Improved Kernel Possibilistic Fuzzy Clustering Algorithm Based on Invasive Weed Optimization

Fuzzy c-means(FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means(PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some problems: it is still sensitive to initial clustering centers and the clustering results are not good when the tested datasets with noise are very unequal. An improved kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization(IWO-KPFCM) is proposed in this paper. This algorithm first uses invasive weed optimization(IWO) algorithm to seek the optimal solution as the initial clustering centers, and introduces kernel method to make the input data from the sample space map into the high-dimensional feature space. Then, the sample variance is introduced in the objection function to measure the compact degree of data. Finally, the improved algorithm is used to cluster data. The simulation results of the University of California-Irvine(UCI) data sets and artificial data sets show that the proposed algorithm has stronger ability to resist noise, higher cluster accuracy and faster convergence speed than the PFCM algorithm.     

Kernel Generalized Noise Clustering Algorithm

IntroductionFuzzy clustering is one of the important methodsin pattern recognition. The most widely used fuzzyclustering is the fuzzy c-means (FCM) algorithm[1]which is conceived by Dunn[2]and generalized byBezdek[3]. Based on an objective function, the F…     

基于改进的FCM在人脑MR图像分割中的应用

为解决模糊C-均值聚类（FCM）算法在医学图像分割中存在计算量大、运行时间过长以及样本集不理想会导致不好的聚类结果的问题,提出了相应的改进算法．利用收敛速度快的K均值聚类法得到的聚类中心作为FCM算法的初始聚类中心,并将样本对于各个聚类的隶属度之和为1这一约束条件,改变为所有样本对各类的隶属度总和等于样本总数．实验表明,该方法用于人脑磁共振图像分割时,运行速度提高了近3倍,分割准确度明显得到提高．     

基于个体最优位置的自适应变异扰动粒子群算法

针对粒子群算法在寻优时容易陷入局部最优的不足,提出了一种基于个体最优位置的自适应变异扰动粒子群算法AMDPSO (adaptive mutation disturbance particle swarm optimization).该算法以粒子群算法为基础,加入扰动,当满足自适应条件时,粒子以个体最优位置为依据进行变异操作.将该算法运用于6个测试函数,并与惯性权重粒子群算法、收缩因子粒子群算法以及差分进化算法进行了比较,结果表明:AMDPSO能在寻优过程中让粒子跳出局部最优,保持种群多样性,具有更好的收敛速度和优化性能.      

基于优化模糊C均值算法的锚泊船聚集特性

针对模糊C均值算法随机选择初始聚类中心导致聚类结果对噪声样本点敏感性的不足, 采用局部密度加权的方法, 将初始聚类中心的选择范围限制在局部密度较高样本点区域, 优化初始聚类中心的选择方法; 利用样本点的局部密度改进目标函数, 提高局部密度较高的样本点在目标函数迭代过程中的影响力, 从而提升模糊C均值算法的聚类性能, 并采用人造数据集和鸢尾花真实数据集验证优化的局部密度模糊C均值算法的聚类效果; 通过计算锚泊船位置数据的局部密度, 分析了船舶锚泊偏好。试验结果表明: 对比模糊C均值算法, 优化的局部密度模糊C均值算法聚类精准率提高了2.9%, 召回率提高了3.8%, F度量值提高了3.9%, 说明优化的局部密度模糊C均值算法的性能优于模糊C均值算法; 在锚泊船位置数据上的聚类结果正确反映了天津港锚泊船的聚集特点和锚泊偏好, 其结果与船舶的常规做法一致, 说明优化的局部密度模糊C均值聚类算法是一种分析锚泊船聚集特性和锚泊偏好的有效方法。      

Large Thinned Array Design Based on Multi-objective Cross Entropy Algorithm

To consider multi-objective optimization problem with the number of feed array elements and sidelobe level of large antenna array, multi-objective cross entropy(CE) algorithm is proposed by combining fuzzy c-mean clustering algorithm with traditional cross entropy algorithm, and specific program flow of the algorithm is given.Using the algorithm, large thinned array(200 elements) given sidelobe level(-10,-19 and-30 d B) problem is solved successfully. Compared with the traditional statistical algorithms, the optimization results of the algorithm validate that the number of feed array elements reduces by 51%, 11% and 6% respectively. In addition, compared with the particle swarm optimization(PSO) algorithm, the number of feed array elements from the algorithm is more similar, but the algorithm is more efficient.     

Application of particle swarm algorithm in the optimal allocation of regional water resources based on immune evolutionary algorithm

The optimal allocation model of regional water resources is built with the purpose of maximizing the comprehensive economic,social and environmental benefits of regional water consumption.In order to solve the problems that easily appear during the model solution of regional water resource optimal allocation with multiple water sources,multiple users and multiple objectives like＂curse of dimensionality＂or sinking into local optimum,this paper proposes a particle swarm optimization（PSO）algorithm based on immune evolutionary algorithm（IEA）.This algorithm introduces immunology principle into particle swarm algorithm.Its immune memorizing and self-adjusting mechanism is utilized to keep the particles in the fitness level at a certain concentration and guarantee the diversity of population.Also,the global search characteristics of IEA and the local search capacity of particle swarm algorithm have been fully utilized to overcome the dependence of PSO on initial swarm and the deficiency of vulnerability to local optimum.After applying this model to the allocation of water resources in Zhoukou,we obtain the scheme for optimization allocation of water resources in the planning level years,i.e.2015and 2025 under the guarantee rate of 50%.The calculation results indicate that the application of this algorithm to solve the issue of optimal allocation of regional water resources is reliable and reasonable.Thus it ofers a new idea for solving the issue of optimal allocation of water resources.     

非线性整数规划问题的改进粒子群优化算法

提出了一种求解非线性整数规划问题的改进粒子群优化算法．在这个算法里,对粒子群优化模型的速度方程和位置方程进行改进,加入了动态约束处理技术以提高选择最优点的能力;加入了粒子的邻域加速寻优策略以提高局部优化能力．数值结果表明所提出的算法计算精度高且稳定性好．     

基于目的层预约的改进型粒子群电梯群控调度策略

针对单一粒子群算法的派梯策略优化运算过程中容易陷入局部极值点的状况,结合模拟退火理论,提出一种改进型的粒子群电梯群控派梯策略,应用到目的层预约的电梯群控系统中.通过仿真和对比试验可知,基于目的层预约的电梯群控系统能有效地提高服务的各项指标,改进型的粒子群电梯群控调度策略可有效减小乘客候梯时间和电梯启停次数,改善电梯运行性能.     

基于遗传粒子群算法的船舶航迹融合研究

研究利用遗传算子对粒子群算法进行优化设计,建立了基于遗传算子的粒子群算法多源数据融合模型。该模型克服了粒子群算法在训练过程中容易陷入局部极值的缺陷,得到了更高的学习精度和更快的收敛速度。利用多传感器检测到的目标船舶航迹点数据进行了融合验证,MATLAB仿真结果表明,基于遗传算子的粒子群算法融合模型融合后的目标船舶航迹点比各传感器单独检测到的目标船舶航迹点数据更加精确,更适用于船舶航迹的跟踪及预测。     

Advanced Fuzzy C-Means Algorithm Based on Local Density and Distance

This paper presents an advanced fuzzy C-means (FCM) clustering algorithm to overcome the weakness of the traditional FCM algorithm, including the instability of random selecting of initial center and the limitation of the data separation or the size of clusters. The advanced FCM algorithm combines the distance with density and improves the objective function so that the performance of the algorithm can be improved. The experimental results show that the proposed FCM algorithm requires fewer iterations yet provides higher accuracy than the traditional FCM algorithm. The advanced algorithm is applied to the influence of stars’ box-office data, and the classification accuracy of the first class stars achieves 92.625%.     

基于改进K均值聚类POS算法的应急物资分类研究

为了提高突发事件应急救援的效率,应急物资分类的科学性是应急物资调拨与配送的关键环节之一.通过分析既有应急物资分类以及聚类算法存在的问题,提出了基于改进K均值聚类的应急物资分类方法,构建了基于K均值的粒子群优化算法设计.最后,选取了206种最为常用的应急物资为例,采用Matlab软件平台分析计算.结果表明:基于改进K均值聚类POS算法全局寻优能力明显要强于其他聚类算法.为应急决策者提供一定的理论依据.     

一种改进型粒子群算法求解资源优化配置问题

针对粒子群算法在求解优化问题时难以兼顾收敛精度与收敛速度这一问题,提出对目标的惯性权重进行修正和引入随着惯性权重变化的惯性学习因子的方法,该算法充分利用了上一代速度与位置、自我认知和群体间信息共享3部分内容,来影响算法的优化结果,提高了算法的全局和局部的搜索能力.最后将改进的粒子群算法应用于工程项目中的资源优化配置问题中,证明了该算法的有效性.     

基于粒子群的城市交通信号两级模糊控制

针对城市交通流的特点,设计一种单交叉口多相位两级模糊控制器,有效地减少控制规则数,实现相序、绿信比、周期随交通状况而自适应变化,并采用粒子群算法对模糊控制器的隶属度函数进行优化。仿真结果表明,该系统能有效地提高交叉口的通行能力,减少车辆平均延误。     

桁架结构拓扑优化的微粒群算法

为了解决有应力和位移约束的桁架结构的拓扑优化问题,将微粒群算法用于桁架结构拓扑优化.用罚函数法将应力和位移约束下的结构优化问题转化为无约束优化问题,用微粒群算法迭代计算.为了证明此方法的可行性,给出了2个具有应力和位移约束的桁架结构拓扑优化的算例.计算结果表明,微粒群算法与现有算法获得的桁架结构拓扑优化结果一致.     

局部阴影光伏发电系统中基于改进PSO的MPPT控制

光伏发电系统在局部阴影条件下,传统的最大功率点跟踪算法（maximum power point tracking,MPPT）容易陷入局部寻优,无法跟踪到全局最大功率点. 针对这一问题,本文提出了一种基于自适应学习因子粒子群算法的最大功率跟踪方法. 该方法在普通粒子群算法的基础上不断改变学习因子和权重系数,以提高算法收敛的速度和精度. 将其应用于局部阴影条件下的光伏发电系统最大功率点跟踪中,并在RT-LAB实时仿真平台中以两个接受不同光照强度的光伏阵列为例进行实时仿真验证. 仿真结果表明,两峰情况下本文所提出的自适应学习因子粒子群算法能够在0.298 s左右跟踪到全局最大功率点,普通粒子群算法需要约0.615 s,而扰动观察法陷入了局部最大功率点,本文所提算法能够有效提高系统的收敛速度和精度并且适用于多峰情况. 最后设置仿真算例验证本算法适用于光照突变的情况.      

RES脉内特征的差分进化粒子群投影寻踪评价模型

针对雷达辐射源信号脉内特征综合评估存在标准单一、缺乏客观性等问题,提出了基于群体智能的雷达辐射源信号脉内特征综合评估模型.首先,通过投影寻踪算法将雷达辐射源信号脉内特征的综合评估问题转化为有条件限制的多元非线性目标函数的优化问题;其次,通过改进的粒子群优化算法与差分进化算法的结合得到新的智能算法;最后,利用该算法实现多元非线性目标函数的优化求解.仿真结果表明:该群体智能算法对Rosenbrock测试函数的最优适应度值最小,对Rastrigrin函数和Girewank测试函数的最优适应度值为0,说明该算法的计算精度优于其他算法.同时适应度值的方差比标准粒子群算法和差分进化算法小,说明该算法的收敛性和鲁棒性较好.通过与加速遗传算法对评估问题目标函数5次优化结果的比较,本算法的计算结果没有波动,说明基于群体智能的RES脉内特征综合评估模型能够更客观、更有效地实现对RES脉内特征的综合评估.      

Magnetic Tile Surface Defect Detection Based on Texture Feature Clustering

In the field of magnetic tile surface detection, artificial detection efficiency is low, and the traditional image segmentation algorithm cannot show good performance when the gray scale of the magnetic tile itself is small, or the image is affected by uneven illumination. In view of these questions, this paper puts forward a new clustering segmentation algorithm based on texture feature. This algorithm uses Gabor function spectra to represent magnetic tile surface texture and then uses a user-defined local product coefficient to modify Gabor energy spectra to get the center number of fuzzy C-means(FCM) clustering. Moreover, the user-defined Gabor energy spectra image is segmented by clustering algorithm. Finally, it extracts the magnetic tile surface defects according to the changes of regional gray characteristics. Experiments show that the algorithm effectively overcomes the noise interference and makes a good performance on accuracy and robustness, which can effectively detect crack,damage, pit and other defects on the magnetic tile surface.     

基于免疫粒子群神经网络的短时交通流量预测

免疫理论中的基于浓度选择机制能避免粒子群算法在群体收敛性和个体多样性平衡问题上的不足,使改进后的粒子群算法优化BP神经网络参数的配置,提高短时交通流量预测的准确性。仿真实验表明：免疫粒子群优化后的BP神经网络可有效提高短时交通流量的预测精度,减小预测误差。     

FCM聚类分析在公路边坡稳定性评价中的应用

在公路工程边坡稳定性评价过程中需要考虑很多因素的影响,这些影响难以用精确的数字来描述,因此很多情况下不适宜用定量的评价方法。鉴于此,主要采用FCM聚类分析方法研究公路边坡的稳定性评价,引入模糊聚类和改进的遗传算法,克服了传统FCM算法在模糊聚类分析中对初始化敏感的缺点,对于存在多个不确定因素的评价问题有明显的优势。通过实例分析表明,用该方法对公路工程中边坡稳定性评价是可行的、有效的。