Chaotic particle swarm optimization for data clustering

Data clustering is a popular analysis tool for data statistics in several fields, including includes pattern recognition, data mining, machine learning, image analysis and bioinformatics, in which the information to be analyzed can be of any distribution in size and shape. Clustering is effective as a technique for discerning the structure of and unraveling the complex relationship between massive amounts of data. An improved technique which combines chaotic map particle swarm optimization with an acceleration strategy is proposed, since results of one of the most used clustering algorithm, K-means can be jeopardized by improper choices made in the initializing stage. Accelerated chaotic particle swarm optimization (ACPSO) searches through arbitrary data sets for appropriate cluster centers and can effectively and efficiently find better solutions. Comparisons of the clustering performance are obtained from tests conducted on six experimental data sets; the algorithms compared with ACPSO includes PSO, CPSO, K-PSO, NM-PSO, K-NM-PSO and K-means clustering. Results of the robust performance from ACPSO indicate that this method an ideal alternative for solving data clustering problem.     

基于多种群协同微粒群优化的流数据聚类算法

针对流数据的实时、有序和维数高等特点, 提出一种基于多种群协同微粒群优化的流数据聚类算法. 该算法利用变量分而治之的思想, 多个种群协同优化多个类中心, 进而求出问题完整的类中心集合. 给出一种类中心变化趋势的预估策略, 以快速追踪环境变化. 为防止多个子微粒群同时优化一个类中心, 提出一种相似子微粒群的合并策略. 最后将所提出的算法用于多个数据集, 实验结果验证了算法的有效性.

     

Cooperative bare-bone particle swarm optimization for data clustering

Cooperative coevolution (CC) was used to improve the performance of evolutionary algorithms (EAs) on complex optimization problems in a divide-and-conquer way. In this paper, we show that the CC framework can be very helpful to improve the performance of particle swarm optimization (PSO) on clustering high-dimensional datasets. Based on CC framework, the original partitional clustering problem is first decomposed to several subproblems, each of which is then evolved by an optimizer independently. We employ a very simple but efficient optimization algorithm, namely bare-bone particle swarm optimization (BPSO), as the optimizer to solve each subproblem cooperatively. In addition, we design a new centroid-based encoding schema for each particle and apply the Chernoff bounds to decide a proper population size. The experimental results on synthetic and real-life datasets illustrate the effectiveness and efficiency of the BPSO and CC framework. The comparisons show the proposed algorithm significantly outperforms five EA-based clustering algorithms, i.e., PSO, SRPSO, ACO, ABC and DE, and K-means on most of the datasets.     

基于K-均值聚类粒子群优化算法的组合测试数据生成

在解决组合测试中的测试数据集生成问题时,粒子群优化算法(PSO)在待测数据量增加达到一定程度以后,出现迭代次数增加、收敛速度减慢的缺点。针对该问题,提出了一种应用于组合测试数据集生成问题的基于K-均值聚类的粒子群优化算法。通过对测试数据集合进行聚类分区域,增强测试数据集的多态性,从而对粒子群优化算法进行改进,增加各个区域内粒子之间的影响力。典型案例实验表明该方法在保证覆盖度的情况下具有一定的优势和特点。     

粒子群聚类算法综述

聚类分析是数据挖掘的重要技术之一,它能够通过无监督的学习过程发现隐藏的模式,具有独立发现知识的能力。对现有文献中基于粒子群优化算法的聚类分析技术作了全面的介绍,对几种主要的粒子群聚类算法的基本原理及其特点进行了总结,并分析比较了它们的优点和不足,概述了粒子群聚类算法的常见应用领域;最后探讨了粒子群聚类算法进一步的研究方向。     

Automated clustering of trajectory data using a particle swarm optimization

Clustering trajectory data discovers and visualizes available structure in movement patterns of mobile objects and has numerous potential applications in traffic control, urban planning, astronomy, and animal science. In this paper, an automated technique for clustering trajectory data using a Particle Swarm Optimization (PSO) approach has been proposed, and Dynamic Time Warping (DTW) distance as one of the most commonly-used distance measures for trajectory data is considered. The proposed technique is able to find (near) optimal number of clusters as well as (near) optimal cluster centers during the clustering process. To reduce the dimensionality of the search space and improve the performance of the proposed method (in terms of a certain performance index), a Discrete Cosine Transform (DCT) representation of cluster centers is considered. The proposed method is able to admit various cluster validity indexes as objective function for optimization. Experimental results over both synthetic and real-world datasets indicate the superiority of the proposed technique to fuzzy C-means, fuzzy K-medoids, and two evolutionary-based clustering techniques proposed in the literature.     

Particle swarm optimization with selective particle regeneration for data clustering

This paper presents selective regeneration particle swarm optimization (SRPSO), a novel algorithm developed based on particle swarm optimization (PSO). It contains two new features, unbalanced parameter setting and particle regeneration operation. The unbalanced parameter setting enables fast convergence of the algorithm and the particle regeneration operation allows the search to escape from local optima and explore for better solutions. This algorithm is applied to data clustering problems for performance evaluation and a hybrid algorithm (KSRPSO) of K-means clustering method and SRPSO is developed. In the conducted numerical experiments, SRPSO and KSRPSO are compared to the original PSO algorithm, K-means, as well as, other methods proposed by other studies. The results demonstrate that SRPSO and KSRPSO are efficient, accurate, and robust methods for data clustering problems.     

多样性引导的QPSO基因表达数据聚类算法

针对基于粒子群优化的聚类算法容易陷入局部最优值的缺点,提出将量子行为粒子群优化应用于基因表达数据的聚类分析问题中。在新的聚类算法中采用了对粒子群的多样性控制,以提高算法的全局收敛性能;此外还在新算法中引入了类似于K均值聚类的操作步骤,用以提高算法整体的收敛速度。选择Rand指数和Silhouette指数作为聚类评价标准,对5个人工和实际的基因表达数据集合进行聚类实验分析表明,新算法和基于粒子群优化的聚类算法相比,具有较快的收敛速度,粒子多样性的控制能有效改善算法的全局收敛性能。和其他一些常用的聚类算法比较,也能够获得更好的聚类评价,聚类效果更好。     

Hybridization strategies for continuous ant colony optimization and particle swarm optimization applied to data clustering

Ant colony optimization (ACO) and particle swarm optimization (PSO) are two popular algorithms in swarm intelligence. Recently, a continuous ACO named ACOR was developed to solve the continuous optimization problems. This study incorporated ACOR with PSO to improve the search ability, investigating four types of hybridization as follows: (1) sequence approach, (2) parallel approach, (3) sequence approach with an enlarged pheromone-particle table, and (4) global best exchange. These hybrid systems were applied to data clustering. The experimental results utilizing public UCI datasets show that the performances of the proposed hybrid systems are superior compared to those of the K-mean, standalone PSO, and standalone ACOR. Among the four strategies of hybridization, the sequence approach with the enlarged pheromone table is superior to the other approaches because the enlarged pheromone table diversifies the generation of new solutions of ACOR and PSO, which prevents traps into the local optimum.     

混合型粒子群优化算法研究

为了改进粒子群算法的性能,提出了融合其他算法优点的混合型粒子群算法。对三种主流的混合粒子群优化算法(基因粒子群、免疫粒子群、混沌粒子群)分别从混合目的、混合方式、实现步骤、算法优化性能等多个方面进行了研究,给出了这三种混合粒子群算法的优缺点及适用范围。     

一种新的粒子群优化聚类方法

针对K-均值聚类方法受初始聚类中心影响,容易陷入局部最优解的问题。提出了一种新的粒子群优化聚类方法,该聚类方法采用改进的交叉、变异算子,使群体粒子保持品种的多样性和优良性,减小随机初始聚类中心的影响,同时结合粒子群优化算法,增加粒子群的全局搜索能力。实验结果表明,提出的方法在稳定性和分类准确率上都有所提高。     

Rough particle swarm optimization and its applications in data mining

This paper proposes a novel particle swarm optimization algorithm, rough particle swarm optimization algorithm (RPSOA), based on the notion of rough patterns that use rough values defined with upper and lower intervals that represent a range or set of values. In this paper, various operators and evaluation measures that can be used in RPSOA have been described and efficiently utilized in data mining applications, especially in automatic mining of numeric association rules which is a hard problem.     

基于改进粒子群优化的无标记数据鲁棒聚类算法

已有的聚类算法大多仅考虑单一的目标,导致对某些形状的数据集性能较弱,对此提出一种基于改进粒子群优化的无标记数据鲁棒聚类算法。优化阶段:首先,采用多目标粒子群优化的经典形式生成聚类解集合;然后,使用K-means算法生成随机分布的初始化种群,并为其分配随机初始化的速度;最终,采用MaxiMin策略确定帕累托最优解。决策阶段：测量帕累托解集与理想解的距离,将距离最短的帕累托解作为最终聚类解。对比实验结果表明,本算法对不同形状的数据集均可获得较优的类簇数量,对目标问题的复杂度具有较好的鲁棒性。     

基于PSO的模糊K-Prototypes聚类

模糊K-Prototypes(FKP)算法能够对包含数值属性和分类属性相混合的数据集进行有效聚类,但是存在对初始值敏感、容易陷入局部极小值的问题.为了克服该缺点,提出了一种基于粒子群优化(PSO)算法和FKP算法的混合聚类算法,先利用PSO算法确定FKP的初始聚类中心,再将PSO聚类结果作为后续FKP算法的初始值.实验结果表明,新算法具有良好的收敛性和稳定性,聚类效果优于单一使用FKP算法.     

一种改进的基于粒子群的聚类算法

针对K-means对初始聚类中心敏感和易陷入局部最优的缺点,提出了一种改进的基于粒子群的聚类算法.该算法结合基于密度和最大最小距离法来确定初始聚类中心,解决K-means对初始值敏感的问题;利用粒子群算法全局寻优能力强的优点,避免K-means陷入局部最优.通过对样本集各维属性的规范化处理,惯性权值采用凹函数递减,计算相异度矩阵,引入用群体适应度方差,进一步优化混合算法.实验结果表明,该算法具有更高的准确率和更强的收敛能力.     

A review of particle swarm optimization and its applications in Solar Photovoltaic system

Particle swarm optimization is a stochastic optimization, evolutionary and simulating algorithm derived from human behaviour and animal behaviour as well. Special property of particle swarm optimization is that it can be operated in continuous real number space directly, does not use gradient of an objective function similar to other algorithms. Particle swarm optimization has few parameters to adjust, is easy to implement and has special characteristic of memory. Paper presents extensive review of literature available on concept, development and modification of Particle swarm optimization. This paper is structured as first concept and development of PSO is discussed then modification with inertia weight and constriction factor is discussed. Issues related to parameter tuning, dynamic environments, stagnation, and hybridization are also discussed, including a brief review of selected works on particle swarm optimization, followed by application of PSO in Solar Photovoltaics.     

基于拓扑结构与粒子变异改进的粒子群优化算法

为使粒子群优化算法(PSO)优化过程的多样性与收敛性得到合理解决,以提高算法优化性能,基于种群拓扑结构与粒子变异提出两种粒子群改进算法RSMPSO和RVMPSO.改进算法将具有信息定向流动的闭环拓扑结构与星型拓扑结构或四边形拓扑结构相结合,促使粒子在前期寻优过程中具有较高的多样性,保证搜索的广度,而在后期满足粒子群的整体收敛性,保证寻优的精度.同时,将布谷鸟搜索算法(CS)中的偏好随机游走变异策略引入改进算法中,增强粒子跳出局部最优的能力.对标准测试函数的仿真实验表明,所改进的PSO算法与其他6个对比算法相比不仅操作简单,优化精度高,而且在算法收敛性及稳健性方面都有着更出色的表现.     

Dynamic clustering using combinatorial particle swarm optimization

Combinatorial Particle Swarm Optimization (CPSO) is a relatively recent technique for solving combinatorial optimization problems. CPSO has been used in different applications, e.g., partitional clustering and project scheduling problems, and it has shown a very good performance. In partitional clustering problem, CPSO needs to determine the number of clusters in advance. However, in many clustering problems, the correct number of clusters is unknown, and it is usually impossible to estimate. In this paper, an improved version, called CPSOII, is proposed as a dynamic clustering algorithm, which automatically finds the best number of clusters and simultaneously categorizes data objects. CPSOII uses a renumbering procedure as a preprocessing step and several extended PSO operators to increase population diversity and remove redundant particles. Using the renumbering procedure increases the diversity of population, speed of convergence and quality of solutions. For performance evaluation, we have examined CPSOII using both artificial and real data. Experimental results show that CPSOII is very effective, robust and can solve clustering problems successfully with both known and unknown number of clusters. Comparing the obtained results from CPSOII with CPSO and other clustering techniques such as KCPSO, CGA and K-means reveals that CPSOII yields promising results. For example, it improves 9.26 % of the value of DBI criterion for Hepato data set.