明渠断面的流量,首先需要确定明渠断面的流速分布,然而以往的流速分布公式大都不够准确,无法满足精准灌溉的需求,针对这一难题,在基于Tsallis熵推导流速分布的基础上,对熵参数重新推导,提出新的熵参数,进一步简化了流速分布公式,提出两点法确定断面流速分布的研究方法,并结合实测资料和数值模拟软件进行验证。结果表明:通过测量水面下断面中心线上一点流速值u_(c)与相同水深下另一点的流速值u_(z),可计算出流速分布公式中两个未知参数G_(p)、m_(p),确定该水深位置横向流速分布公式,再通过已知参数计算出断面最大流速u_(max),并确定断面中心线流速分布公式。与以往的流速分布公式相比,两点法更加简便,能够较好的应用在工程实际中,具有较高的理论意义和实用价值。

基于改进PSO的三维Tsallis熵图像分割

针对二维Tsallis熵图像分割不精确以及优化图像阈值分割函数的元启发式优化算法容易陷入局部最优这两个问题,提出了一种新的三维Tsallis熵阈值分割法以及一种新的改进粒子群优化算法。通过引入均值、中值、梯度三种因素,构建出三维直方图,并结合Tsallis熵理论提出了一种三维Tsallis熵阈值分割法。为了避免粒子群优化算法陷入局部最优,通过引入综合学习策略并改进粒子群优化算法的迭代方式,提出了综合学习改进粒子群优化算法。将提出的三维Tsallis熵阈值分割法与综合学习改进粒子群优化算法结合进行图像分割。与其他元启发式算法相比,综合学习改进粒子群优化算法能在低维环境下有效避免局部最优。实验结果表明相比于二维Tsallis熵阈值分割法,三维Tsallis熵阈值分割法分割效果更好,且具有更好的抗噪性能。由此可以表明综合学习改进粒子群优化算法结合三维Tsallis熵进行图像分割可以取得更好的结果。

Thermodynamic properties at the kinetic freeze-out in the Au + Au and Cu + Cu collisions at the RHIC using the Tsallis distribution

The thermodynamic properties of charged particles,such as the energy density,pressure,entropy density,particle density,and squared speed of sound at the kinetic freeze-out in the Au+Au collisions from the relativistic heavy ion collider (RHIC)beam energy scan program √S_(NN) and in the Cu+Cu collisions at √S_(NN),200 GeV are studied using the thermodynamically consistent Tsallis distribution.The energy density,pressure,and particle density decrease monotonically with the collision energy for the same collision centrality;These properties also decrease monotonically from the central to peripheral collisions at the same collision energy.While the scaled energy densityε∕T^(4) and scaled entropy density s∕T^(3) demonstrate the opposite trend with the collision energy for the same collision centrality.There is a correlation betweenε∕T^(4) and s∕T^(3) at the same centrality.In addition,the squared speed of sound was calculated to determine that all the collision energies share nearly the same value at different collision centralities.

Two-dimensional horizontal visibility graph analysis of human brain aging on gray matter

Characterizing the trajectory of the healthy aging brain and exploring age-related structural changes in the brain can help deepen our understanding of the mechanism of brain aging.Currently,most structural magnetic resonance imaging literature explores brain aging merely from the perspective of morphological features,which cannot fully utilize the grayscale values containing important intrinsic information about brain structure.In this study,we propose the construction of two-dimensional horizontal visibility graphs based on the pixel intensity values of the gray matter slices directly.Normalized network structure entropy(NNSE)is then introduced to quantify the overall heterogeneities of these graphs.The results demonstrate a decrease in the NNSEs of gray matter with age.Compared with the middle-aged and the elderly,the larger values of the NNSE in the younger group may indicate more homogeneous network structures,smaller differences in importance between nodes and thus a more powerful ability to tolerate intrusion.In addition,the hub nodes of different adult age groups are primarily located in the precuneus,cingulate gyrus,superior temporal gyrus,inferior temporal gyrus,parahippocampal gyrus,insula,precentral gyrus and postcentral gyrus.Our study can provide a new perspective for understanding and exploring the structural mechanism of brain aging.

Two-dimensional cross entropy multi-threshold image segmentation based on improved BBO algorithm

In order to improve the global search ability of biogeography-based optimization(BBO)algorithm in multi-threshold image segmentation,a multi-threshold image segmentation based on improved BBO algorithm is proposed.When using BBO algorithm to optimize threshold,firstly,the elitist selection operator is used to retain the optimal set of solutions.Secondly,a migration strategy based on fusion of good solution and pending solution is introduced to reduce premature convergence and invalid migration of traditional migration operations.Thirdly,to reduce the blindness of traditional mutation operations,a mutation operation through binary computation is created.Then,it is applied to the multi-threshold image segmentation of two-dimensional cross entropy.Finally,this method is used to segment the typical image and compared with two-dimensional multi-threshold segmentation based on particle swarm optimization algorithm and the two-dimensional multi-threshold image segmentation based on standard BBO algorithm.The experimental results show that the method has good convergence stability,it can effectively shorten the time of iteration,and the optimization performance is better than the standard BBO algorithm.

On Utilization of K-Means for Determination of <i>q</i>-Parameter for Tsallis-Entropy-Maximized-FCM

In this paper, we consider a fuzzy c-means (FCM) clustering algorithm combined with the deterministic annealing method and the Tsallis entropy maximization. The Tsallis entropy is a q-parameter extension of the Shannon entropy. By maximizing the Tsallis entropy within the framework of FCM, membership functions similar to statistical mechanical distribution functions can be derived. One of the major considerations when using this method is how to determine appropriate q values and the highest annealing temperature, Thigh?, for a given data set. Accordingly, in this paper, a method for determining these values simultaneously without introducing any additional parameters is presented. In our approach, the membership function is approximated by a series of expansion methods and the K-means clustering algorithm is utilized as a preprocessing step to estimate a radius of each data distribution. The results of experiments indicate that the proposed method is effective and both q and Thigh can be determined automatically and algebraically from a given data set.

A New Approach to Time-Dependent Solutions to the Non-Linear Fokker-Planck Equations Related to Arbitrary Functions of Tsallis Entropy: A Mathematical Study and Investigation

The following article has been retracted due to the investigation of complaints received against it. Mr. Mohammadali Ghorbani (corresponding author and also the last author) cheated the authors’ name: Alireza Heidari and Seyedali Vedad. The scientific community takes a very strong view on this matter and we treat all unethical behavior such as plagiarism seriously. This paper published in Vol.3 No.5 420-429, 2012, has been removed from this site.

EXISTENCE OF ENTROPY SOLUTIONS TO TWO-DIMENSIONAL STEADY EXOTHERMICALLY REACTING EULER EQUATIONS

We are concerned with the global existence of entropy solutions of the two-dimensional steady Euler equations for an ideal gas, which undergoes a one-step exothermic chemical reaction under the Arrhenius-type kinetics. The reaction rate function φ（T ） is assumed to have a positive lower bound. We first consider the Cauchy problem （the initial value problem）, that is, seek a supersonic downstream reacting flow when the incoming flow is supersonic, and establish the global existence of entropy solutions when the total variation of the initial data is sufficiently small. Then we analyze the problem of steady supersonic, exothermically reacting Euler flow past a Lipschitz wedge, generating an ad-ditional detonation wave attached to the wedge vertex, which can be then formulated as an initial-boundary value problem. We establish the global existence of entropy solutions containing the additional detonation wave （weak or strong, determined by the wedge angle at the wedge vertex） when the total variation of both the slope of the wedge boundary and the incoming flow is suitably small. The downstream asymptotic behavior of the global solutions is also obtained.

Nonextensivity and Tsallis Entropy in DNA Fragmentation Patterns by Ionizing Radiation

Nonextensive statistical mechanics as in Tsallis formalism was used in this study, along with the dynamical Hamiltonian rod-like DNA model and the maximum entropy criteria for Tsallis’ entropy, so as to obtain length distribution of plasmid fragments, after irradiation with very high doses, assuming that the system reaches metaequilibrium. By intensively working out the Grand Canonical Ensemble (used to take into account the variation of the number of base pairs) a simplified expression for Fragment Size Distribution Function (FSDF) was obtained. This expression is dependent on two parameters only, the Tsallis q value and the minimal length of the fragments. Results obtained from fittings to available experimental data were adequate and the characteristic behavior of the shortest fragments was clearly documented and reproduced by the model, a circumstance never verified from theoretical distributions. The results point to the existence of an entropy which characterizes fragmentation processes and depending only on the q entropic index.

融合量子克隆进化与二维Tsallis熵的医学图像分割算法

针对进化算法用于图像分割时收敛速度慢、易早熟的缺点,提出一种改进的量子克隆进化算法.首先利用量子空间的多样性丰富种群信息,在量子变异中根据适应度的不同对个体施以不同的混沌扰动,以克服量子门旋转方向单一、大小固定的缺陷,避免种群陷入局部早熟;然后利用克隆算子将最优个体信息扩充至下一代,以提高其局部寻优能力,加快收敛速度;最后将此算法用于寻找二维Tsallis熵的最佳阈值,实现了对图像的分割.实验结果表明,该算法有效地解决了进化算法收敛速度慢和容易陷入局部极值的问题,而且在分割速度和精度上得到了较大提高,分割效果良好,可以满足医学图像三维重建要求.

输电线路故障层次化变步长Tsallis小波奇异熵诊断方法

为提高熵方法输电线路故障信号时-频域的特征提取能力,提出层次化变步长Tsallis小波奇异熵(Tsallis Wavelet Singular Entropy,TWSE)方法用于电力系统故障诊断。首先,对采集到的电压信号进行小波分解与单支重构,构建时-频矩阵;之后,将奇异值分解与Tsallis熵理论相结合,对该时-频矩阵求滑动步长为1的Tsallis奇异熵,确定故障发生时刻;然后,对故障发生后1周期内的三相电压重构系数求滑动步长为1/4周期的TWSE,构建用于故障诊断的特征向量;最后,将TWSE特征向量输入到极限学习机(Extremly Learning Machine,ELM)分类器中,实现输电线路故障诊断。仿真结果表明,新方法具有更好的故障暂态信号特征表现能力,且分类结果不受故障时间、过渡电阻和故障位置等因素影响,相较基于小波奇异熵的线路故障诊断方法具有更好的诊断效果。