Search

An original computational approach for cluster analysis is proposed.The method consists of two phases, which are based on Self-Organizing Map.Topology-preserving and connectivity functions are used in the clustering process.The method is proved using three benchmark datasets and a real biological dataset.Automation in parameterization results in a user-friendly methodology. Data clustering is aimed at finding groups of data that share common hidden properties. These kinds of techniques are especially critical at early stages of data analysis where no information about the dataset is available. One of the mayor shortcomings of the clustering algorithms is the difficulty for non-experts users to configure them and, in some cases, interpret the results. In this work a computational approach with a two-layer structure based on Self-Organizing Map (SOM) is presented for cluster analysis. In the first level, a quantization of the data samples using topology-preserving metrics to automatically determine the number of units in the SOM is proposed. In the second level the obtained SOM prototypes are clustered by means of a connectivity analysis to explore the quality of the partitioning with different number of clusters. The most important benefit of this two-layer procedure is that computational load decreases considerably in comparison with data based clustering methods, making it possible to cluster large data sets and to consider several different clustering alternatives in a limited time. This methodology produces a two-dimensional map representation of the, usually, high dimensional input space, along with quantitative information on viable clustering alternatives, which facilitates the exploration of the possible partitions in a dataset. The efficiency and interpretation of the methodology is illustrated by its application to artificial, benchmark and real complex biological datasets. The experimental results demonstrate the ability of the method to identify possible segmentations in a dataset, compared to algorithms that only yield a single clustering solution. The proposed algorithm tackles the intrinsic limitations of SOM and the parameter settings associated with the clustering methodology, without requiring the number of clusters or the SOM architecture as a prerequisite, among others. This way, it makes possible its application even by researchers with a limited expertise in machine learning.

A new hybrid method of FCM and CRO algorithm is proposed for optimal cluster analysis.The performance of CRO-FCM is compared with evolutionary & swarm based methods.Performance metrics like rate of error, inter & intra cluster distance are considered. Hybridization of two or more algorithms has always been a keen interest of research due to the quality of improvement in searching capability. Taking the positive insights of both the algorithms, the developed hybrid algorithm tries to minimize the substantial limitations. Clustering is an unsupervised learning method, which groups the data according to their similar or dissimilar properties. Fuzzy c-means (FCM) is one of the popularly used clustering algorithms and performs better as compared to other clustering techniques such as k-means. However, FCM possesses certain limitations such as premature trapping at local minima and high sensitivity to the cluster center initialization. Taking these issues into consideration, this research proposes a novel hybrid approach of FCM with a recently developed chemical based metaheuristic for obtaining optimal cluster centers. The performance of the proposed approach is compared in terms of cluster fitness values, inter-cluster distance and intra-cluster distance with other evolutionary and swarm optimization based approaches. A rigorous experimentation is simulated and experimental result reveals that the proposed hybrid approach is performing better as compared to other approaches.

Perform cluster analysis using three newly designed objective functions.Utilize three optimization algorithms like, genetic, cuckoo search and PSO.Present 21 different clustering algorithms and the validation with 16 datasets.Proved, objective function decides effectiveness & search algorithm decides efficiency.Presented a suggestion for a better algorithm based on input data characteristics. Clustering finds various applications in the field of medical and telecommunication for unsupervised learning which is much required in expert system and its application. Various algorithms have been developed to clustering for the past fifty years after the introduction of k-means clustering. Recently, optimization algorithms are applied for clustering to find optimal clusters with the help of different objective functions. Accordingly, in this research, clustering is performed using three newly designed objective functions along with four existing objective functions with the help of optimization algorithms like, genetic algorithm, cuckoo search and particle swarm optimization algorithm. Here, three different objective functions are designed including the cumulative summation of fuzzy membership and distance value with normal data space, kernel space as well as multiple kernel space. In addition to the existing seven objective functions, totally, 21 different clustering algorithms are discussed and the performance is validated with 16 different datasets which are synthetic, small and large scale real data. The comparison is made with five different evaluation metrics to validate the effectiveness and efficiency. From the research outcome, the suggestion is presented to select a suitable algorithm among 21 algorithms for a particular data and results proved that the effectiveness of cluster analysis is mainly dependent on objective function and the efficiency of cluster analysis is based on search algorithm.

Data-driven modeling provides an attractive alternative to predict SAGD recovery.The modeling approach is applied successfully for heterogeneous reservoirs.Arps parameters are proposed to parameterize production time-series data.A normalized shale indicator is used as a pertinent input attribute.Accuracy of the prediction is greatly enhanced when cluster analyses are performed. Evaluation of steam-assisted gravity drainage (SAGD) performance that involves detailed compositional simulations is usually deterministic, cumbersome, expensive (manpower and time consuming), and not quite suitable for practical decision making and forecasting, particularly when dealing with high-dimensional data space consisting of large number of operational and geological parameters. Data-driven modeling techniques, which entail comprehensive data analysis and implementation of machine learning methods for system forecast, provide an attractive alternative.In this paper, artificial neural network (ANN) is employed to predict SAGD production in heterogeneous reservoirs, an important application that is lacking in existing literature. Numerical flow simulations are performed to construct a training data set consists of various attributes describing characteristics associated with reservoir heterogeneities and other relevant operating parameters. Empirical Arps decline parameters are tested successfully for parameterization of cumulative production profile and considered as outputs of the ANN models. Sensitivity studies on network configurations are also investigated. Principal components analysis (PCA) is performed to reduce the dimensionality of the input vector, improve prediction quality, and limit over-fitting. In a case study, reservoirs with distinct heterogeneity distributions are fed to the model. It is shown that robustness and accuracy of the prediction capability are greatly enhanced when cluster analysis are performed to identify internal data structures and groupings prior to ANN modeling. Both deterministic and fuzzy-based clustering techniques are compared, and separate ANN model is constructed for each cluster. The model is then tested using a validation data set (cases that have not been used during the training stage).The proposed approach can be integrated directly into most existing reservoir management routines. In addition, incorporating techniques for dimensionality reduction and clustering with ANN demonstrates the viability of this approach for analyzing large field data set. Given that quantitative ranking of operating areas, robust forecasting, and optimization of heavy oil recovery processes are major challenges faced by the industry, the proposed research highlights the significant potential of applying effective data-driven modeling approaches in analyzing other solvent-additive steam injection projects.

This paper proposes a new hierarchical clustering method using genetic algorithms for the analysis of gene expression data. This method is based on the mathematical proof of several results, showing its effectiveness with regard to other clustering methods. Genetic algorithms applied to cluster analysis have disclosed good results on biological data and many studies have been carried out in this sense, although most of them are focused on partitional clustering methods. Even though there are few studies that attempt to use genetic algorithms for building hierarchical clustering, they do not include constraints that allow us to reduce the complexity of the problem. Therefore, these studies become intractable problems for large data sets. On the other hand, the deterministic hierarchical clustering methods generally face the problem of convergence towards local optimums due to their greedy strategy. The method introduced here is an alternative to solve some of the problems existing methods face. The results of the experiments have shown that our approach can be very effective in cluster analysis of DNA microarray data.

Prova tipográfica, Cluster analysis of DNA microarray data is an important but difficult task in knowledge discovery processes. Many clustering methods are applied to analysis of data for gene expression, but none of them is able to deal with an absolute way with the challenges that this technology raises. Due to this, many applications have been developed for visually representing clustering algorithm results on DNA microarray data, usually providing dendrogram and heat map visualizations. Most of these applications focus only on the above visualizations, and do not offer further visualization components to the validate the clustering methods or to validate one another. This paper proposes using a visual analytics framework in cluster analysis of gene expression data. Additionally, it presents a new method for finding cluster boundaries based on properties of metric spaces. Our approach presents a set of visualization components able to interact with each other; namely, parallel coordinates, cluster boundary genes, 3D cluster surfaces and DNA microarray visualizations as heat maps. Experimental results have shown that our framework can be very useful in the process of more fully understanding DNA microarray data. The software has been implemented in Java, and the framework is publicly available at http://www. analiticavisual.com/jcastellanos/3DVisualCluster/3D-VisualCluster., This work has been partially funded by the Spanish Ministry of Science and Innovation, the Plan E from the Spanish Government, the European Union from the ERDF (TIN2009-14057-C03-02).

Clustering is an important concept formation process within AI. It detects a set of objects with similar characteristics. These similar aggregated objects represent interesting concepts and categories. As clustering becomes more mature, post-clustering activities that reason about clusters need a great attention. Numerical quantitative information about clusters is not as intuitive as qualitative one for human analysis, and there is a great demand for an intelligent qualitative cluster reasoning technique in data-rich environments. This article introduces a qualitative cluster reasoning framework that reasons about clusters. Experimental results demonstrate that our proposed qualitative cluster reasoning reveals interesting cluster structures and rich cluster relations.

This paper proposes a fuzzy modeling method via Enhanced Objective Cluster Analysis to obtain the compact and robust approximate TSK fuzzy model. In our approach, the Objective Cluster Analysis algorithm is introduced. In order to obtain more compact and more robust fuzzy rule prototypes, this algorithm is enhanced by introducing the Relative Dissimilarity Measure and the new consistency criterion to represent the similarity degree between the clusters. By these additional criteria, the redundant clusters caused by iterations are avoided; the subjective influence from human judgment for clustering is weakened. Moreover the clustering results including the number of clusters and the cluster centers are considered as the initial condition of the premise parameters identification. Thus the traditional iteration modeling procedure for determining the number of rules and identifying parameters is changed into one-off modeling, which significantly reduces the burden of computation. Furthermore the decomposition errors and the approximation errors resulted from premise parameters identification by Fuzzy c-Means clustering are decreased. For the consequence parameters identification, the Stable Kalman Filter algorithm is adopted. The performance of the proposed modeling method is evaluated by the example of Box-Jenkins gas furnace. The simulation results demonstrate the power of our model.

Strategic group analysis comprises of clustering of firms within an industry according to their similarities with respect to a set of strategic dimensions and investigating the performance implications of strategic group membership. One of the challenges of strategic group analysis is the selection of the clustering method. In this study, the results of the strategic group analysis of Turkish contractors are presented to compare the performances of traditional cluster analysis techniques, self-organizing maps (SOM) and fuzzy C-means method (FCM) for strategic grouping. Findings reveal that traditional cluster analysis methods cannot disclose the overlapping strategic group structure and position of companies within the same strategic group. It is concluded that SOM and FCM can reveal the typology of the strategic groups better than traditional cluster analysis and they are more likely to provide useful information about the real strategic group structure.

The goal of this study was to overcome three main shortcomings in using a single algorithm to determine a particular clustering of a phenomenon. We addressed this issue by considering cross-cultural research as a case in point and applied Multi-Algorithm Voting (MAV) methodology to cluster analysis. Specifically, this study was designed to provide more systematic supportive decision tools for researchers and managers alike when attempting to cluster analyzing phenomena. To assess the merits of the methodology of MAV for cluster analysis, we analytically examined cross-cultural data from Merritt [Merritt, A. (2000). Culture in the cockpit Do Hofstede's dimensions replicate? Journal of Cross-Cultural Psychology, 31, 283-301] study as well as data scored and ranked by Hofstede [Hofstede, G. (1980). Culture's consequences: International differences in work-related values. Beverly Hills, CA: Sage; Hofstede, G. (1982). Values survey module (Tech. Paper). Maastricht, The Netherlands: Institute for Research on Intercultural Cooperation]. Our study contributes to the literature in several ways. From a methodological point of view, we show how researchers can avoid arbitrary decisions in determining the number of clusters. We provide the researcher with more compelling and robust methodologies not only for analyzing the results of cluster analysis, but also for more better-grounded decision-making through which theoretical insights and implications can be drawn.

Highlights? Offer an alternative way to explore the spatial patterns of typhoon tracks. ? Cluster methodologies show that typhoon centers pass through Taiwan from the south-east to the north-west. ? Provide planners to understand the hotspot areas of typhoon tracks and adjust disaster management efforts. Increasing our understanding of typhoon movements remains a priority in the western North Pacific. In this study, the trajectories of typhoons that affected Taiwan between 1986 and 2010 are used for clustering, where each trajectory consists of 6-hourly latitude-longitude positions over two days. We compare the performance of four statistical clustering methods, namely, k-means clustering, fuzzy c-means (FCM) clustering, hierarchical clustering, and normalized cut techniques. The results show that the FCM technique provides sufficient cluster efficiency with a relatively high degree of goodness of fit. FCM identifies six clusters according to the minimum coefficients of variation (CV). The hotspots of the typhoon centers in each cluster are determined by kernel density estimation (KDE). Moreover, the typhoon track belongs to six clusters with different membership degrees in FCM. The typhoon track density map is estimated by combining the KDE hotspot maps associated with the FCM weights. The information could be used in planning for disaster management.

Data envelopment analysis (DEA) is a widely used non-parametric data analytic tool discriminatory power of which is dependent on the homogeneity of the domain of the sample. In many real-life cases, however, the sample of the decision making units (DMU) could consist of two or more naturally occurring subsets, thus exhibiting clear signs of heterogeneity. In such situations, the discriminatory power of DEA is limited, for the nature of the relative efficiency of a DMU is likely to be influenced by its membership in a particular subset of the sample. In this study, we propose a three-step methodology allowing for increasing the discriminatory power of DEA in the presence of the heterogeneity of the sample. In the first phase, we use cluster analysis (CA) in order to test for the presence of the naturally occurring subsets in the sample. In the second phase DEA is used to calculate the relative efficiencies of the DMUs, as well as averaged relative efficiencies of each subset identified in the previous phase. Finally, we utilize decision tree (DT) induction in order to inquire into the subset-specific nature of the relative efficiencies of the DMUs in the sample. Illustrative example is provided.

Aiming at the multi-disease diagnosis, a self-organizing map (SOM) is developed. In this paper the tomato disease features are extracted and a mapping relationship between the diseases and the features is created. The inaccurate clustering of traditional SOM algorithm is analyzed. According to the analysis, Euclidean distance is taken as the main discrimination, and the adjacent-searching algorithm is optimized. Using the optimized algorithm, the cluster results of input samples are obtained, features of diseases are mapped, and a multi-disease diagnosis model is developed. The proposed SOM-based model has two layers. The feature array of diseases can be accurately and rapidly sorted and clustered using this model. This model can achieve an accurate diagnosis of multi-diseases. The simulation results show that the proposed model performs well and the proposed multi-disease diagnosis is effective.

Dimensionality reduction is inevitable in stock selection with cluster analysis. Considering relations among dimensionality reduction, noise trading, and market situations, we empirically investigate the effect of dimensionality-reduction methods–principal component analysis, stacked autoencoder, and stacked restricted Boltzmann machine–on stock selection with cluster analysis in different market situations. Based on the index fluctuation, the market is divided into sideways and trend situations. For the CSI 100 and Nikkei 225 constituent stocks, experimental results show that: (1) In sideways situations, dimensionality reduction hardly improves the performance of stock selection with cluster analysis; (2) the advantage of dimensionality reduction is mainly reflected in trend situations, but whether it is in an up or down trend depends on the market analyzed. More importantly, according to the above findings and assuming that the dimensionality-reduction effect will continue, we propose a rotation strategy with and without dimensionality reduction. The results of experiments show that the proposed rotation strategy outperforms the stock market indices as well as the stock-selection strategies based on dimensionality reduction and cluster analysis. These findings offer practical insights into how dimensionality reduction can be efficiently used for stock selection.

A visual inspection over 41 global stock indexes is conducted.We use MDS and AHC methods to detect (dis)integration levels and clusters.For each level and cluster, the abnormal indexes are detected.Using most integrated indexes, we report their linkage in 12 different time periods. Following the globalization of the economy, interests in examining the financial linkages of economies have been increased, especially in the wake of the global financial crisis. In light of the benefits of international portfolio diversification, it is not surprising that there has been a strong interest among researchers to capture presence and extent of global stock market GSM integration. This study addresses to the feasibility and benefits of two visual data interpretation methods, based on multidimensional scaling and cluster analysis, in GSM integration context. The explanatory power of applied methods has become stronger by putting both integration and disintegration (anomaly) detection strategies. Empirically, in the first phase, we detect (dis)integration levels and clusters among 41 indexes from 40 countries. In the second phase, we choose most integrated indexes, detected in the first phase, to see whether their linkages are progressing, stable or regressing during different time series (12 seasons). In phase one and two, the topological properties of global stock networks are expressed in two-dimensional plots (dendrogram, heat map, frequency map). Based on the results, we found proposed methods capable of capturing (1) hierarchy of interrelated clusters embedded in a complex network of objects (2) different (dis)integration levels among selected global stock indexes and (3) abnormal seasons and indexes considering time and regional horizons.

This work proposes a method of analyzing ECG signal to diagnose cardiac arrhythmias utilizing the cluster analysis (CA) method. The proposed method can accurately classify and distinguish the difference between normal heartbeats (NORM) and abnormal heartbeats. Abnormal heartbeats may include the following: left bundle branch block (LBBB), right bundle branch block (RBBB), ventricular premature contractions (VPC), and atrial premature contractions (APC). Analysis of ECG signal consists of three major stages: (i) detecting the QRS waveform; (ii) selecting qualitative features; and (iii) determining heartbeat case. The ECG signals in the MIT-BIH arrhythmia database are adopted as reference data for accomplishing the first two stages, and cluster analysis is used to determine patient heartbeat case. In the experiments, the sensitivity is 95.59%, 91.32%, 90.50%, 94.51%, and 93.77% for heartbeat case NORM, LBBB, RBBB, VPC, and APC, respectively. The total classification accuracy (TCA) was about 94.30%.

Bio-chip data that consists of high-dimensional attributes have more attributes than specimens. Thus, it is difficult to obtain covariance matrix from tens thousands of genes within a number of samples. Feature selection and extraction is critical to remove noisy features and reduce the dimensionality in microarray analysis. This study aims to fill the gap by developing a data mining framework with a proposed algorithm for cluster analysis of gene expression data, in which coefficient correlation is employed to arrange genes. Indeed, cluster analysis of microarray data can find coherent patterns of gene expression. The output is displayed as table list for convenient survey. We adopt the breast cancer microarray dataset to demonstrate practical viability of this approach.

Distributed Denial of Service (DDoS) attacks generate enormous packets by a large number of agents and can easily exhaust the computing and communication resources of a victim within a short period of time. In this paper, we propose a method for proactive detection of DDoS attack by exploiting its architecture which consists of the selection of handlers and agents, the communication and compromise, and attack. We look into the procedures of DDoS attack and then select variables based on these features. After that, we perform cluster analysis for proactive detection of the attack. We experiment with 2000 DARPA Intrusion Detection Scenario Specific Data Set in order to evaluate our method. The results show that each phase of the attack scenario is partitioned well and we can detect precursors of DDoS attack as well as the attack itself.

Data mining (DM) methodology has a tremendous contribution for researchers to extract the hidden knowledge and information which have been inherited in the data used by researchers. This study has proposed a new procedure, based on expanded RFM model by including one additional parameter, joining WRFM-based method to K-means algorithm applied in DM with K-optimum according to Davies-Bouldin Index, and then classifying customer product loyalty in under B2B concept. The developed methodology has been implemented for SAPCO Co. in Iran. The result shows a tremendous capability to the firm to assess his customer loyalty in marketing strategy designed by this company in comparing with random selection commonly used by most companies in Iran.