基于随机权重粒子群和K-均值聚类的图像分割

K-均值聚类具有简单、快速的特点,因此被广泛应用于图像分割领域.但K-均值聚类容易陷入局部最优,影响图像分割效果.针对K-均值的缺点,提出一种基于随机权重粒子群优化（RWPSO）和K-均值聚类的图像分割算法RWPSOK.在算法运行初期,利用随机权重粒子群优化的全局搜索能力,避免算法陷入局部最优;在算法运行后期,利用K-均值聚类的局部搜索能力,实现算法快速收敛.实验表明：RWPSOK算法能有效地克服K-均值聚类易陷入局部最优的缺点,图像分割效果得到了明显改善;与传统粒子群与K-均值聚类混合算法（PSOK）相比,RWPSOK算法具有更好的分割效果和更高的分割效率.     

基于WebGIS的电子商务空间数据挖掘方法研究

聚类是重要的空间数据挖掘技术,主要用于在隐含的数据中发现有意义的数据分布和数据模式。针对k-means算法依赖于聚类中心,聚类个数以及容易陷入局部最优的缺点,提出"蚁群聚类算法",并将此算法应用到WebGIS的电子商务平台中。实验结果表明:此算法具有良好的性能。     

基于毫米波雷达的运动目标点云聚类和扩展算法

用毫米波雷达对运动目标进行姿态识别时,雷达点云数据具有噪点多、分布离散的特征,传统基于密度空间的聚类算法对点云聚类成像的过程中,会出现邻近目标之间的点云分类错误及同一目标点簇聚类为多个点簇等问题。针对上述情况,提出一种运动多目标邻近点云优化聚类算法,利用自适应距离加权的模糊c均值算法对聚类结果进行修正,提高近邻目标点云聚类准确度。同时提出一种目标点簇扩展聚合算法,利用卡尔曼滤波对运动目标位置预测,将多帧迭代三维点云尺寸作为波门对目标点云进行点簇扩展,提高目标点云完整性。试验结果表明,所提方法能有效提高聚类准确度。     

基于多尺度信息融合的层次聚类算法

在体绘制领域和图像分割中,数据集通常具有流形结构,各部分边界连接紧密且伴随局部噪声,给传统聚类算法的应用带来了较大的困难．本文根据非参数密度估计方法提出了一种基于多尺度信息融合的层次聚类算法．新算法通过整合密度差异和边界信息构造了一种多尺度结构信息融合的相似性度量,通过水平集的图连接策略推导出一种层次化的类结构剖析过程以获取稳定的聚类结果．新算法不受数据集形状、密度类型的限制,无需对数据集进行假设,可自动识别数据集常见的聚类结构特征．同时聚类结果较为稳定,算法对噪声具有较强的鲁棒性．从人工数据集和真实数据集以及应用试验的测试结果可以看出新算法的优越性能．     

基于DTW距离的探地雷达数据可视化

提出一种基于动态时间弯曲算法距离度量的探地雷达数据可视化方法,利用动态时间弯曲算法在时间轴方向上伸缩的优越性,结合可指定类数的聚类算法对探地雷达数据进行聚类和可视化分析。可用于实测的探地雷达数据集,实验结果表明,相对于传统的聚类算法,本文算法能得到更好的聚类结果。     

改进的灰度级-彩色变换法在B超图像中的应用

B超图像的伪彩色增强在医学临床诊断上具有重要意义。该文提出了一种对灰度级-彩色变换法中分段传递函数阈值重新划分的新算法。该算法首先利用改进的K均值聚类算法对图像的灰度值进行聚类,再根据聚类各簇的灰度值阈值重新设置分段传递函数的节点。通过实验对比,该算法处理后的图像轮廓更清晰,层次感更强,能有效地突出病灶区,有利于医学诊断。     

基于改进谱聚类算法的复杂产品模块发现方法研究

模块化复杂产品具有耦合性、多层次和重叠性等复杂特征。针对现有模块发现方法不能识别产品架构中的重叠结构,本文在对谱聚类算法进行改进的基础上,提出一种新的复杂产品模块发现方法。该方法能实现复杂产品模块化组织的可视化,发现共享零部件,有助于协同设计和任务间的信息交互。以轮式装载机的工作装置为实例,验证了该方法的可行性。     

基于改进蝙蝠优化自确定的模糊C-均值聚类算法

针对模糊C-均值聚类算法敏感于初始聚类中心及聚类收敛慢、聚类数目手动设定等缺陷,提出了基于改进蝙蝠优化自确定的模糊C-均值聚类算法。该算法是基于密度峰值综合衡量聚类中心外围数据密集程度和聚类中心间距离,自动确定聚类中心和聚类数目,以此作为改进蝙蝠算法的初始中心;在原始蝙蝠算法中引入Levy飞行特征加强算法跳出局部最优能力;使用Powell局部搜索加快算法的收敛,利用改进的蝙蝠种群进行种群寻优,并将最优蝙蝠位置作为聚类C-均值新聚类中心,进行模糊聚类,以此循环交叉迭代多次最终获得聚类结果。将基于改进蝙蝠优化自确定的模糊C-均值聚类算法与其它两种聚类算法在标准数据集上进行仿真对比,实验结果表明:与其它两种算法相比,该算法收敛速度快、误差率低。     

一种中文文本聚类算法的研究

聚类是一种无指导的分类方法,在没有预先定义好分类的情况下,将一个大的数据集合分成若干个簇,要求数据在同一个簇中相似度尽可能大,而不同簇之间相似度尽可能小。聚类作为数据挖掘的一种重要方法,现在越来越被人们所重视。目前常见的聚类方法有:基于划分的聚类方法、基于层次的聚类方法、基于局部的聚类方法和基于模型的聚类方法,吸取各类聚类算法的实质,提出一种预设阀值,逐一归类的简单聚类实现算法,并在后端对聚类结果做精确行处理,经实验验证该方法能达到一定的聚类效果。     

基于改进人工鱼群算法的机械故障聚类诊断方法

发展新的理论或方法快速准确地实现机械故障信号的聚类诊断是众多学者研究热点。由于人工鱼群优化算法具有结构简单,良好的并行性、快速性等特点,把人工鱼群优化算法引入机械故障诊断中。基于人工鱼群算法的基本原理提出了一种改进的人工鱼群追尾聚类算法,定义了相似度因子和聚类判别因子,建立了模拟人工鱼群追尾行为的机械故障聚类诊断模型,并将之应用于机械故障特征信息的聚类分析。实例分析表明了本文方法的有效性。     

面向超市货架包装的人眼检测技术

为对超市的消费者进行人眼追踪,分析消费者在货架前的购买行为,提出了基于K-means的人眼检测算法。通过分析图像序列中每一帧的静态图像,运用K-means聚类算法分割人脸区域,计算脸部尺寸,找出脸部中心点,确定眼睛范围,寻找眼睛坐标,分割眼部图像,并绘制出两只眼睛的垂直投影曲线及水平投影曲线。选取不同人种、不同背景、不同角度、不同姿态下的人物图像进行实验,以验证算法的精确性和有效性。实验结果表明:本文算法能从复杂背景下不同人物图像中准确地分割人脸区域,并精准地定位人眼位置,算法准确性高、适用性好,能够较好地实现超市环境中人眼的快速检测。     

Data Mining with Clustering Algorithms to Reduce Packaging Costs: A Case Study

Reducing package‐related cost is essential for various companies and institutions. Different packages are usually designed separately for each and every product, which results in less cost‐effective packaging systems. In this study, a data mining model with three clustering algorithms was developed to modularize a packaging system by reducing the variety of packaging sizes. The three algorithms were k‐means clustering, agglomerative hierarchical clustering and self‐organizing feature map. The package models with similar shapes and sizes were clustered automatically and replaced by one package model with a size that suited them all. The study also analysed the financial effects including the purchasing and inventory costs of the package material and the transportation cost of the packaged products. The case study was carried out at Ericsson to select the best clustering algorithm of the three and to test the effectiveness and applicability of the proposed model. The results show that the packaging system modularized by the agglomerative hierarchical clustering algorithm is more cost‐effective in this case compared with the ones modularized by the other two clustering algorithms and with the one without modularization. Copyright © 2017 John Wiley & Sons, Ltd.     

Optimal wavelength band clustering for multispectral iris recognition

This work explores the possibility of clustering spectral wavelengths based on the maximum dissimilarity of iris textures. The eventual goal is to determine how many bands of spectral wavelengths will be enough for iris multispectral fusion and to find these bands that will provide higher performance of iris multispectral recognition. A multispectral acquisition system was first designed for imaging the iris at narrow spectral bands in the range of 420 to 940 nm. Next, a set of 60 human iris images that correspond to the right and left eyes of 30 different subjects were acquired for an analysis. Finally, we determined that 3 clusters were enough to represent the 10 feature bands of spectral wavelengths using the agglomerative clustering based on two-dimensional principal component analysis. The experimental results suggest (1) the number, center, and composition of clusters of spectral wavelengths and (2) the higher performance of iris multispectral recognition based on a three wavelengths-bands fusion.     

产品声音的交互式聚类设计研究

目的 声音是产品和用户之间的一种沟通媒介,为了增进设计师对产品声音的理解、合成与设计匹配,提出一种交互式可视化产品声音数据聚类分析框架。方法 首先通过神经网络将设计师感官描述式信息与声音的特征参数进行融合嵌套;其次基于高斯混合模型来描述非线性几何分布的产品声音数据;最后设计师输入个人先验知识经验参与交互聚类。结果 基于Python的Anaconda3包开发了产品声音交互式聚类的可视化分析实验工具,得到最优化产品声音聚类结果。结论 该产品声音交互聚类可视化分析工具融合了声音技术参数和人脑听觉反应机制,在聚类过程中允许用户参与交互并融入用户的先验知识,并行视图可以实时显示数据元素的流向和判别类别的稳定性。同时,可视化分析可以帮助用户横向比较各聚类结果的异同,样本的比例分布与合理性,以期寻求最优聚类结果。     

An Adaptive Anomaly Detection Algorithm Based on CFSFDP

CFSFDP (Clustering by fast search and find of density peak) is a simple and crisp density clustering algorithm. It does not only have the advantages of density clustering algorithm, but also can find the peak of cluster automatically. However, the lack of adaptability makes it difficult to apply in intrusion detection. The new input cannot be updated in time to the existing profiles, and rebuilding profiles would waste a lot of time and computation. Therefore, an adaptive anomaly detection algorithm based on CFSFDP is proposed in this paper. By analyzing the influence of new input on center, edge and discrete points, the adaptive problem mainly focuses on processing with the generation of new cluster by new input. The improved algorithm can integrate new input into the existing clustering without changing the original profiles. Meanwhile, the improved algorithm takes the advantage of multi-core parallel computing to deal with redundant computing. A large number of experiments on intrusion detection on Android platform and KDDCUP 1999 show that the improved algorithm can update the profiles adaptively without affecting the original detection performance. Compared with the other classical algorithms, the improved algorithm based on CFSFDP has the good basic performance and more room of improvement.     

Modelling the performance of isoniazid preventive therapy for reducing tuberculosis in HIV endemic settings: the effects of network structure

Individuals living with HIV experience a much higher risk of progression from latent M. tuberculosis infection to active tuberculosis (TB) disease relative to individuals with intact immune systems. A several-month daily course of a single drug during latent infection (i.e. isoniazid preventive therapy (IPT)) has proved in clinical trials to substantially reduce an HIV-infected individual''s risk of TB disease. As a result of these findings and ongoing studies, the World Health Organization has produced strong guidelines for implementing IPT on a community-wide scale for individuals with HIV at risk of TB disease. To date, there has been limited use of IPT at a community-wide level. In this paper, we present a new co-network model for HIV and TB co-epidemics to address questions about how the population-level impact of community-wide IPT may differ from the individual-level impact of IPT offered to selected individuals. In particular, we examine how the effect of clustering of contacts within high-TB incidence communities may affect the rates of re-infection with TB and how this clustering modifies the expected population-level effects of IPT. We find that populations with clustering of respiratory contacts experience aggregation of TB cases and high numbers of re-infection events. While, encouragingly, the overall population-level effects of community-wide IPT appear to be sustained regardless of network structure, we find that in populations where these contacts are highly clustered, there is dramatic heterogeneity in the impact of IPT: in some sub-regions of these populations, TB is nearly eliminated, while in others, repeated re-infection almost completely undermines the effect of IPT. Our findings imply that as IPT programmes are brought to scale, we should expect local heterogeneity of effectiveness as a result of the complex patterns of disease transmission within communities.     

Fuzzy C-Means Algorithm Automatically Determining Optimal Number of Clusters

In clustering analysis, the key to deciding clustering quality is to determine the optimal number of clusters. At present, most clustering algorithms need to give the number of clusters in advance for clustering analysis of the samples. How to gain the correct optimal number of clusters has been an important topic of clustering validation study. By studying and analyzing the FCM algorithm in this study, an accurate and efficient algorithm used to confirm the optimal number of clusters is proposed for the defects of traditional FCM algorithm. For time and clustering accuracy problems of FCM algorithm and relevant algorithms automatically determining the optimal number of clusters, kernel function, AP algorithm and new evaluation indexes were applied to improve the confirmation of complexity and search the scope of traditional fuzzy C-means algorithm, and evaluation of clustering results. Besides, three groups of contrast experiments were designed with different datasets for verification. The results showed that the improved algorithm improves time efficiency and accuracy to certain degree.     

Information Theoretic Weighted Fuzzy Clustering Ensemble

In order to improve performance and robustness of clustering, it is proposed to generate and aggregate a number of primary clusters via clustering ensemble technique. Fuzzy clustering ensemble approaches attempt to improve the performance of fuzzy clustering tasks. However, in these approaches, cluster (or clustering) reliability has not paid much attention to. Ignoring cluster (or clustering) reliability makes these approaches weak in dealing with low-quality base clustering methods. In this paper, we have utilized cluster unreliability estimation and local weighting strategy to propose a new fuzzy clustering ensemble method which has introduced Reliability Based weighted co-association matrix Fuzzy C-Means (RBFCM), Reliability Based Graph Partitioning (RBGP) and Reliability Based Hyper Clustering (RBHC) as three new fuzzy clustering consensus functions. Our fuzzy clustering ensemble approach works based on fuzzy cluster unreliability estimation. Cluster unreliability is estimated according to an entropic criterion using the cluster labels in the entire ensemble. To do so, the new metric is defined to estimate the fuzzy cluster unreliability; then, the reliability value of any cluster is determined using a Reliability Driven Cluster Indicator (RDCI). The time complexities of RBHC and RBGP are linearly proportional with the number of data objects. Performance and robustness of the proposed method are experimentally evaluated for some benchmark datasets. The experimental results demonstrate efficiency and suitability of the proposed method.     

Fuzzy clustering based parameter clustering method in mandarin speech recognition

Abstract

In a large vocabulary continuous speech recognition system, to efficiently decrease parameter size and improve the robustness of parameter training, a parameter clustering method by fuzzy clustering is proposed. Based on the structure of the phonetic decision tree, leaf nodes are used for Gaussian clustering and root nodes or shallow leaf nodes are used for covariance sharing. Experimental results show that when the number of Gaussians is reduced by 50%, recognition accuracy only decreases by 0.55%. By combining fuzzy covariance sharing, a total of 4.16% in recognition increase is achieved over the conventional system with approximately the same parameter size.     

Subassembly identification based on grey clustering

Nowadays discarded electromechanical products are more and more common, and have done much harm to the ecological environment, human health and natural resources. In order to recycle discarded products effectively, it is necessary to disassemble them properly in an integrated consideration of economic returns and environmental protection. Therefore Disassembly Process Planning has become a key part in Environmentally Conscious Design. Because there may be a combination explosion when the disassembly process of a product with a large number of parts is planned, subassembly identification is often adopted to divide the product into some reasonable subassemblies. This paper uses a method of grey clustering based on grey system theory to perform subassembly identification. The clustered objects are part pairs with adjacency relation in a product, and the clustering indices consist of energy consumption of disassembly, disassembly time, disassemblable direction and diameter of part pair. The indices can be obtained by detailed estimate or direct input from a CAD system via secondary development. After five grey clusters are set up, their whitening weight functions are presented in detail. Several other key problems in subassembly identification based on grey clustering are also expounded, such as obtaining the nondimensional matrix of sample values, determining the weight of clustering index relative to grey cluster. A heat-sealing machine with 80 components is selected as an example to validate the method of subassembly identification based on grey clustering. The identification result of the example is feasible according to experiences, and at the same time it satisfies the requirement of Disassembly Process Planning.