Search

"Clustering" the significance and application of this technique is spread over various fields. Clustering is an unsupervised process in data mining, that is why the proper evaluation of the results and measuring the compactness and separability of the clusters are important issues. The procedure of evaluating the results of a clustering algorithm is known as cluster validity measure. Different types of indexes are used to solve different types of problems and indices selection depends on the kind of available data. This paper first proposes Canonical PSO based K-means clustering algorithm and also analyses some important clustering indices (intercluster, intracluster) and then evaluates the effects of those indices on real-time air pollution database, wholesale customer, wine, and vehicle datasets usingtypical K-means, Canonical PSO based K-means, simple PSO based K-means, DBSCAN, and Hierarchical clustering algorithms. This paper also describes the nature of the clusters and finally compares the performances of these clustering algorithms according to the validity assessment. It also defines which algorithm will be more desirable among all these algorithms to make proper compact clusters on this particular real life datasets. It actually deals with the behaviour of these clustering algorithms with respect to validation indexes and represents their results of evaluation in terms of mathematical and graphical forms. [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]

The main influencing factors of the clustering effect of the k-means algorithm are the selection of the initial clustering center and the distance measurement between the sample points. The traditional k-mean algorithm uses Euclidean distance to measure the distance between sample points, thus it suffers from low differentiation of attributes between sample points and is prone to local optimal solutions. For this feature, this paper proposes an improved k-means algorithm based on evidence distance. Firstly, the attribute values of sample points are modelled as the basic probability assignment (BPA) of sample points. Then, the traditional Euclidean distance is replaced by the evidence distance for measuring the distance between sample points, and finally k-means clustering is carried out using UCI data. Experimental comparisons are made with the traditional k-means algorithm, the k-means algorithm based on the aggregation distance parameter, and the Gaussian mixture model. The experimental results show that the improved k-means algorithm based on evidence distance proposed in this paper has a better clustering effect and the convergence of the algorithm is also better. [ABSTRACT FROM AUTHOR]

This very special, 27.0 - 1 volume of Fundamenta Informaticae is dedicated to Andrzej Skowron on the occasion of his 70th birthday. The contributions are on an invitational basis, but they have been reviewed according to the usual standards of the journal. The editors want to thank all the contributors and reviewers for their great work. Without it, this volume would be much less special.It is very hard, if even possible, to describe Andrzej Skowron in a finite collection of words. He is such an unique personality and scientist. To get some understanding what he is like it may help to read the accounts included in this preface. These accounts are provided by persons who interact with Andrzej for years on both professional and personal grounds: Roman Świniarski with family, Janusz Kacprzyk, Damian Niwiński, and Stanisław Matwin.When we started to circulate the idea of this special volume among Andrzej's extended scientific family, we have met an enthusiastic response. So enthusiastic in fact, that we were initially a little bit overwhelmed. Everybody wanted to be on board. We managed to convince several groups of researchers to join forces and write one comprehensive, yet compact article instead of several. In this way, it was possible to fit the material in one, thirty-six-piece volume.The thirty-six articles that make this special volume of Fundamenta Informaticae span over a very wide range of topics. They reflect Andrzej Skowron's activities as a researcher and a scholar as well as his influence on a broad scientific community. In order to make this volume more approachable we have ordered the papers with respect to general areas their represent. To do that we have used a methodology that has quite bit to do with results of one of the research projects Andrzej was recently involved in. Namely, we have manually performed a semantic clustering of our contribution pool. As a result the papers have been organized into four disjoint clusters (thematic groups) that we briefly introduce below.First of the clusters gathers articles that correspond to some fundamental directions in recent and past research of Andrzej Skowron. The reader will find in this cluster papers representing such areas as: foundations of rough sets, logical aspects of both rough and related models of computation, foundational issues relating to logical aspects of non-classical computational systems, formal and computational aspects of inference systems, and nature-inspired computational systems. In this cluster we have contributions by: Mihir K. Chakraborty and Mohua Banerjee; Anna Gomolińska and Marcin Wolski; Ewa Orłowska and Ivo Düntsch; Yiyu Yao; Lech Polkowski and Maria Semeniuk-Polkowska; Ludwik Czaja; Grzegorz Rozenberg, Gheorghe Paun, and Mario J. Perez-Jimenez; Alberto Pettorossi, Fabio Fioravanti, Maurizio Proietti, and Valerio Senni; Andrzej Szałas and Patrick Doherty.The second cluster contains papers that describe research results in topics associated with discovering, representing and making use of knowledge learned form data. In particular, several of approaches described in these papers make use of reducts and decision rules. The contributions made by Andrzej Skowron to methods and algorithms for representation, reduction, and simplification of information retrieved from data are instrumental here. There are also papers that deal with approximations and approximation spaces, an area pioneered by Andrzej. Members of this cluster are papers by: Mikhail Moshkov, Talha Amin, Igor Chikalov, and Beata Zielosko; Roman Słowiński, Salvatore Greco, and Izabela Szczęch; Jerzy Grzymała-Busse and Patrick G. Clark; Wojciech Ziarko and Xugunag Chen; Shusaku Tsumoto and Shoji Hirano; Zbigniew Raś and Hakim Touati; Hui Wang and Ivo Düntsch; Zbigniew Suraj and Krzysztof Pancerz; Jan Komorowski, Marcin Kruczyk, Nicholas Baltzer, Jakub Mieczkowski, Michał Dramiński, and Jacek Koronacki.The third group of contributions relates to another large area of research on which Andrzej Skowron left his mark. The papers represent studies on fundamentals and applications of granular approach to knowledge-based systems as well as investigations into underlying notions of closeness, similarity, and nearness. They also address challenges associated with construction and usage of granular systems - in particular multi-layered, hierarchical ones - in knowledge discovery and decision support. Papers by the following authors make this group: Sankar K. Pal, Jayanta Kumar Pal, and Shubhra Sankar Ray; Marzena Kryszkiewicz; Bożena Kostek and Andrzej Kaczmarek; Alicja Wakulicz-Deja, Agnieszka Nowak-Brzezińska, and Małgorzata Przybyła-Kasperek; James Peters and Sheela Ramanna; Hung Son Nguyen, Sinh Hoa Nguyen, Tuan Trung Nguyen, and Marcin Szczuka; Guoyin Wang, Yuchao Liu, Deyi Li, and Wen He; Witold Pedrycz; Tsau Young Lin, Yong Liu, and Wenliang Huang.The fourth and final group contains nine papers that represent a little wider range of topics. Among them are papers that deal with data processing in general, including research related to database technology as well as search techniques. There are papers in this cluster that deal with data and knowledge representation and navigation. There are also described various aspects of data mining including those that make use of multiagent approach as well as methods based on processing of visual information. In this cluster the reader will find contributions by: Jarosław Stepaniuk, Maciej Kopczyński, and Tomasz Grzes; Dominik Ślęzak, Piotr Synak, Arkadiusz Wojna, and Jakub Wróblewski; Henryk Rybiński and Jacek Lewandowski; Jiming Liu, Hao Lan Zhang, and Yanchun Zhang; Jan G. Bazan, Andrzej Jankowski, and Sylwia Buregwa-Czuma; Wojciech Froelich, Rafał Deja, and Grażyna Deja; Piotr Wasilewski and Adam Krasuski; Ning Zhong, Linchan Qin, Shengfu Lu, and Mi Li; Andrzej Czyżewski and Karol Lisowski.The editors of this special volume would like to wish a Happy Birthday to Andrzej and hope that he will like this little gift.Dominik ŚlęzakHung Son NguyenMarcin SzczukaOctober 2013 [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we describe an algorithm devised to be used for the extraction of patterns existing in fingerprints. The algorithm takes as input data a data set of molecules represented by its corresponding fingerprints, and generates a set of disjoint patterns also consisting of binary arrays satisfying to subsets, not necessarily disjoint, of the input data set. The algorithm has been developed in Java, allowing its integration in free and proprietary computational chemistry software due to acceptable performance. Fingerprint patterns extracted by the algorithm from molecule data sets are organized in a hierarchical structure where the nodes at each level can be used as a cluster for the classification of the data set. In this paper, we analyze the usefulness of this tree structure and we describe the advantages in the analysis of data sets regarding MCS-based tree structure. Moreover, the use of fingerprint patterns is compared with other representational spaces in the building of QSAR models, showing better results. [Copyright &y& Elsevier]

Purpose – This paper aims to analyze the relationship among measures of resource and service usage and other features of academic libraries in the USA and Canada. Design/methodology/approach – Through the use of a self-organizing map, academic library data were clustered and visualized. Analysis of the library data was conducted through the computation of a "library performance metric" that was applied to the resulting map. Findings – Two areas of high-performing academic libraries emerged on the map. One area included libraries with large numbers of resources, while another area included libraries that had low resources but gave greater numbers of presentations to groups, offered greater numbers of public service hours, and had greater numbers of staffed service points. Research limitations/implications – The metrics chosen as a measure of library performance offer only a partial picture of how libraries are being used. Future research might involve the use of a self-organizing map to cluster library data within certain parameters and the identification of high-performing libraries within these clusters. Practical implications – This study suggests that libraries can improve their performance not only by acquiring greater resources but also by putting greater emphasis on the services that they provide to their users. Originality/value – This paper demonstrates how a self-organizing map can be used in the analysis of large data sets to facilitate library comparisons. [ABSTRACT FROM AUTHOR]

Detection of an environmental phenomenon, e.g. air pollution and oil spills, occurs when a group of sensors continuously produces similar readings (i.e. data streams) over a period of time. Thus, detection of environmental phenomena is basically a process of clustering the sensors' data streams, which commonly involves the processing of hundreds and maybe thousands of data streams in real time. Since the sensor network environment is wireless, energy conservation of the sensors would be the main concern. Thus in this paper, we propose an efficient and energy friendly distributed scheme to detect phenomena in a wireless sensor network (WSN). To achieve fast response, the proposed algorithms reduce the dimensionality of the streams. Then, each stream is represented by a point in a multi-dimensional grid. The algorithm uses a grid-based clustering technique to detect clusters of similar stream values. The processing of the algorithm is distributed among different elements of the WSN in a hierarchical topology for more energy efficiency. The paper shows the feasibility of the proposed fully distributed scheme by comparing it with three other WSN schemes in terms of clustering accuracy and energy consumption. [ABSTRACT FROM PUBLISHER]

This paper considers three crucial issues in processing scaled down image, the representation of partial image, similarity measure and domain adaptation. Two Gaussian mixture model based algorithms are proposed to effectively preserve image details and avoids image degradation. Multiple partial images are clustered separately through Gaussian mixture model clustering with a scan and select procedure to enhance the inclusion of small image details. The local image features, represented by maximum likelihood estimates of the mixture components, are classified by using the modified Bayes factor (MBF) as a similarity measure. The detection of novel local features from MBF will suggest domain adaptation, which is changing the number of components of the Gaussian mixture model. The performance of the proposed algorithms are evaluated with simulated data and real images and it is shown to perform much better than existing Gaussian mixture model based algorithms in reproducing images with higher structural similarity index. [ABSTRACT FROM AUTHOR]

Aim The objective of this paper is to identify attribute patterns of influential individuals in intensive care units using unsupervised cluster analysis. Background Despite the acknowledgement that culture of an organisation is critical to improving patient safety, specific methods to shift culture have not been explicitly identified. Methods A social network analysis survey was conducted and an unsupervised cluster analysis was used. Results A total of 100 surveys were gathered. Unsupervised cluster analysis was used to group individuals with similar dimensions highlighting three general genres of influencers: well-rounded, knowledge and relational. Conclusions Culture is created locally by individual influencers. Cluster analysis is an effective way to identify common characteristics among members of an intensive care unit team that are noted as highly influential by their peers. To change culture, identifying and then integrating the influencers in intervention development and dissemination may create more sustainable and effective culture change. Additional studies are ongoing to test the effectiveness of utilising these influencers to disseminate patient safety interventions. Implications for nursing management This study offers an approach that can be helpful in both identifying and understanding influential team members and may be an important aspect of developing methods to change organisational culture. [ABSTRACT FROM AUTHOR]

In recent years, metaheuristic algorithms have been widely used in solving clustering problems because of their good performance and application effects. Krill herd algorithm (KHA) is a new effective algorithm to solve optimization problems based on the imitation of krill individual behavior, and it is proven to perform better than other swarm intelligence algorithms. However, there are some weaknesses yet. In this paper, an improved krill herd algorithm (IKHA) is studied. Modified mutation operators and updated mechanisms are applied to improve global optimization, and the proposed IKHA can overcome the weakness of KHA and performs better than KHA in optimization problems. Then, KHA and IKHA are introduced into the clustering problem. In our proposed clustering algorithm, KHA and IKHA are used to find appropriate cluster centers. Experiments were conducted on University of California Irvine (UCI) standard datasets, and the results showed that the IKHA clustering algorithm is the most effective. [ABSTRACT FROM AUTHOR]

This paper introduces a new mathematical algorithm termed Clustering Disjoint HJ-Biplot (CDBiplot), which searches for the underlying data structure in order to find the best classification of the object groups in a reduced space. To this end, disjoint factorial axes are generated, in which each variable only contributes to the formation of one factorial axis. A graphical representation of the individuals and variables is performed using the HJ-Biplot method. In order to facilitate the use of this new method within any practical context, a function in the language R has been developed. This work applies the CDBiplot to study an environmental geochemistry case involving environmental pollution in river surface sediments. The study focuses on an area close to an important mining and metallurgical site, where sediments share a similar geological origin and chemical composition. The algorithm permitted a detailed study of the geochemical interactions and performed an excellent separation of the samples. Thus, the groups obtained were formed according to a similar geological origin, location, and nature of the anthropogenic inputs based only on chemical composition data. These results allowed clear identification of the sources of pollution and the delimitation of the polluted zones. All things considered, we conclude that the proposed algorithm is a powerful tool for studying environmental geochemistry data sets, and suggest that the application of this methodology be extended to other research fields. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet and its applications, growing volumes of documents increasingly become interconnected to form large-scale document networks. Accordingly, topic modeling in a network of documents has been attracting continuous research attention. Most of the existing network-based topic models assume that topics in a document are influenced by its directly linked neighbouring documents in a document network and overlook the potential influence from indirectly linked ones. The existing work also has not carefully modeled variations of such influence among neighboring documents. Recognizing these modeling limitations, this paper introduces a novel Local Context-Aware LDA Model (LC-LDA), which is capable of observing a local context comprising a rich collection of documents that may directly or indirectly influence the topic distributions of a target document. The proposed model can also differentiate the respective influence of each document in the local context on the target document according to both structural and temporal relationships between the two documents. The proposed model is extensively evaluated through multiple document clustering and classification tasks conducted over several large-scale document sets. Evaluation results clearly and consistently demonstrate the effectiveness and superiority of the new model with respect to several state-of-the-art peer models. [ABSTRACT FROM AUTHOR]

With the progress of network technology, there are more and more digital images of the internet. But most images are not semantically marked, which makes it difficult to retrieve and use. In this paper, a new algorithm is proposed to automatically annotate images based on particle swarm optimization (PSO) and support vector clustering (SVC). The algorithm includes two stages: firstly, PSO algorithm is used to optimize SVC; secondly, the trained SVC algorithm is used to annotate the image automatically. In the experiment, three datasets are used to evaluate the algorithm, and the results show the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Document clustering can be applied in document organisation and browsing, document summarisation and classification. The identification of an appropriate representation for textual documents is extremely important for the performance of clustering or classification algorithms. Textual documents suffer from the high dimensionality and irrelevancy of text features. Besides, conventional clustering algorithms suffer from several shortcomings, such as slow convergence and sensitivity to the initial value. To tackle the problems of conventional clustering algorithms, metaheuristic algorithms are frequently applied to clustering. In this paper, an improved ant clustering algorithm is presented, where two novel heuristic methods are proposed to enhance the clustering quality of ant-based clustering. In addition, the latent Dirichlet allocation (LDA) is used to represent textual documents in a compact and efficient way. The clustering quality of the proposed ant clustering algorithm is compared to the conventional clustering algorithms using 25 text benchmarks in terms of F-measure values. The experimental results indicate that the proposed clustering scheme outperforms the compared conventional and metaheuristic clustering methods for textual documents. [ABSTRACT FROM AUTHOR]

Induced by 'big data,' 'topic modeling' has become an attractive alternative to mapping co-words in terms of co-occurrences and co-absences using network techniques. Does topic modeling provide an alternative for co-word mapping in research practices using moderately sized document collections? We return to the word/document matrix using first a single text with a strong argument ('The Leiden Manifesto') and then upscale to a sample of moderate size ( n = 687) to study the pros and cons of the two approaches in terms of the resulting possibilities for making semantic maps that can serve an argument. The results from co-word mapping (using two different routines) versus topic modeling are significantly uncorrelated. Whereas components in the co-word maps can easily be designated, the topic models provide sets of words that are very differently organized. In these samples, the topic models seem to reveal similarities other than semantic ones (e.g., linguistic ones). In other words, topic modeling does not replace co-word mapping in small and medium-sized sets; but the paper leaves open the possibility that topic modeling would work well for the semantic mapping of large sets. [ABSTRACT FROM AUTHOR]

This paper proposes an unsupervised method for analyzing speaker roles in multi-participant conversational speech. First, features for characterizing the differences of various roles are extracted from the outputs of speaker diarization. Then, an algorithm of role clustering based on the criterion of maximizing the inter-cluster distance without using any convergence threshold is proposed to obtain the number of roles and to merge the utterances belonging to the same role into one cluster. The contributions of different combinations of individual feature subsets are compared for the proposed method on the outputs from speaker diarization, and the combined feature subsets obtain higher F scores than the individual ones for clustering speaker roles. The impacts of both speaker diarization errors and feature dimensions on the performance of the proposed method are also discussed. Experiments are done on the outputs of both manual annotations and automatic speaker diarization to compare the proposed method with both the state-of-the-art clustering method and the supervised method. Evaluations show that the proposed method is superior to the previous clustering method and close to the conventional supervised method in terms of F scores under two different experimental conditions. [ABSTRACT FROM AUTHOR]

In this paper, we propose a fuzzy SV- k -modes algorithm that uses the fuzzy k -modes clustering process to cluster categorical data with set-valued attributes. In the proposed algorithm, we use Jaccard coefficient to measure the dissimilarity between two objects and represent the center of a cluster with set-valued modes. A heuristic update way of cluster prototype is developed for the fuzzy partition matrix. These extensions make the fuzzy SV- k -modes algorithm can cluster categorical data with single-valued and set-valued attributes together and the fuzzy k -modes algorithm is its special case. Experimental results on the synthetic data sets and the three real data sets from different applications have shown the efficiency and effectiveness of the fuzzy SV- k -modes algorithm. [ABSTRACT FROM AUTHOR]

By combining linear discriminant analysis and Kmeans into a coherent framework, a dimension reduction algorithm was recently proposed to select the most discriminative subspace. This algorithm utilized the clustering method to generate cluster labels and after that employed discriminant analysis to do subspace selection. However, we found that this algorithm only considers the information of global structure, and does not take into account the information of local structure. In order to overcome the shortcoming mentioned above, this paper presents a dimension reduction algorithm preserving both global and local clustering structure. Our algorithm is an unsupervised linear dimension reduction algorithm suitable for the data with cloud distribution. In the proposed algorithm, the Kmeans clustering method is adopted to generate the clustering labels for all data in the original space. And then, the obtained clustering labels are utilized to describe the global and local clustering structure. Finally, the objective function is established to preserve both the local and global clustering structure. By solving this objective function, the projection matrix and the corresponding subspace are yielded. In this way, the global and local information of the clustering structure are integrated into the process of the subspace selection, in fact, the structure discovery and the subspace selection are performed simultaneously in our algorithm. Encouraging experimental results are achieved on the artificial dataset, real-life benchmark dataset and AR face dataset. [ABSTRACT FROM AUTHOR]

Cluster validity indexes are very important tools designed for two purposes: comparing the performance of clustering algorithms and determining the number of clusters that best fits the data. These indexes are in general constructed by combining a measure of compactness and a measure of separation. A classical measure of compactness is the variance. As for separation, the distance between cluster centers is used. However, such a distance does not always reflect the quality of the partition between clusters and sometimes gives misleading results. In this paper, we propose a new cluster validity index for which Jeffrey divergence is used to measure separation between clusters. Experimental results are conducted using different types of data and comparison with widely used cluster validity indexes demonstrates the outperformance of the proposed index. [ABSTRACT FROM AUTHOR]

Clustering is a powerful unsupervised tool for sentiment analysis from text. However, the clustering results may be affected by any step of the clustering process, such as data pre-processing strategy, term weighting method in Vector Space Model and clustering algorithm. This paper presents the results of an experimental study of some common clustering techniques with respect to the task of sentiment analysis. Different from previous studies, in particular, we investigate the combination effects of these factors with a series of comprehensive experimental studies. The experimental results indicate that, first, the K-means-type clustering algorithms show clear advantages on balanced review datasets, while performing rather poorly on unbalanced datasets by considering clustering accuracy. Second, the comparatively newly designed weighting models are better than the traditional weighting models for sentiment clustering on both balanced and unbalanced datasets. Furthermore, adjective and adverb words extraction strategy can offer obvious improvements on clustering performance, while strategies of adopting stemming and stopword removal will bring negative influences on sentiment clustering. The experimental results would be valuable for both the study and usage of clustering methods in online review sentiment analysis. [ABSTRACT FROM AUTHOR]

The result of feature selection for software birthmark has a direct bearing on software recognition rate. In this paper, we apply constrained clustering to analyze the software features (SF). The within-class (homogeneous software) and between-class (heterogeneous software) distances of features are measured based on mutual information. Information gain functions and penalty functions are constructed using homogeneous and heterogeneous SF, respectively; and redundancy is measured with correlation coefficients. Then the software birthmark features with high class distinction and minimum redundancy are selected. The example of extracting and detecting framework of birthmark feature is also given. The algorithm is analyzed and compared with the similar algorithms, and it is shown the algorithm provide an effective approach for software birthmark selection and optimization. [ABSTRACT FROM PUBLISHER]

Clustering a set of objects into homogeneous groups is a fundamental operation in data mining. Recently, many attentions have been put on categorical data clustering, where data objects are made up of non-numerical attributes. For categorical data clustering the rough set based approaches such as Maximum Dependency Attribute (MDA) and Maximum Significance Attribute (MSA) has outperformed their predecessor approaches like Bi-Clustering (BC), Total Roughness (TR) and Min-Min Roughness(MMR). This paper presents the limitations and issues of MDA and MSA techniques on special type of data sets where both techniques fails to select or faces difficulty in selecting their best clustering attribute. Therefore, this analysis motivates the need to come up with better and more generalize rough set theory approach that can cope the issues with MDA and MSA. Hence, an alternative technique named Maximum Indiscernible Attribute (MIA) for clustering categorical data using rough set indiscernible relations is proposed. The novelty of the proposed approach is that, unlike other rough set theory techniques, it uses the domain knowledge of the data set. It is based on the concept of indiscernibility relation combined with a number of clusters. To show the significance of proposed approach, the effect of number of clusters on rough accuracy, purity and entropy are described in the form of propositions. Moreover, ten different data sets from previously utilized research cases and UCI repository are used for experiments. The results produced in tabular and graphical forms shows that the proposed MIA technique provides better performance in selecting the clustering attribute in terms of purity, entropy, iterations, time, accuracy and rough accuracy. [ABSTRACT FROM AUTHOR]

Community detection and analysis have attracted wide public concerns over the recent years. Meanwhile, many related algorithms in complex networks have been proposed. However, most of them concentrate on undirected and unweighted networks. Concerning the significant theoretical value and potential application foreground for directed-weighted networks, in this paper, a novel hierarchical communities detection algorithm (termed as DCBAI) has been proposed on the basis of asymmetric intimacy between nodes. Community structures are effectively detected by node clustering algorithm in directed-weighted network, and a set of optimal communities are generated. In addition, a new and asymmetric parameter is adopted to measure the intimate relationship between nodes. We make some simulation using the proposed algorithm in real-world networks and artificial networks, and the result obtained proves that the parameter can describe the direct and indirect relationships between two nodes. Eventually, comparison with similar algorithms shows that our proposed algorithm has better performance. [ABSTRACT FROM AUTHOR]

In complex networks, information regarding the nodes is usually incomplete because of the effects of interference, noise, and other factors. This results in parts of the network being blurred and some information having an unknown source. In this paper, a spectral clustering algorithm is used to identify fuzzy nodes and solve network reconstruction problems. By changing the fuzzy degree of placeholders, we achieve various degrees of credibility and accuracy for the restored network. Our approach is verified by experiments using open source datasets and simulated data. [ABSTRACT FROM AUTHOR]

Purpose The purpose of this paper is to present the results of a comparison among three different approaches for recommending learning objects (LO) inside a repository. The comparison focuses not only on prediction errors but also on the coverage of each tested configuration.Design/methodology/approach The authors compared the offline evaluation by using pure collaborative filtering (CF) algorithms with two other different combinations of pre-processed data. The first approach for pre-processing data consisted of clustering users according to their disciplines resemblance, while the second approach consisted of clustering LO according to their textual similarity regarding title and description. The three methods were compared with respect to the mean average error between predicted values and real values. Moreover, we evaluated the impact of the number of clusters and neighborhood size on the user-coverage.Findings Clustering LO has improved the prediction error measure with a small loss on user-coverage when compared to the pure CF approach. On the other hand, the approach of clustering users failed in both the error and in user-space coverage. It also became clear that the neighborhood size is the most relevant parameter to determine how large the coverage will be.Research limitations The methods proposed here were not yet evaluated in a real-world scenario, with real users opinions about the recommendations and their respective learning goals. Future work is still required to evaluate users opinions.Originality/value This research provides evidence toward new recommendation methods directed toward LO repositories. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we give some extensive benchmark results for some dynamic priority clustering algorithms for homogeneous multiprocessor environments. By dynamic priority we mean a priority function that can change with every step of the algorithm. Using dynamic priority can give us more flexibility as compared to static priority algorithms. Our objective in this paper is to compare the dynamic priority algorithms with some well known algorithms from the literature and discuss their strengths and weaknesses. For our study we have selected two recently proposed dynamic priority algorithms: CPPS (Cluster Pair Priority Scheduling algorithm) having complexity and DCCL (Dynamic Computation Communication Load scheduling algorithm) having complexity where is the number of nodes in the task graph, and is the number of edges in the task graph. We have selected a recently proposed randomized algorithm with static priority (RCCL: Randomized Computation Communication Load scheduling algorithm) and converted it into a dynamic priority algorithm: RDCC (Randomized Dynamic Computation Communication load scheduling algorithm) having complexity where a is the number of randomization steps, and b is a limit on the number of clusters formed. We have also selected three well known algorithms from literature: DSC (Dominant Sequence Clustering algorithm) having complexity , EZ (Edge Zeroing algorithm) having complexity , and LC (Linear Clustering algorithm) having complexity . We have compared these algorithms using various comparison parameters including some statistical parameters, and also using various types of task graphs including some synthetic and real task graphs. Our results show that the dynamic priority algorithms give best results for the case of random task graphs, and for the case when the number of available processors are small. [Copyright &y& Elsevier]

Abstract: Centroids are key components in many data analysis algorithms such as clustering or microaggregation. They are considered as the central value that minimises the distance to all the objects in a dataset or cluster. Methods for centroid construction are mainly devoted to datasets with numerical and categorical attributes, focusing on the numerical and distributional properties of data. Textual attributes, on the contrary, consist of term lists referring to concepts with a specific semantic content (i.e., meaning), which cannot be evaluated by means of classical numerical operators. Hence, the centroid of a dataset with textual attributes should be the term that minimises the semantic distance against the members of the set. Semantically-grounded methods aiming to construct centroids for datasets with textual attributes are scarce and, as it will be discussed in this paper, they are hampered by their limited semantic analysis of data. In this paper, we propose a method that, exploiting the knowledge provided by background ontologies (like WordNet), is able to construct the centroid of multivariate datasets described by means of textual attributes. Special efforts have been put in the minimisation of the semantic distance between the centroid and the input data. As a result, our method is able to provide optimal centroids (i.e., those that minimise the distance to all the objects in the dataset) according to the exploited background ontology and a semantic similarity measure. Our proposal has been evaluated by means of a real dataset consisting on short textual answers provided by visitors of a natural park. Results show that our centroids retain the semantic content of the input data better than related works. [Copyright &y& Elsevier]

There exist already various approaches to outlier detection, in which semisupervised methods achieve encouraging superiority due to the introduction of prior knowledge. In this paper, an adaptive feature weighted clustering-based semisupervised outlier detection strategy is proposed. This method maximizes the membership degree of a labeled normal object to the cluster it belongs to and minimizes the membership degrees of a labeled outlier to all clusters. In consideration of distinct significance of features or components in a dataset in determining an object being an inlier or outlier, each feature is adaptively assigned different weights according to the deviation degrees between this feature of all objects and that of a certain cluster prototype. A series of experiments on a synthetic dataset and several real-world datasets are implemented to verify the effectiveness and efficiency of the proposal. [ABSTRACT FROM AUTHOR]

In this paper, a novel transition process identification algorithm based on distributed model projection (DMP) is proposed for clustering nonlinear transition data and monitoring the variations in the transition process. Compared to several alternative identification methods, the DMP algorithm considers both the correlations between variables and correlations between samples. Also, a framework is proposed to combine DMP algorithm and hierarchical clustering to derive an optimal clustering results through a large amount of individual trials of the DMP algorithm. Based on the offline classification results, a transition process is divided into several sub-segments and each of them can be characterized by a stable model. Then the online identification and monitoring methods are carried out based on the sub-models established in those segments. Finally, the Tennessee Eastman (TE) benchmark process is utilized to demonstrate the performance of the proposed process identification and monitoring strategy. Compared to previous works, the proposed algorithm is shown to be superior both in identification and monitoring. [ABSTRACT FROM AUTHOR]

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]

The classification can be performed by using the decision tree approach. Previous researches on the classification using the decision tree have mostly been intended to classify text data. This paper was intended to introduce a classification application to the content-based image retrieval (CBIR) with multiattributes by using a decision tree. The attributes used were the visual features of the image, i.e. : color moments (order 1, 2 and 3), image entropy, energy and homogeneity. K-means cluster algorithm was used to categorize each attribute. The result of categorized data was then built into a decision tree by using C4.5. To show the concept in application, this research built an application with main features, i.e.: cases data input, cases list, training process and testing process to do classification. The resulting tests of 150 rontgen data showed the training data classification's truth value of 75.33% and testing data classification of 55.7%. [ABSTRACT FROM AUTHOR]

Grouping and clustering alerts for intrusion detection based on the similarity of features is referred to as structurally base alert correlation and can discover a list of attack steps. Previous researchers selected different features and data sources manually based on their knowledge and experience, which lead to the less accurate identification of attack steps and inconsistent performance of clustering accuracy. Furthermore, the existing alert correlation systems deal with a huge amount of data that contains null values, incomplete information, and irrelevant features causing the analysis of the alerts to be tedious, time-consuming and error-prone. Therefore, this paper focuses on selecting accurate and significant features of alerts that are appropriate to represent the attack steps, thus, enhancing the structural-based alert correlation model. A two-tier feature selection method is proposed to obtain the significant features. The first tier aims at ranking the subset of features based on high information gain entropy in decreasing order. The‏ second tier extends additional features with a better discriminative ability than the initially ranked features. Performance analysis results show the significance of the selected features in terms of the clustering accuracy using 2000 DARPA intrusion detection scenario-specific dataset. [ABSTRACT FROM AUTHOR]

There is always a lack of a cluster validity function and optimization strategy to find out clusters and catch the evolution trend of cluster structures on a categorical data stream. Therefore, this paper presents an optimization model for clustering categorical data streams. In the model, a cluster validity function is proposed as the objective function to evaluate the effectiveness of the clustering model while each new input data subset is flowing. It simultaneously considers the certainty of the clustering model and the continuity with the last clustering model in the clustering process. An iterative optimization algorithm is proposed to solve an optimal solution of the objective function with some constraints. Furthermore, we strictly derive a detection index for drifting concepts from the optimization model. We propose a detection method that integrates the detection index and the optimization model to catch the evolution trend of cluster structures on a categorical data stream. The new method can effectively avoid ignoring the effect of the clustering validity on the detection result. Finally, using the experimental studies on several real data sets, we illustrate the effectiveness of the proposed algorithm in clustering categorical data streams, compared with existing data-streams clustering algorithms. [ABSTRACT FROM AUTHOR]

Saving of fuel cost can be done through proper commitment of available generating units. This paper presents a novel technique to solve the problem of unit commitment through sorting of units into different clusters based on Imperialistic Competition Algorithm (ICA). This sorting is implemented in order to decrease the overall operating cost and to assure the various constraints that involve minimum up/down. The technique of unit commitment is a significant assignment in the normal working of power systems which can actually be represented as a large scale minimization problem that involves non linear mixed integers. A new technique employing the concept of cluster algorithm called as additive and divisive hierarchical clustering has been used based on a new technique called as Imperialistic Competition Algorithm in order to carry out the technique of unit commitment. Proposed methodology involves two individual algorithms. Additive cluster algorithm has been employed while the load is increasing while divisive cluster algorithm has been used when the load is decreasing. The technique that has been developed has been tested on system with generating units in range of 10–100 and the superior performance of the technique has been reported through simulation results. [ABSTRACT FROM AUTHOR]

A GPGPU is very important technology and a research hotspot for cloud computing. We pay close attention to its energy consumption and performance. In this paper, a static performance analysis model of GPU, SKE (Single Kernel Estimate), is set up to analyze the completion time of the kernel function on a GPU to find the optimal parallel solution to different tasks in a specific GPU device and the granularity size of the thread-block division, thus enabling the fastest execution speed of the kernel function. The deviation between the completion time calculated by SKE and the real execution time of the kernel is no more than 13%. On this basis, we calculate the completion time for each sub-GPU task and seek the critical path of the GPU cluster, and propose a GPU cluster scheduling algorithm, BCS (Based on Critical-path-Scheduling). The algorithm regulates the frequency of non-critical nodes, mainly through dynamic voltage and frequency scaling (DVFS) technology, and achieves the goal of reducing the energy consumption of GPU nodes without affecting the final completion time of the cluster. The evaluation results show that BCS reduces energy consumption by a maximum of 9.4%, compared to DRS. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a link density clustering (LDC) method for overlapping community detection based on density peaks. We firstly use an extended cosine link distance metric to reflect the relationship of links. Then we introduce a clustering algorithm with fast search for solving the link clustering (LC) problem by density peaks with box plot strategy to determine the cluster centers automatically. Finally, we acquire both the link communities and the node communities. Our algorithm is compared with other representative algorithms through substantial experiments on real-world networks. The experimental results show that our algorithm consistently outperforms other algorithms in terms of modularity and coverage. [ABSTRACT FROM AUTHOR]

In network analysis, a community can be defined as a group of nodes of a network (or clusters) that are densely interconnected with each other but only sparsely connected with the rest of the network. Several algorithms have been used to obtain a convenient partition allowing extracting the communities in a given network, based on their topology and, possibly, the weights of links. These weights usually represent specific characteristics for example: distance, reactance, reliability. Even if the optimum partitions could be derived, there are uncertainties associated to the network parameters that affect the network partition. In this paper, the authors extend a previous approach for assessing the effects of weight uncertainties on community structures and propose a global approach for (a) understanding the global similarity among the partitions; (b) analyzing the robustness of the communities derived without uncertainty; and (c) quantifying the robustness of the inter-community links. To this aim an uncertainty propagation analysis, based on the Monte Carlo technique is proposed. The approach is illustrated through analyzing the topology of an electric power system. [ABSTRACT FROM AUTHOR]

In this paper, an algorithm is proposed to detect one-mode community structures in bipartite networks, and to deduce which one-mode community structures are weighted. After analyzing the topological properties in bipartite networks, bipartite clustering triangular is introduced. First, bipartite networks are projected into two weighted one-mode networks by bipartite clustering triangular. Then all the maximal sub-graphs from two one-mode weighted networks are extracted and the maximal sub-graphs are merged together using a weighted clustering threshold. In addition, the proposed algorithm successfully finds overlapping vertices between one-mode communities. Experimental results using some real-world network data shows that the performance of the proposed algorithm is satisfactory. [ABSTRACT FROM AUTHOR]

Explicit criteria, such as the STOPP/START criteria, are increasingly used both in clinical practice and in research to identify potentially inappropriate prescribing in older people. In an article on the STOPP/START criteria version 2, O'Mahony et al. have pointed out the advantages of developing computerised criteria. Both clinical decision support systems to support healthcare professionals and software applications to automatically detect inappropriate prescribing in research studies can be developed. In the process of developing such tools, difficulties may occur. In the context of a research study, we have developed an algorithm to automatically apply STOPP/START criteria version 2 to our research database. We comment in this paper on different kinds of difficulties encountered and make suggestions that could be taken into account when developing the next version of the criteria. [ABSTRACT FROM AUTHOR]

In order to avoid the false alarm and alarm failure caused by sensor malfunction or failure, it has been critical to diagnose the fault and analyze the failure of the sensor measuring system in major infrastructures. Based on the real time monitoring of bridges and the study on the correlation probability distribution between multisensors adopted in the fault diagnosis system, a clustering algorithm based on k-medoid is proposed, by dividing sensors of the same type into k clusters. Meanwhile, the value of k is optimized by a specially designed evaluation function. Along with the further study of the correlation of sensors within the same cluster, this paper presents the definition and corresponding calculation algorithm of the sensor’s validation. The algorithm is applied to the analysis of the sensor data from an actual health monitoring system. The result reveals that the algorithm can not only accurately measure the failure degree and orientate the malfunction in time domain but also quantitatively evaluate the performance of sensors and eliminate error of diagnosis caused by the failure of the reference sensor. [ABSTRACT FROM AUTHOR]

Incomplete data imputation plays an important role in big data analysis and smart computing. Existing algorithms are of low efficiency and effectiveness in imputing incomplete high-dimensional data. The paper proposes an incomplete high-dimensional data imputation algorithm based on feature selection and cluster analysis (IHDIFC), which works in three steps. First, a hierarchical clustering-based feature subset selection algorithm is designed to reduce the dimensions of the data set. Second, a parallel $$k$$ -means algorithm based on partial distance is derived to cluster the selected data subset efficiently. Finally, the data objects in the same cluster with the target are utilized to estimate its missing feature values. Extensive experiments are carried out to compare IHDIFC to two representative missing data imputation algorithms, namely FIMUS and DMI. The results demonstrate that the proposed algorithm achieves better imputation accuracy and takes significantly less time than other algorithms for imputing high-dimensional data. [ABSTRACT FROM AUTHOR]

With the increasing of available protein-protein interaction (PPI) data, many computational methods have been explored to identify protein complexes from PPI networks. Majority of algorithms employ the feature of local neighbors to detect local dense subgraphs which correspond to protein complexes. Those approaches neglect the inherent core-attachment structure of protein complexes, which to an extent affect the protein complexes of prediction accuracy. In this paper, we propose a new algorithm for predicting protein complexes, deriving from the framework of the core-attachment. The proposed method first obtains the triangular structures of the core of protein complexes, name as cells, in which the edge-clustering coefficient is used. And then the cells are expanded to protein complex cores based on the closeness. Finally, the attachments are added to their corresponding cores to form the final protein complexes. The experimental results on two yeast PPI data show our method outperform the existing algorithms in terms of matched protein complexes and biological significance using two benchmark data sets. [ABSTRACT FROM AUTHOR]

The general clustering algorithms do not guarantee optimality because of the hardness of the problem. Polynomial-time methods can find the clustering corresponding to the exact optimum only in special cases. For example, the dynamic programming algorithm can solve the one-dimensional clustering problem, i.e., when the items to be clustered can be characterised by only one scalar number. Optimal one-dimensional clustering is provided by package Ckmeans.1d.dp in R. The paper shows a possible generalisation of the method implemented in this package to multidimensional data: the dynamic programming method can be applied to find the optimum clustering of vectors when only subsequent items may form a cluster. Sequential data are common in various fields including telecommunication, bioinformatics, marketing, transportation etc. The proposed algorithm can determine the optima for a range of cluster numbers in order to support the case when the number of clusters is not known in advance. [ABSTRACT FROM AUTHOR]

It is well known that, in the presence of outliers, the single linkage algorithm generally fails to identify clusters. In this paper, we construct a new version of this algorithm, less sensitive to outliers, and study both its theoretical properties and its practical behavior. In particular, we provide an oracle-type inequality which guarantees that our procedure recovers clusters with high probability under mild assumptions on the distribution of the outliers. Using this inequality, we prove the consistency of our method and exhibit rates of convergence in various situations. The performance of this approach is also assessed through simulation studies. A thorough comparison with several classical clustering algorithms on simulated data is presented. [ABSTRACT FROM AUTHOR]

Abstract: In cluster analysis, one of the most challenging and difficult problems is the determination of the number of clusters in a data set, which is a basic input parameter for most clustering algorithms. To solve this problem, many algorithms have been proposed for either numerical or categorical data sets. However, these algorithms are not very effective for a mixed data set containing both numerical attributes and categorical attributes. To overcome this deficiency, a generalized mechanism is presented in this paper by integrating Rényi entropy and complement entropy together. The mechanism is able to uniformly characterize within-cluster entropy and between-cluster entropy and to identify the worst cluster in a mixed data set. In order to evaluate the clustering results for mixed data, an effective cluster validity index is also defined in this paper. Furthermore, by introducing a new dissimilarity measure into the k-prototypes algorithm, we develop an algorithm to determine the number of clusters in a mixed data set. The performance of the algorithm has been studied on several synthetic and real world data sets. The comparisons with other clustering algorithms show that the proposed algorithm is more effective in detecting the optimal number of clusters and generates better clustering results. [Copyright &y& Elsevier]

New instruments are beginning to reveal the chemical complexity of atmospheric aerosol particles. Exploitation of the plethora of information being made accessible through aerosol particle spectrometry and other techniques requires new strategies for data interpretation. This paper demonstrates and evaluates several analysis methods used to exploit this single-particle high-time-resolution data. In the first part of this study, Standard Reference Material (SRM) particulate matter samples were analyzed by an Aerosol Time-of-Flight Mass Spectrometer (ATOFMS) in order to evaluate the use of a modified, logarithm based, method of clustering mass spectra using the Adaptive Resonance Theory (ART-2a) algorithm. In the second part of this study, data obtained from the ATOFMS during the four seasons of 2007 were interpreted using a variety of approaches so as to elucidate the nature and sources of particles influencing the great lakes region of North America. This dataset is believed to represent the longest time-span of single-particle data ever analyzed in a study of this nature. These mass spectra were clustered into 21 different particle types using the supervised log-transformed ART-2a algorithm. Both long-term seasonal trends and high-time-resolution temporal patterns of particle type concentrations were examined. Source identification was supported by comparison with known source samples. Potential source contribution functions were used to identify source regions. This paper describes and evaluates these approaches to data interpretation using examples from the ambient air study to illustrate the methodology and highlight the findings. Furthermore, these ambient examples demonstrate how the application of these strategies enhances the interpretation of single-particle ambient aerosol data. Copyright 2012 American Association for Aerosol Research [ABSTRACT FROM AUTHOR]

Abstract: The advent of high throughput technologies, in particular microarrays, for biological research has revived interest in clustering, resulting in a plethora of new clustering algorithms. However, model selection, i.e., the identification of the correct number of clusters in a dataset, has received relatively little attention. Indeed, although central for statistics, its difficulty is also well known. Fortunately, a few novel techniques for model selection, representing a sharp departure from previous ones in statistics, have been proposed and gained prominence for microarray data analysis. Among those, the stability-based methods are the most robust and best performing in terms of prediction, but the slowest in terms of time. It is very unfortunate that as fascinating and classic an area of statistics as model selection, with important practical applications, has received very little attention in terms of algorithmic design and engineering. In this paper, in order to partially fill this gap, we make the following contributions: (A) the first general algorithmic paradigm for stability-based methods for model selection; (B) reductions showing that all of the known methods in this class are an instance of the proposed paradigm; (C) a novel algorithmic paradigm for the class of stability-based methods for cluster validity, i.e., methods assessing how statistically significant is a given clustering solution; (D) a general algorithmic paradigm that describes heuristic and very effective speed-ups known in the literature for stability-based model selection methods. Since the performance evaluation of model selection algorithms is mainly experimental, we offer, for completeness and without even attempting to be exhaustive, a representative synopsis of known experimental benchmarking results that highlight the ability of stability-based methods for model selection and the computational resources that they require for the task. As a whole, the contributions of this paper generalize in several respects reference methodologies in statistics and show that algorithmic approaches can yield deep methodological insights into this area, in addition to practical computational procedures. [Copyright &y& Elsevier]

This paper discusses an alternative approach to the estimation procedure presented in a recently published paper. The authors developed a model-based clustering approach for regression time series and proposed the APECM procedure as an acceleration method for the expectation-maximization algorithm. The process of the estimation of model parameters was discussed in great detail. In this paper, we show how the proposed procedure can be modified to achieve substantial acceleration and better stability. In particular, numerical maximization suggested for the estimation of parameters can be replaced with analytical closed-form expressions, and inverting high dimensional matrices can be avoided entirely. A convenient approach for assessing variability in parameter estimates is also provided. The results of conducted experiments are very promising. © 2012 Wiley Periodicals, Inc. Statistical Analysis and Data Mining, 2012 [ABSTRACT FROM AUTHOR]