Identification and classification of dynamic event tree scenarios via possibilistic clustering: Application to a steam generator tube rupture event

This paper illustrates a method to identify and classify scenarios generated in a dynamic event tree (DET) analysis. Identification and classification are carried out by means of an evolutionary possibilistic fuzzy C-means clustering algorithm which takes into account not only the final system states but also the timing of the events and the process evolution. An application is considered with regards to the scenarios generated following a steam generator tube rupture in a nuclear power plant. The scenarios are generated by the accident dynamic simulator (ADS), coupled to a RELAP code that simulates the thermo-hydraulic behavior of the plant and to an operators’ crew model, which simulates their cognitive and procedures-guided responses.A set of 60 scenarios has been generated by the ADS DET tool. The classification approach has grouped the 60 scenarios into 4 classes of dominant scenarios, one of which was not anticipated a priori but was “discovered” by the classifier. The proposed approach may be considered as a first effort towards the application of identification and classification approaches to scenarios post-processing for real-scale dynamic safety assessments.     

一种新的最小二乘支持向量聚类

针对传统支持向量聚类的低性能和高耗费问题,提出最小二乘支持向量聚类(LSSVC)模型,设计自适应参数化方案。模型中包括两步簇划分算法和快速训练算法。前者对支持向量和非支持向量分别进行划分,后者采用增量方式,每次增量对应聚类模型的双向学习过程。实验结果证明,LSSVC可有效提高同类算法的效率,具有良好聚类能力,当数据增量为工作集大小的10%时,算法可在时间耗费和聚类准确率之间取得良好的平衡。     

基于Gur Game的LEACH改进算法

在LEACH中引入了Gur Game算法,来实现对无线传感网络中工作节点总数的控制。在节点密度较高的网络中,当算法满足它的节点密度要求时,允许部分节点进入低能耗状态同时也减少了簇头节点个数。仿真实验证明改进算法与LEACH相比能有效延长了系统的生存时间。     

基于遗传FCM算法和SVM的图像检索

提出基于遗传FCM聚类算法和SVM相关反馈的图像检索方法。首先对图像库提取颜色和纹理特征,采用遗传FCM聚类算法对图像进行聚类,得到每个图像类的聚类中心;最后计算查询示例图像和对应图像类的图像之间的相似度,按照相似度的大小返回检索结果。为了进一步提高检索精度,提出基于SVM的相关反馈算法。实验结果表明,提出的方法具有优良的检索性能。     

一种含影响力因子的自适应C均值算法

含影响力因子的硬聚类算法(HCMef)在对多于两类规模不均的样本进行聚类时,影响力因子指数对聚类结果影响很大,取值不当会引起类消失.影响力因子指数在0附近穷举,并利用影响力因子指数较大时类规模会在较少训练次数内消失的现象,降低计算量.提出了含影响力因子的自适应C均值聚类策略(AHCMef),并介绍了两阶段聚类方法,进一步提高聚类成功率和执行效率.结果显示,最佳影响力因子指数出现在成功聚类时的较大值附近,聚类效果从该点起随影响力因子指数的减小而降低.对HCMef算法应用于多类规模不均样本情况时,影响力因子指数的选取具有指导意义.     

基于密度加权的粗糙K-均值聚类改进算法

针对粗糙K-均值聚类算法中类均值计算式的特点,提出了一种改进的粗糙K-均值算法.改进后的算法基于数据对象所在区域的密度,在类的均值计算过程中对每个对象赋以不同的权重.不同测试数据集的实验结果表明,改进后的粗糙K-均值算法提高了聚类的准确性,降低了迭代次数,并且可以有效地减小孤立点对聚类的影响.     

卫星云图感兴趣区域自动提取方法研究

卫星云图中人们感兴趣的区域(ROI)往往是各类云团,针对卫星云图内容的复杂性,利用直方图模糊加权C均值聚类方法实现云图的图像分割,对分割结果进行后处理,最终获取云图内的感兴趣区域。常规聚类方法需要人工指定类个数,影响了ROI提取过程的自动化程度。引入修正聚类评价指标,基于该指标实现最佳类别个数的自动确定。云图分割是感兴趣区域提取过程的关键,采用的直方图模糊加权C均值聚类方法在原有算法基础上,引入样本权重概念,使得聚类过程更为合理;同时将聚类对象由原始像素转换为灰度直方图,提高了聚类过程执行效率。实验结果表明设计的感兴趣区域提取方法能较为准确地分辨出陆地、水体、低云、中云、卷云、对流云六类区域,提取结果与客观实际一致。     

基于兴趣的社交网络用户聚类及可视化

随着社交网络的流行,从各种各样的社交网络数据中提取出有效信息并进行清晰直观的可视化分析,从而为用户提供有价值的潜在知识,显得尤为重要。聚类分析是数据挖掘中的重要分析手段,传统的面向社交网络数据的用户聚类分析大都仅考虑网络的拓扑链接结构,未考虑用户的兴趣相似度。文中基于贝叶斯概率模型来计算用户兴趣相似度并进行聚类,进一步设计交互可视化方式来展示上述聚类结果。具体地,针对社交网络中的用户评分数据 建立潜在语义模型来提取表示每个用户兴趣特点的特征向量;基于用户的特征向量对用户进行聚类,得到具有不同特征的人群,并通过实验和热度图选择合适的人群聚类数;最后提出了基于层次气泡图的可视化展现和分析方案,将用户、电影类型、电影等多维信息在图形中交互展示,支持用户从全局概览到局部细节的推进式探索,从多角度可视化人群特征。对豆瓣网用户和电影评分数据进行了实验和分析,结果验证了所提方法的有效性。     

The mystery of clustering in macromolecular media

Clustering occurs in most polar media such as water-soluble macromolecules. The true origin of clustering has been elusive despite a great deal of research effort. This paper uses the simplest water-soluble polymer, poly(ethylene oxide), dissolved in deuterated water to investigate the cause of clustering. The small-angle neutron scattering technique is used to separate out solvation effects from clustering effects and back out the various interaction parameters. It is found that clustering is related to attractive inter-chain interactions between hydrophobic groups which create physical crosslinks thereby causing clustering.     

Agglomerative clustering using the concept of mutual nearest neighbourhood

A method for determining the mutual nearest neighbours (MNN) and mutual neighbourhood value (mnv) of a sample point, using the conventional nearest neighbours, is suggested. A nonparametric, hierarchical, agglomerative clustering algorithm is developed using the above concepts. The algorithm is simple, deterministic, noniterative, requires low storage and is able to discern spherical and nonspherical clusters. The method is applicable to a wide class of data of arbitrary shape, large size and high dimensionality. The algorithm can discern mutually homogenous clusters. Strong or weak patterns can be discerned by properly choosing the neighbourhood width.