Integration of growing self-organizing map and continuous genetic algorithm for grading lithium-ion battery cells

This study attempts to employ growing self-organizing map (GSOM) algorithm and continuous genetic algorithm (CGA)-based SOM (CGASOM) to improve the performance of SOM neural network (SOMnn). The proposed GSOM + CGASOM approach for SOMnn is consisted of two stages. The first stage determines the SOMnn topology using GSOM algorithm while the weights are fine-tuned by using CGASOM algorithm in the second stage. The proposed CGASOM algorithm is compared with other two clustering algorithms using four benchmark data sets, Iris, Wine, Vowel, and Glass. The simulation results indicate that CGASOM algorithm is able to find the better solution. Additionally, the proposed approach has been also employed to grade Lithium-ion cells and characterize the quality inspection rules. The results can assist the battery manufacturers to improve the quality and decrease the costs of battery design and manufacturing.     

Accelerating k-medoid-based algorithms through metric access methods

Scalable data mining algorithms have become crucial to efficiently support KDD processes on large databases. In this paper, we address the task of scaling up k-medoid-based algorithms through the utilization of metric access methods, allowing clustering algorithms to be executed by database management systems in a fraction of the time usually required by the traditional approaches. We also present an optimization strategy that can be applied as an additional step of the proposed algorithm in order to achieve better clustering solutions. Experimental results based on several datasets, including synthetic and real ones, show that the proposed algorithm can reduce the number of distance calculations by a factor of more than three thousand times when compared to existing algorithms, while producing clusters of equivalent quality.     

一种新的基于隐Markov模型的分层时间序列聚类算法

针对传统的基于隐Markov模型(HMM)的聚类算法在时间序列聚类的不足,提出了一种新的基于HMM的分层时间序列聚类算法HBHCTS,旨在提高聚类质量,同时对聚类结果给出类的表示. HBHCTS算法应用HMM对时间序列进行建模,并按照“最相似”的原则得到序列所对应的初始模型集,进而对这些初始模型合并更新及迭代得到聚类结果.实验中主要研究了聚类正确率与序列长度及模型距离的关系,结果表明HBHCTS算法比传统的基于HMM的聚类算法准确性高.     

一种基于分簇蚁群策略的无线传感器网络路由算法

如何最大化地延长网络的生存时间是无线传感器（WSN）网络研究的核心问题.基于分簇策略,提出一种能量有效的路由算法（EEA）.该算法利用分簇原理减少了参与寻找最优路径的节点数,从而降低了系统的能耗.同时设计一种改进的最优路径评价标准,该标准兼顾了传输路径上各节点的剩余能量和最优路径上总的能量消耗.仿真结果表明,与其他蚁群策略的路由算法（如：基于蚁群算法的路由算法（ARA）和EEAWSN）相比,该算法能在寻找最优路径时避开剩余能量少的节点,使最优路径上各节点的能量呈整体性衰落,从而沿长了网络的寿命.     

云计算下基于改进遗传算法的聚类融合算法

针对无监督聚类缺少数据分类等先验信息、基聚类的准确性受聚类算法影响以及一般聚类融合算法空间复杂度高的问题,提出一种基于改进遗传算法的聚类融合算法（CEIGA）;同时针对传统聚类融合算法已经不能满足大规模数据处理对于时间的要求的问题,提出一种云计算下使用Hadoop平台的基于改进遗传算法的并行聚类融合算法（PCEIGA）。首先,基聚类生成机制产生的基聚类划分在完成簇标签转化后进行基因编码作为遗传算法的初始种群。其次,通过改进遗传算法的选择算子,保证基聚类的多样性;再根据改进的选择算子对染色体进行交叉和变异操作并使用精英策略得到下一代种群,保证基聚类的准确性。如此循环,使聚类融合最终结果达到全局最优,提高算法准确度。通过设计两个MapReduce过程并加入Combine过程减少节点通信,提高算法运行效率。最后,在UCI数据集上比较了CEIGA、PCEIGA和四个先进的聚类融合算法。实验结果表明,与先进的聚类融合算法相比,CEIGA性能最好;而PCEIGA能在不影响聚类结果准确度的前提下明显降低算法运行时间,提高算法效率。     

Clustering-based algorithms for single-hidden-layer sigmoid perceptron

Gradient-descent type supervised learning is the most commonly used algorithm for design of the standard sigmoid perceptron (SP). However, it is computationally expensive (slow) and has the local-minima problem. Moody and Darken (1989) proposed an input-clustering based hierarchical algorithm for fast learning in networks of locally tuned neurons in the context of radial basis function networks. We propose and analyze input clustering (IC) and input-output clustering (IOC)-based algorithms for fast learning in networks of globally tuned neurons in the context of the SP. It is shown that "localizing' the input layer weights of the SP by the IC and the IOC minimizes an upper bound to the SP output error. The proposed algorithms could possibly be used also to initialize the SP weights for the conventional gradient-descent learning. Simulation results offer that the SPs designed by the IC and the IOC yield comparable performance in comparison with its radial basis function network counterparts.     

基于群体智慧的簇连接聚类集成算法

利用群体智慧原理,将多个相互独立的聚类算法的结果进行聚合,将显著提高聚类结果的准确性.基于群体智慧的簇连接聚类集成算法,首先使用群体智慧理论的独立性、分散性、多样性原则引导个体聚类结果的生成,然后提出基于连接三元组的聚类集成算法对个体聚类结果进行分组聚合,将分组聚合的结果再次进行聚合得到最终的聚类结果.该算法的优点包括:1)通过簇的分组和权重调整,避免了对基聚类生成的簇进行选择,有利于充分利用已生成簇的信息;2)采用连接三元组算法计算数据之间的相似性,可以充分挖掘数据点之间的关系.对不同数据集的实验研究表明：该算法相对传统的集成聚类算法以及群体智慧与机器学习相结合的集成聚类算法,可以进一步提高集成聚类结果的准确性.     

基于聚类和改进共生演算法的云任务调度策略

针对云计算环境中一些基于服务质量（QoS）调度算法存在寻优速度慢、调度成本与用户满意度不均衡的问题,提出了一种基于聚类和改进共生演算法的云任务调度策略。首先将任务和资源进行模糊聚类并对资源进行重排序放置,依据属性相似度对任务进行指导分配,减小对资源的选择范围;然后依据交叉和旋转学习机制改进共生演算法,提升算法的搜索能力;最后通过加权求和方式构造驱动模型,均衡调度代价与系统性能间关系。通过不同任务量的云任务调度仿真实验,表明该算法相比改进遗传算法、混合粒子群遗传算法和离散共生演算法,有效减少了进化代数,降低了调度成本并提升了用户满意度,是一种可行有效的任务调度算法。     

Self-Organizing-Map Based Clustering Using a Local Clustering Validity Index

Classical clustering methods, such as partitioning and hierarchical clustering algorithms, often fail to deliver satisfactory results, given clusters of arbitrary shapes. Motivated by a clustering validity index based on inter-cluster and intra-cluster density, we propose that the clustering validity index be used not only globally to find optimal partitions of input data, but also locally to determine which two neighboring clusters are to be merged in a hierarchical clustering of Self-Organizing Map (SOM). A new two-level SOM-based clustering algorithm using the clustering validity index is also proposed. Experimental results on synthetic and real data sets demonstrate that the proposed clustering algorithm is able to cluster data in a better way than classical clustering algorithms on an SOM.     

基于向量空间模型的文本聚类算法

文本聚类是聚类的一个重要研究分支,是聚类方法在文本处理领域的应用。该文探讨了基于向量空间模型的文本聚类方法,提出了一种文本聚类的改进算法——LP算法。同时,基于语料库的实际聚类效果,就维度确定、特征选择等方面提出优化方案。实验证明,LP算法有效地减少了聚类所消耗的时间,实用性和灵活性都较高。     

基于差分隐私保护的Stacking集成聚类算法研究

针对差分隐私保护下单一聚类算法准确性和安全性不足的问题,提出了一种基于差分隐私保护的Stacking集成聚类算法。使用Stacking集成多种异质聚类算法,将K-means聚类、Birch层次聚类、谱聚类和混合高斯聚类作为初级聚类算法,结合轮廓系数对初级聚类算法产生的聚类结果加权并入原始数据,将K-means算法作为次级聚类算法对扩展后的数据集进行聚类分析。其中,针对原始数据和初级聚类算法的聚类结果分别提出自适应的ε函数确定隐私预算,为不同敏感度的数据分配不同程度的Laplace噪声。理论分析和实验结果均表明,与单一聚类算法相比,该算法满足ε-差分隐私保护的同时有效提高了聚类准确性,实现了隐私保护与数据可用性的高度平衡。     

矢量聚类及其在稀疏分量分析中的应用

针对传统聚类分析不能有效处理矢量数据聚类的问题,提出矢量聚类算法。该算法以点到矢量的距离最小化为分类依据,所得类簇中心为一矢量。根据稀疏信号的分布特性,用矢量聚类方法估计系统的混合矩阵,再利用估计的混合矩阵分离混合信号,从而得到稀疏信源的估计,简化了传统的混合信号分离过程。实验结果表明该矢量聚类方法能比传统的标量聚类方法更有效地估计矢量数据的中心,能在稀疏的处理域中很好地分离出稀疏信源。     

Improved cat swarm optimization algorithm for solving global optimization problems and its application to clustering

This paper presents a cat swarm optimization (CSO) algorithm for solving global optimization problems. In CSO algorithm, some modifications are incorporated to improve its performance and balance between global and local search. In tracing mode of the CSO algorithm, a new search equation is proposed to guide the search toward a global optimal solution. A local search method is incorporated to improve the quality of solution and overcome the local optima problem. The proposed algorithm is named as Improved CSO (ICSO) and the performance of the ICSO algorithm is tested on twelve benchmark test functions. These test functions are widely used to evaluate the performance of new optimization algorithms. The experimental results confirm that the proposed algorithm gives better results than the other algorithms. In addition, the proposed ICSO algorithm is also applied for solving the clustering problems. The performance of the ICSO algorithm is evaluated on five datasets taken from the UCI repository. The simulation results show that ICSO-based clustering algorithm gives better performance than other existing clustering algorithms.     

Particle swarm optimization-based algorithms for TSP and generalized TSP

A novel particle swarm optimization (PSO)-based algorithm for the traveling salesman problem (TSP) is presented. An uncertain searching strategy and a crossover eliminated technique are used to accelerate the convergence speed. Compared with the existing algorithms for solving TSP using swarm intelligence, it has been shown that the size of the solved problems could be increased by using the proposed algorithm.Another PSO-based algorithm is proposed and applied to solve the generalized traveling salesman problem by employing the generalized chromosome. Two local search techniques are used to speed up the convergence. Numerical results show the effectiveness of the proposed algorithms.     

Combining multiple clusterings using evidence accumulation

We explore the idea of evidence accumulation (EAC) for combining the results of multiple clusterings. First, a clustering ensemble - a set of object partitions, is produced. Given a data set (n objects or patterns in d dimensions), different ways of producing data partitions are: 1) applying different clustering algorithms and 2) applying the same clustering algorithm with different values of parameters or initializations. Further, combinations of different data representations (feature spaces) and clustering algorithms can also provide a multitude of significantly different data partitionings. We propose a simple framework for extracting a consistent clustering, given the various partitions in a clustering ensemble. According to the EAC concept, each partition is viewed as an independent evidence of data organization, individual data partitions being combined, based on a voting mechanism, to generate a new n /spl times/ n similarity matrix between the n patterns. The final data partition of the n patterns is obtained by applying a hierarchical agglomerative clustering algorithm on this matrix. We have developed a theoretical framework for the analysis of the proposed clustering combination strategy and its evaluation, based on the concept of mutual information between data partitions. Stability of the results is evaluated using bootstrapping techniques. A detailed discussion of an evidence accumulation-based clustering algorithm, using a split and merge strategy based on the k-means clustering algorithm, is presented. Experimental results of the proposed method on several synthetic and real data sets are compared with other combination strategies, and with individual clustering results produced by well-known clustering algorithms.     

基于改进粒子群优化的移动界面模式聚类算法

聚类是一种非常有效的信息分析方法。针对现有基于粒子群优化的模糊C均值(Fuzzy C-means,FCM)聚类算法的聚类效果不佳的问题,提出一种基于改进粒子群优化的模糊C均值聚类算法,并将该聚类算法应用到移动界面模式的聚类中。首先,利用直觉模糊熵的几何解释和约束构造合理的直觉模糊熵;然后,在粒子群优化中使用直觉模糊熵判断种群的多样性程度,并引入混沌反向学习策略来提高全局搜索能力;最后,为了增强聚类算法的非线性处理能力,在聚类算法中加入高斯核函数,并将该聚类算法应用到移动界面模式的聚类中。移动界面模式聚类的实验表明,与现有聚类算法相比,文中所提聚类算法具有更好的聚类效果。     

Cuckoo and krill herd‐based k‐means++ hybrid algorithms for clustering

Clustering algorithms can be optimized using nature‐inspired techniques. Many algorithms inspired by nature, namely, firefly algorithm, ant colony optimization algorithm, and so forth, have improved clustering results. k‐means is a popular clustering technique but has limitations of local optima, which have been overcome using its various hybrids. k‐means++ is a hybrid k‐means clustering algorithm that gives the procedure to initialize centre of the clusters. In the proposed work, hybrids of nature‐inspired techniques using cuckoo and krill herd algorithm are implemented on k‐means++ algorithm to enhance cluster quality and generate optimized clusters. The designed algorithms are implemented, and the results are compared with their counterparts. Performance parameters such as accuracy, f‐measure, error rate, standard deviation, CPU time, cluster quality check, and so forth are used to measure the clustering capabilities of these algorithms. The results indicate the high performance of newly designed algorithms.     

Centroid neural network for unsupervised competitive learning

An unsupervised competitive learning algorithm based on the classical k-means clustering algorithm is proposed. The proposed learning algorithm called the centroid neural network (CNN) estimates centroids of the related cluster groups in training date. This paper also explains algorithmic relationships among the CNN and some of the conventional unsupervised competitive learning algorithms including Kohonen's self-organizing map and Kosko's differential competitive learning algorithm. The CNN algorithm requires neither a predetermined schedule for learning coefficient nor a total number of iterations for clustering. The simulation results on clustering problems and image compression problems show that CNN converges much faster than conventional algorithms with compatible clustering quality while other algorithms may give unstable results depending on the initial values of the learning coefficient and the total number of iterations.     

Adaptive fuzzy c-means clustering algorithm for a radial basis function network

This paper presents a new recursive hybrid algorithm for training a radial basis function (RBF) network. The algorithm consists of a proposed clustering algorithm to position the RBF centres and the Givens least-squares algorithm to estimate the weights. This paper begins with a discussion about the problems of clustering in positioning RBF centres. Then a new clustering algorithm called adaptive fuzzy c-means clustering algorithm is proposed to reduce the problems. The capability of the proposed algorithm was tested to model three data sets: one simulated and two real data sets. It was found that the algorithm provided good performance. The performance of the algorithm was then compared with adaptive k-means, non-adaptive k-means and non-adaptive fuzzy cmeans clustering algorithms. Overall performance of the RBF network that used the proposed clustering algorithm was found to be much better than those that used other clustering algorithms. Simulation results also revealed that the algorithm was not sensitive to initial centres.