Search

Evolutionary algorithm (EA) incorporating with k-means local search operator represents an important approach for cluster analysis. In the existing EA approach, however, the k-means operators are usually directly employed on the individuals and generally applied with fixed intensity as well as frequency during evolution, which could significantly limit their performance. In this paper, we first introduce a hybrid EA based clustering framework such that the frequency and intensity of k-means operator could be arbitrarily configured during evolution. Then, an adaptive strategy is devised to dynamically set its frequency and intensity according to the feedback of evolution. Further, we develop an opposite search strategy to implement the proposed adaptive k-means operation, thus appropriately exploring the search space. By incorporating the above two strategies, a memetic algorithm with adaptive and opposite k-means operation is finally proposed for data clustering. The performance of the proposed method has been evaluated on a series of data sets and compared with relevant algorithms. Experimental results indicate that our proposed algorithm is generally able to deliver superior performance and outperform related methods. [ABSTRACT FROM AUTHOR]

Abstract Clustering analysis is to classify elements into categories based on their similarity. Clustering by fast search and find of density peaks (CFSFDP) has been proven to be an effective and novel algorithm, which identifies the centers of clusters with density maxima. However, the performance of CFSFDP is quite sensitive to the estimation of densities, that is exactly the selection of the cutoff distance (d c). In a conventional way, the selection of d c is based on subjective experience. It meets difficulties in finding an appropriate d c , especially for detecting nonspherical clusters, because CFSFDP cannot perform well when there are more than one density peak for one cluster. Besides, another barrier of applying CFSFDP is that manual interaction is always required for making an effective selection of cluster centers. In this paper, a new density-based clustering algorithm, clustering by defining and merging candidates of cluster centers via independence and affinity (CDMC-IA), is proposed. With its strategy, an appropriate value of cutoff distance d c can be well suggested and the robustness of the method itself is enhanced. Moreover, CDMC-IA introduces a new quantity independence to sort and select cluster centers, instead of human based selection from decision graph. Another quantity affinity is also introduced, which well handles multiple density peaks existing in one cluster and is able to assign each data point to the its targeted cluster. The performance of applying conventional clustering methods to benchmark datasets will be compared with the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Nonlinear clustering has attracted an increasing amount of attention recently. In this paper, we propose a new nonlinear clustering method based on crowd movement and selection (CCMS). Different from most of the existing clustering methods that concentrate on cluster centers, our method focuses on the data points themselves and the data distribution of their neighborhood. Based on this novel idea, some useful rules are designed to transform the original nonlinearly separable datasets into linearly separable datasets. Finally, a new clustering phase is designed to partition the transformed data. Extensive experiments have been conducted to evaluate the effectiveness of the proposed CCMS method. [ABSTRACT FROM AUTHOR]

Automatic Vehicles Counting and Recognizing (AVCR) is a very challenging topic in transport engineering having important implications for the modern transport policies. Implementing a computer-assisted AVCR in the most vital districts of a country provides a large amount of measurements which are statistically processed and analyzed, the purpose of which is to optimize the decision-making of traffic operation, pavement design, and transportation planning. Since, the advent of computer vision technology, video-based surveillance of road vehicles has become a key component in developing autonomous intelligent transportation systems. In this context, this paper proposes a Pattern Recognition system which employs an unsupervised clustering algorithm with the objective of detecting, counting and recognizing a number of dynamic objects crossing a roadway. This strategy defines a virtual sensor, whose aim is similar to that of an inductive-loop in a traditional mechanism, i.e. to extract from the traffic video streaming a number of signals containing anarchic information about the road traffic. Then, the set of signals is filtered with the aim of conserving only motion’s significant patterns. Resulted data are subsequently processed by a statistical analysis technique so as to estimate and try to recognize a number of clusters corresponding to vehicles. Finite mixture models fitted by the EM algorithm are used to assess such clusters, which provides important information about the traffic such as the instantaneous number of vehicles, their weights, velocities and intervehicular distances. [ABSTRACT FROM AUTHOR]

Abstract: An unsupervised image segmentation method for natural images is proposed in this paper. We assume that texture features in natural images are distributed as a mixture of Gaussians. In order to cluster the extracted feature vectors, we modify a clustering algorithm based on Bayesian Ying–Yang (BYY) harmony learning theory with Dirichlet-Normal-Wishart prior. This algorithm can determine the number of components automatically during the clustering procedure, as long as we give a large enough initial component number. Our works in this paper have presented a complete pipeline of clustering-based image segmentation including feature extraction, robust feature clustering and methodological effective post processing. The experiments reported in this paper demonstrate that the proposed method is efficient (in terms of visual evaluation and quantitative performance measures) and performs competitively compared to the existing state-of-the-art segmentation methods. [Copyright &y& Elsevier]

Multi-view clustering algorithms have shown promising performance in various applications over the last few decades. Most of them, however, do not adequately take noises and correlation among multiple views into account, which may degrade the clustering performance. In this paper, we propose a novel multi-view clustering method to address these issues. In specific, we construct a low-rank consensus matrix and a sparse error matrix from each similarity matrix corresponding to each view. Furthermore, a matrix-induced regularization term is incorporated to reduce the redundancy and enhance the diversity among different views. The augmented Lagrangian multiplier algorithm is adopted to solve the resultant optimization problem. Comprehensive experiments are conducted to verify the effectiveness of the proposed algorithm. Results demonstrate that our algorithm outperforms several state-of-the-art ones on both synthetic and benchmark data sets. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new constrained clustering algorithm, named Constrained Community Clustering (C 3 ). It can utilize both must-link and cannot-link constraints that specify the pairs of data that belong to the same or different clusters. Instead of directly enforcing the pairwise constraints on the constrained data, C 3 first builds constrained communities around each constrained data, and then exert pairwise constraints on the constrained communities. Therefore, C 3 can not only extend the influence of pairwise constraints to the surrounding unconstrained data, but also uncover the underlying sub-structures of the clusters. The promising experimental results on the real-world text documents, handwritten digits, alphabetic characters, face recognition, and community discovery illustrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the cluster synchronization for linearly coupled networks with constant time delay by pinning periodically intermittent controllers. The network topology can be directed. The time delay is assumed to be less than the control width. At first, we give some criteria for cluster synchronization under constant pinning control strategy. Furthermore, by applying the adaptive approach, we design a centralized adaptive algorithm on the intermittent control gain, and also prove its validity rigorously. Finally, numerical simulations are given to demonstrate the correctness of obtained theoretical results. [ABSTRACT FROM AUTHOR]

Abstract: Extreme learning machine (ELM), used for the “generalized” single-hidden-layer feedforward networks (SLFNs), is a unified learning platform that can use a widespread type of feature mappings. In theory, ELM can approximate any target continuous function and classify any disjoint regions; in application, many experiment results have already demonstrated the good performance of ELM. In view of the good properties of the ELM feature mapping, the clustering problem using ELM feature mapping techniques is studied in this paper. Experiments show that the proposed ELM kMeans algorithm and ELM NMF (nonnegative matrix factorization) clustering can get better clustering results than the corresponding Mercer kernel based methods and the traditional algorithms using the original data. Moreover, the proposed methods have the advantage of being more convenient to implementation and computation, as the ELM feature mapping is much simpler than the Mercer kernel function based feature mapping methods. [Copyright &y& Elsevier]

Abstract: In recent years, extensive research efforts have been dedicated to automatic news content analysis. In this paper, we propose a novel algorithm for anchorperson detection in news video sequences. In this method, the raw news videos are firstly split into shots by a four-threshold method, and the key frames are extracted from each shot. After that, the anchorperson detection is conducted from these key frames by using a clustering-based method based on a statistical distance of Pearson's correlation coefficient. To evaluate the effectiveness of the proposed method, we have conducted experiments on 10 news sequences. In these experiments, the proposed scheme achieves a recall of 0.96 and a precision of 0.97 for anchorperson detection. [Copyright &y& Elsevier]

Abstract: Many real-world networks have a structure of overlapping cohesive groups. In order to uncover this structure several clustering algorithms have been developed. In this paper, we focus on the evaluation of these algorithms. Quality measures are commonly used for this purpose and provide a means to assess the quality of a derived cluster structure. Currently, there are too few measures for graph clusterings with overlaps available that would enable a meaningful evaluation, even though many well studied crisp quality measures exist. In order to expand the pool of overlapping measures we propose three methods to adapt existing crisp quality measures so that they can handle graph overlaps appropriately. We demonstrate our methods on the well known measures Density, Modularity and Conductance. We also propose an enhancement of an existing modularity measure for networks with overlapping structure. We analyse the proposed quality indices using experiments on artificial graphs that possess overlapping structure. For this evaluation, we apply a graph generation model to create clustered graphs with overlaps that are similar to real-world networks, i.e., their node degree and cluster size distribution follow a power law. [Copyright &y& Elsevier]

Abstract: This paper proposes a color lip segmentation method with unknown true segment number. Firstly, we build up a multi-layer hierarchical model, in which each layer corresponds to one segment cluster. Subsequently, a Markov random field derived from this model is obtained such that the segmentation problem is formulated as a labeling optimization problem under the maximum a posteriori Markov random field (MAP-MRF) framework. Suppose the pre-assigned number of segment clusters may over-estimate the ground truth, whereby leading to the over-segmentation. We present a rival penalized iterative algorithm capable of performing segment clusters and over-segmentation elimination simultaneously. Based upon this algorithm, we propose a lip segmentation and tracking scheme, featuring the robust performance to the estimate of the number of segment clusters. Experimental results show the efficacy of the proposed method in comparison with the existing counterparts. [Copyright &y& Elsevier]

Abstract: This paper presents optimization techniques that substantially speed up the Growing Neural Gas (GNG) algorithm. The GNG is an example of the Self-Organizing Map algorithm that is a subject of an intensive research interest in recent years as it is used in various practical applications. However, a poor time performance on large scale problems requiring neural networks with a high amount of nodes can be a limiting factor for further applications (e.g., cluster analysis, classification, 3-D reconstruction) or a wider usage. We propose two optimization techniques that are aimed exclusively on an efficient implementation of the GNG algorithm internal structure rather than on a modification of the original algorithm. The proposed optimizations preserve all properties of the GNG algorithm and enable to use it on large scale problems with reduced computational requirements in several orders of magnitude. [Copyright &y& Elsevier]

Abstract: This paper considers the problem of mixing matrix estimation in underdetermined blind source separation (UBSS). We propose a simple and effective detection algorithm which detects the time-frequency (TF) points occupied by only a single source for each source. The detection algorithm identifies the single source points by comparing the normalized real and imaginary parts of the TF coefficient vectors of the mixed signals, which is simpler than previously reported algorithms. Then we propose a modified similarity-based robust clustering method (MSCM) to estimate the number of sources and the mixing matrix using these detected single source points. Experimental results show the efficiency of the proposed algorithm, especially in the cases where the number of sources is unknown. [Copyright &y& Elsevier]

Abstract: The quantum clustering (QC) algorithm suffers from the issues of getting stuck in local extremes and computational bottleneck when handling large-size image segmentation. By embedding a potential evolution formula into affinity function calculation of multi-elitist immune clonal optimization, and updating the cluster center based on the distance matrix, the multi-elitist immune clonal quantum clustering algorithm (ME-ICQC) is proposed in this paper. In the proposed framework, elitist population is composed of the individuals with high affinity, which is considered to play dominant roles in the evolutionary process. It can help to find the global optimal solution or near-optimal solution for most tested tasks. The diversity of population can be well maintained by general subgroup evolution of ME-ICQC. These different functions are implemented by the dissimilar mutation strategies or crossover operators. The bi-group exchanges the information of excellence antibodies using the hypercube co-evolution operation. Compared with existing algorithms, the ME-ICQC achieves an improved clustering accuracy with more stable convergence, but it is not significantly better than other optimization techniques combined with QC. Also, the experimental results also show that our algorithm performs well on multi-class, parameters-sensitive and large-size datasets. [Copyright &y& Elsevier]

Abstract: Semi-supervised classification has become an active topic recently and a number of algorithms, such as Self-training, have been proposed to improve the performance of supervised classification using unlabeled data. In this paper, we propose a semi-supervised learning framework which combines clustering and classification. Our motivation is that clustering analysis is a powerful knowledge-discovery tool and it may reveal the underlying data space structure from unlabeled data. In our framework, semi-supervised clustering is integrated into Self-training classification to help train a better classifier. In particular, the semi-supervised fuzzy c-means algorithm and support vector machines are used for clustering and classification, respectively. Experimental results on artificial and real datasets demonstrate the advantages of the proposed framework. [Copyright &y& Elsevier]

Abstract: This paper provides a novel Exceptional Object Analysis for Finding Rare Environmental Events (EOAFREE). The major contribution of our EOAFREE method is that it proposes a general Improved Exceptional Object Analysis based on Noises (IEOAN) algorithm to efficiently detect and rank exceptional objects. Our IEOAN algorithm is more general than already known outlier detection algorithms to find exceptional objects that may be not on the border; and experimental study shows that our IEOAN algorithm is far more efficient than directly recursively using already known clustering algorithms that may not force every data instance to belong to a cluster to detect rare events. Another contribution is that it provides an approach to preprocess heterogeneous real world data through exploring domain knowledge, based on which it defines changes instead of the water data value itself as the input of the IEOAN algorithm to remove the geographical differences between any two sites and the temporal differences between any two years. The effectiveness of our EOAFREE method is demonstrated by a real world application – that is, to detect water pollution events from the water quality datasets of 93 sites distributed in 10 river basins in Victoria, Australia between 1975 and 2010. [Copyright &y& Elsevier]

Abstract: Support vector machines (SVMs) are a widely used technique for classification, clustering and data analysis. While efficient algorithms for training SVM are available, dealing with large datasets makes training and classification a computationally challenging problem. In this paper we exploit modern processor architectures to improve the training speed of , a well known implementation of the sequential minimal optimization algorithm. We describe , an optimized version of which takes advantage of the peculiar architecture of the Cell Broadband Engine. We assess the performance of on real-world training problems, and we show how this optimization is particularly effective on large, dense datasets. [Copyright &y& Elsevier]

Abstract: Selecting correct dimensions is very important to subspace clustering and is a challenging issue. This paper studies semi-supervised approach to the problem. In this setting, limited domain knowledge in the form of space level pair-wise constraints, i.e., must-links and cannot-links, are available. We propose a semi-supervised subspace clustering (S3C) algorithm that exploits constraint inconsistence for dimension selection. Our algorithm firstly correlates globally inconsistent constraints to dimensions in which they are consistent, then unites constraints with common correlating dimensions, and finally forms the subspaces according to the constraint unions. Experimental results show that S3C is superior to the typical unsupervised subspace clustering algorithm FINDIT, and the other constraint based semi-supervised subspace clustering algorithm SC-MINER. [Copyright &y& Elsevier]

Abstract: The concept of preserving locality information in dimensionality reduction and semi-supervised classification have been very popular recently. In this paper, we attempt to use locality sensitive weight for clustering, where the neighborhood structure information between objects are transformed into weights of objects. We develop two novel locality sensitive C-means algorithms, i.e. Locality-weighted Hard C-Means (LHCM) and Locality-weighted Fuzzy C-Means (LFCM), following the standard C-Means and fuzzy C-means, respectively. In addition, two semi-supervised extensions of LFCM are proposed to better use some given partial supervision information in data objects. Experimental results on both artificial and real datasets validate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we propose a modified Markov clustering algorithm for efficient and accurate clustering of large protein sequence databases, based on previously evaluated sequence similarity criteria. The proposed modification consists in an exponentially decreasing inflation rate, which aims at helping the quick creation of the hard structure of clusters by using a strong inflation in the beginning, and at producing fine partitions with a weaker inflation thereafter. The algorithm, which was tested and validated using the whole SCOP95 database, or randomly selected 10–50% sections, generally converges within 12–14 iteration cycles and provides clusters of high quality. Furthermore, a novel generalized formula for the inflation operation is given, and an efficient matrix symmetrization technique is presented, in order to improve the partition quality with relatively low amount of extra computations. Finally, an extra speedup is achieved via excluding isolated proteins from further processing. The proposed method performs better than previous solutions, from the point of view of partition quality, and computational load as well. [ABSTRACT FROM AUTHOR]

Abstract: Mass spectrometry (MS)-based proteomics has been established as a standard way for biomarker discovery and early detection of disease from the proteome level. However, the data generated by MS technology are noisy, have a lot of redundancy, and most importantly have low sample-to-dimension ratio. Therefore, successful analysis of MS data heavily relies on the algorithmic and data mining techniques used to extract information. In this paper, we briefly discuss some of the commonly used algorithms applied to mass-to-charge (m/z) feature selection, and propose a k-means clustering based hybrid algorithm to address the high-dimension and high-correlation issues associated with this task. Our k-means clustering based hybrid algorithm incorporates the advantages of both filter- and wrapper-based feature selection algorithms. A special iterative procedure is introduced to overcome the instability of k-means clustering and genetic algorithm. By comparing the proposed hybrid system with several popular m/z feature selection algorithms using 10 different classifiers, we show that the proposed algorithm is able to select m/z features with lower correlation while achieving higher sample classification accuracies. The m/z feature selection results also indicate that the proposed hybrid algorithm is very stable despite its stochastic nature. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a spike sorting method using a simplified feature set with a nonparametric clustering algorithm. The proposed feature extraction algorithm is efficient and has been implemented with a custom integrated circuit chip interfaced with the PC. The proposed clustering algorithm performs nonparametric clustering. It defines an energy function to characterize the compactness of the data and proves that the clustering procedure converges. Through iterations, the data points collapse into well formed clusters and the associated energy approaches zero. By claiming these isolated clusters, neural spikes are classified. [Copyright &y& Elsevier]

Abstract: In this paper, we present an algorithm for cluster analysis that integrates aspects from cluster ensemble and multi-objective clustering. The algorithm is based on a Pareto-based multi-objective genetic algorithm, with a special crossover operator, which uses clustering validation measures as objective functions. The algorithm proposed can deal with data sets presenting different types of clusters, without the need of expertise in cluster analysis. Its result is a concise set of partitions representing alternative trade-offs among the objective functions. We compare the results obtained with our algorithm, in the context of gene expression data sets, to those achieved with multi-objective clustering with automatic K-determination (MOCK), the algorithm most closely related to ours. [Copyright &y& Elsevier]

Abstract: A very important category of clustering methods is hierarchical clustering. There are considerable research efforts which have been focused on algorithm-level improvements of the hierarchical clustering process. In this paper, our goal is to provide a systematic understanding of hierarchical clustering from a data distribution perspective. Specifically, we investigate the issues about how the “true” cluster distribution can make impact on the clustering performance, and what is the relationship between hierarchical clustering schemes and validation measures with respect to different data distributions. To this end, we provide an organized study to illustrate these issues. Indeed, one of our key findings reveals that hierarchical clustering tends to produce clusters with high variation on cluster sizes regardless of “true” cluster distributions. Also, our results show that F-measure, an external clustering validation measure, has bias towards hierarchical clustering algorithms which tend to increase the variation on cluster sizes. Viewed in light of this, we propose , the normalized version of the F-measure, to solve the cluster validation problem for hierarchical clustering. Experimental results show that is indeed more suitable than the unnormalized F-measure in evaluating the hierarchical clustering results across data sets with different data distributions. [Copyright &y& Elsevier]

Abstract: Identifying community structure in complex networks is closely related to clustering of data in other areas without an underlying network structure. In this paper, we propose a nonnegative matrix factorization (NMF)-based method for finding community structure. We first evaluate several similarity measures, such as diffusion kernel similarity, shortest path based similarity on several widely well-studied networks. Then, we apply NMF with diffusion kernel similarity to a large biological network, which demonstrates that our method can find biologically meaningful functional modules. Comparison with other algorithms also indicates the good performance of our method. [Copyright &y& Elsevier]

Abstract: Complexity pursuit is a recently developed algorithm using the gradient descent for separating interesting components from time series. It is an extension of projection pursuit to time series data and the method is closely related to blind separation of time-dependent source signals and independent component analysis (ICA). In this paper, a fixed-point algorithm for complexity pursuit is introduced. The fixed-point algorithm inherits the advantages of the well-known FastICA algorithm in ICA, which is very simple, converges fast, and does not need choose any learning step sizes. [Copyright &y& Elsevier]