Clustering Criterion Function Research Articles

MR-DBIFOA: a parallel Density-based Clustering Algorithm by Using Improve Fruit Fly Optimization

<p>Clustering is an important technique for data analysis and knowledge discovery. In the context of big data, the density-based clustering algorithm faces three challenging problems: unreasonable division of data gridding, poor parameter optimization ability and low efficiency of parallelization. In this study, a density-based clustering algorithm by using improve fruit fly optimization based on MapReduce (MR-DBIFOA) is proposed to tackle these three problems. Firstly, based on KD-Tree, a division strategy (KDG) is proposed to divide the cell of grid adaptively. Secondly, an improve fruit fly optimization algorithm (IFOA) which use the step strategy based on knowledge learn (KLSS) and the clustering criterion function (CFF) is designed. In addition, based on IFOA algorithm, the optimal parameters of local clustering are dynamically selected, which can improve the clustering effect of local clustering. Meanwhile, in order to improve the parallel efficiency, the density-based clustering algorithm using IFOA (MR-QRMEC) are proposed to parallel compute the local clusters of clustering algorithm. Finally, based on QR-Tree and MapReduce, a cluster merging algorithm (MR-QRMEC) is proposed to get the result of clustering algorithm more quickly, which improve the core clusters merging efficiency of density-based clustering algorithm. The experimental results show that the MR-DBIFOA algorithm has better clustering results and performs better parallelization in big data.</p> <p> </p>

Data Analysis of College Students’ Mental Health Based on Clustering Analysis Algorithm

Mental health is an important basic condition for college students to become adults. Educators gradually attach importance to strengthening the mental health education of college students. This paper makes a detailed analysis and research on college students’ mental health, expounds the development and application of clustering analysis algorithm, applies the distance formula and clustering criterion function commonly used in clustering analysis, and makes a specific description of some classic algorithms of clustering analysis. Based on expounding the advantages and disadvantages of fast-clustering analysis algorithm and hierarchical clustering analysis algorithm, this paper introduces the concept of the two-step clustering algorithm, discusses the algorithm flow of clustering model in detail, and gives the algorithm flow chart. The main work of this paper is to analyze the clustering algorithm of students’ mental health database formed by mental health assessment tool test, establish a data mining model, mine the database, analyze the state characteristics of different college students’ mental health, and provide corresponding solutions. In order to meet the needs of the psychological management system based on the clustering analysis method, the clustering analysis algorithm is used to cluster the data. Based on the original database, this paper establishes the methods of selecting, cleaning, and transforming the data of students’ psychological archives. Finally, it expounds on the application of data mining in students’ psychological management system and summarizes and prospects the implementation of the system.

Performance evaluation of similarity measures for K-means clustering algorithm

Clustering is a useful technique that organizes a large quantity of unordered datasets into a small number of meaningful and coherent clusters. Every clustering method is based on the index of similarity or dissimilarity between data points. However, the true intrinsic structure of the data could be correctly described by the similarity formula defined and embedded in the clustering criterion function. This paper uses squared Euclidean distance and Manhattan distance to investigates the best method for measuring similarity between data objects in sparse and high-dimensional domain which is fast, capable of providing high quality clustering result and consistent. The performances of these two methods were reported with simulated high dimensional datasets.

Clustering of modal-valued symbolic data

Symbolic Data Analysis is based on special descriptions of data - symbolic objects (SO). Such descriptions preserve more detailed information about units and their clusters than the usual representations with mean values. A special kind of symbolic object is a representation with frequency or probability distributions (modal values). This representation enables us to consider in the clustering process the variables of all measurement types at the same time. In the paper a clustering criterion function for SOs is proposed such that the representative of each cluster is again composed of distributions of variables' values over the cluster. The corresponding leaders clustering method is based on this result. It is also shown that for the corresponding agglomerative hierarchical method a generalized Ward's formula holds. Both methods are compatible - they are solving the same clustering optimization problem. The leaders method efficiently solves clustering problems with large number of units; while the agglomerative method can be applied alone on the smaller data set, or it could be applied on leaders, obtained with compatible nonhierarchical clustering method. Such a combination of two compatible methods enables us to decide upon the right number of clusters on the basis of the corresponding dendrogram. The proposed methods were applied on different data sets. In the paper, some results of clustering of ESS data are presented.

Local difference‐based active contour model for medical image segmentation and bias correction

This study proposes a local bias field and difference estimation (LBDE) model for medical image segmentation and bias field correction. Firstly, the LBDE model uses a linear combination of a given set of smooth orthogonal basis functions, which is called Chebyshev polynomial, to estimate the bias field. Then, a clustering criterion function is defined by considering the difference between the measured image and approximated image in a small region. By applying this difference in the local region, the LBDE model can obtain accurate segmentation results and estimation of the bias field. Finally, the energy functional is incorporated into a level set formulation with a regularisation term, and it is minimised via the level set evolution process. The LBDE model first appears as a two-phase model and then extends to the multi-phase one. Extensive experiments on medical images demonstrate that the LBDE model achieves more precise segmentation results in terms of Jaccard similarity and dice similarity coefficient than the comparative models. Therefore the proposed model can increase the segmentation accuracy and robustness to noise.

Segmentation of Crop Disease Images with an Improved K-means Clustering Algorithm

Abstract. Disease spot segmentation from crop leaf images is a key prerequisite for disease early warning and diagnosis. To improve the accuracy and stability of disease spot segmentation, an adaptive segmentation method for crop disease images based on K-means clustering is proposed. The approach is based on three stages. First, the excess green feature and the a* component of the CIE (L*a*b*) color space were combined to adaptively learn the initial cluster centers. Second, iterative color clustering of two clusters was conducted using the squared Euclidian distance as the similarity distance. Finally, the distance of a* components between two clusters as the clustering criterion function was used to correct the clustering results. To verify the effectiveness of the proposed method, segmentation experiments were performed on images of three kinds of cucumber diseases and one kind of soybean disease. The results of the experiments were compared with the results obtained using a fixed threshold method, the Otsu method, the traditional K-means clustering method, and the Renyi entropy method, which showed that our adaptive segmentation method was accurate and robust for segmentation of crop disease images. Keywords: Adaptive, CIE L*a*b*, Disease spot, Image segmentation, K-means clustering.

Image segmentation and bias correction using local inhomogeneous iNtensity clustering (LINC): A region-based level set method

Image segmentation is still an open problem due to the existing of intensity inhomogeneity and noise. To accurately segment images with these biases, a local inhomogeneous intensity clustering (LINC) model is proposed. In LINC, a linear combination of a given set of smooth orthogonal basis functions is used to estimate the bias field. A local clustering criterion function is first defined to cluster the nearly homogeneous intensities in a relatively small neighborhood of each pixel. An energy functional is then defined by integrating the function with respect to the neighborhood center. This energy together with a regularization term and an arc length term are incorporated into a variational level set formulation in which de-nosing is implicitly included due to the implied convolution. Image segmentation and bias correction can be simultaneously achieved by updating variables of the final energy functional iteratively till it is stable or a predetermined iteration number is reached. The proposed model LINC has been extensively tested on both synthetic and real images. Experimental results and comparison with state-of-the-art methods demonstrate the advantages of the proposed model in terms of segmentation accuracy, bias field correction, dealing with noise, and robustness to initialization.

MR image segmentation and bias field estimation based on coherent local intensity clustering with total variation regularization.

Though numerous segmentation algorithms have been proposed to segment brain tissue from magnetic resonance (MR) images, few of them consider combining the tissue segmentation and bias field correction into a unified framework while simultaneously removing the noise. In this paper, we present a new unified MR image segmentation algorithm whereby tissue segmentation, bias correction and noise reduction are integrated within the same energy model. Our method is presented by a total variation term introduced to the coherent local intensity clustering criterion function. To solve the nonconvex problem with respect to membership functions, we add auxiliary variables in the energy function such as Chambolle's fast dual projection method can be used and the optimal segmentation and bias field estimation can be achieved simultaneously throughout the reciprocal iteration. Experimental results show that the proposed method has a salient advantage over the other three baseline methods on either tissue segmentation or bias correction, and the noise is significantly reduced via its applications on highly noise-corrupted images. Moreover, benefiting from the fast convergence of the proposed solution, our method is less time-consuming and robust to parameter setting.

A Variational Level Set Model Based on Local Clustering for Image Segmentation

For images with intensity inhomogeneities that can’t get accurate segmentation results, this paper proposes a variational level set model based on local clustering. First,based on the model of images with intensity inhomogeneities, we use the K-mean clustering algorithm for intensity clustering in a neighborhood of each point of images with intensity inhomogeneities, and define a local clustering criterion function for the image intensities in the neighborhood. Then this local clustering criterion function is then integrated with respect to the neighborhood center to give a global criterion of image segmentation. This criterion defines an energy function as a local intensity fitting term in the level set model. By minimizing this energy, our method is able to get the accurate image segmentation. The image segmentation results prove that our model in the aspect of segmenting images with intensity inhomogeneity is better than piecewise constant (PC) models, and the segmentation efficiency is higher than region-scalable fitting (RSF) model.

Clustering Method Study on High-Dimensional Trading Data

Existing clustering algorithms are not designed specially for the features of trading data s and most clustering analyses lack scalability for large-scale transactions. Therefore, a rapid and scalable clustering algorithm using little space is proposed by us, to effectively process high-dimensional trading data without setting parameters manually. The improved method introduces weighted coverage density as similarity metrics of data. On this basis, the clustering criterion function is established for clustering analysis. We assume further implementation is to find association rules in clustering rules. Then two transaction-oriented evaluation measures for clustering quality are put forward. The large item size ratio is based on the concept of big data, which is used to measure the percentage in clustering; the average pair-clusters merging index is adopted to indicate the difference among clustering results with coverage density. The experimental results of artificial data and real data sets have shown that the improved method for clustering analysis can generate high-grade clustering results on most of the experimental data sets, compared to traditional algorithms

Dynamic clustering of histogram data based on adaptive squared Wasserstein distances

This paper presents a Dynamic Clustering Algorithm for histogram data with an automatic weighting step of the variables by using adaptive distances. The Dynamic Clustering Algorithm is a k-means-like algorithm for clustering a set of objects into a predefined number of classes. Histogram data are realizations of particular set-valued descriptors defined in the context of Symbolic Data Analysis. We propose to use the ℓ2 Wasserstein distance for clustering histogram data and two novel adaptive distance based clustering schemes. The ℓ2 Wasserstein distance allows to express the variability of a set of histograms in two components: the first related to the variability of their averages and the second to the variability of the histograms related to different size and shape. The weighting step aims to take into account global and local adaptive distances as well as two components of the variability of a set of histograms. To evaluate the clustering results, we extend some classic partition quality indexes when the proposed adaptive distances are used in the clustering criterion function. Examples on synthetic and real-world datasets corroborate the proposed clustering procedure.

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.

Intensity Non-uniformity Correction for Image Segmentation

Intensity non-uniformity or intensity inhomogeneity usually occurs in Real world Images, those images cannot be segmented by using image segmentation. The most commonly used algorithms in image segmentation are region based and depends on the homogeneity of the image intensities which usually fails to produce accurate segmentation results due to the intensity non-uniformity. In this paper we proposed a novel region based method for image segmentation which can be able to discuss with intensity non-uniformities in image segmentation. First according to the image models with intensity non-uniformities we define a local clustering criterion function for the intensities in the image neighbourhood of each part. The local clustering criterion function is then integrated with respect to the neighbourhood center to give a global criterion of image segmentation. In a level set formulation this criterion defines an energy in terms of level set functions that represents the partition of image domain and a bias field that corresponds to the intensity non-uniformity of the image. Therefore, by minimizing the energy we can able to segment the image simultaneously and estimate the bias field can be used for the intensity non-uniformity correction. This method is applied on MRI images and real world images of various modalities with desirable performance in the presence of intensity non- uniformities. The experiment results show that the method is stronger, faster and more accurate than the well- known piecewise smooth model and gives promising results. As an application this method is used for segmentation and bias correction of real world images and MRI images with better results. Keywords -Bias field, Energy minimization, Image segmentation, Intensity non-uniformity, Level set method.

Superior Reconstruction Quality Improvement of CT Image for Bias Correction Variance Measures

Image segmentation algorithms based on ROI typically rely on the homogeneity of image intensities. CT scanner is dedicated as research Scanner which has been developed in view of imaging applications. A key Feature of the work is to use Empirical system to achieve resolution recovery with novel region based method. This method identifies local intensity cluster with local clustering criterion function with respect to neighborhood center. Reconstruction quality is analyzed quantitatively in terms bias field correction for intensity inhomogenity correction. This method is valid on synthetic images of various imaging modalities. A significant improvement in reconstruction quality can be realized by faster and more accurate visual quality quantitative measures where Reconstruction quality is analyzed quantitatively in terms of bias-variance measures (bar phantom) and mean square error (lesion phantom). However, with the inclusion of the empirical kernel, the iterative algorithms provide superior reconstructions compared to FBP, both in terms of visual quality and quantitative measures. Simulated results show improved tumor bias and variance characteristics with the proposed algorithm.

Comparison of Hierarchical Agglomerative Algorithms for Clustering Medical Documents

Extensive amount of data stored in medical documents require developing methods that help users to find what they are looking for effectively by organizing large amounts of information into a small number of meaningful clusters. The produced clusters contain groups of objects which are more similar to each other than to the members of any other group. Thus, the aim of high-quality document clustering algorithms is to determine a set of clusters in which the inter-cluster similarity is minimized and intra-cluster similarity is maximized. The most important feature in many clustering algorithms is treating the clustering problem as an optimization process, that is, maximizing or minimizing a particular clustering criterion function defined over the whole clustering solution. The only real difference between agglomerative algorithms is how they choose which clusters to merge. The main purpose of this paper is to compare different agglomerative algorithms based on the evaluation of the clusters quality produced by different hierarchical agglomerative clustering algorithms using different criterion functions for the problem of clustering medical documents. Our experimental results showed that the agglomerative algorithm that uses I1 as its criterion function for choosing which clusters to merge produced better clusters quality than the other criterion functions in term of entropy and purity as external measures.

A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI

Intensity inhomogeneity often occurs in real-world images, which presents a considerable challenge in image segmentation. The most widely used image segmentation algorithms are region-based and typically rely on the homogeneity of the image intensities in the regions of interest, which often fail to provide accurate segmentation results due to the intensity inhomogeneity. This paper proposes a novel region-based method for image segmentation, which is able to deal with intensity inhomogeneities in the segmentation. First, based on the model of images with intensity inhomogeneities, we derive a local intensity clustering property of the image intensities, and define a local clustering criterion function for the image intensities in a neighborhood of each point. This local clustering criterion function is then integrated with respect to the neighborhood center to give a global criterion of image segmentation. In a level set formulation, this criterion defines an energy in terms of the level set functions that represent a partition of the image domain and a bias field that accounts for the intensity inhomogeneity of the image. Therefore, by minimizing this energy, our method is able to simultaneously segment the image and estimate the bias field, and the estimated bias field can be used for intensity inhomogeneity correction (or bias correction). Our method has been validated on synthetic images and real images of various modalities, with desirable performance in the presence of intensity inhomogeneities. Experiments show that our method is more robust to initialization, faster and more accurate than the well-known piecewise smooth model. As an application, our method has been used for segmentation and bias correction of magnetic resonance (MR) images with promising results.

Study of Modularity-based Fuzzy Immune Network Clustering Algorithm and Its Application in Fault Diagnosis

A new immune network clustering method with the antibody mutation strategy and the idiotypic network regulation strategy is proposed to improve the data compression ratio and the classification accuracy of the immune network clustering algorithm. Firstly, a novel idiotypic fuzzy immune recognition hypersphere is constructed to update the antibody network based on the Timmis’s Artificial Recognition Ball and the fuzzy theory. In addition, according to the modularity concept which can describe the community structure of the complex network effectively, a modularity-based clustering criterion function is designed, and a new algorithm based on the modularity merging for extracting the memory antibody is proposed to realize the self-adaptive compression for the antibody network. Secondly, a new fuzzy immune network clustering algorithm is developed, which combines the artificial immune network clustering strategy with the modularity-based criterion function. The validity of the method is verified with the UCI data sets. Results show that the proposed method can obtain the reasonable memory antibody network and improve the data compression ratio and the classification accuracy. Finally, the method is applied to the fault diagnosis of a four-stage reciprocal compressor. Compared with the aiNet and fuzzy artificial immune network classification method (FAINC), the proposed method is superior in the classification accuracy and the compression ratio.

Evolutionary Algorithm for Extractive Text Summarization

Text summarization is the process of automatically creating a compressed version of a given document preserving its information content. There are two types of summarization: extractive and abstractive. Extractive summarization methods simplify the problem of summarization into the problem of selecting a representative subset of the sentences in the original documents. Abstractive summarization may compose novel sentences, unseen in the original sources. In our study we focus on sentence based extractive document summarization. The extractive summarization systems are typically based on techniques for sentence extraction and aim to cover the set of sentences that are most important for the overall understanding of a given document. In this paper, we propose unsupervised document summarization method that creates the summary by clustering and extracting sentences from the original document. For this purpose new criterion functions for sentence clustering have been proposed. Similarity measures play an increasingly important role in document clustering. Here we’ve also developed a discrete differential evolution algorithm to optimize the criterion functions. The experimental results show that our suggested approach can improve the performance compared to sate-of-the-art summarization approaches.

Empirical and Theoretical Comparisons of Selected Criterion Functions for Document Clustering

This paper evaluates the performance of different criterion functions in the context of partitional clustering algorithms for document datasets. Our study involves a total of seven different criterion functions, three of which are introduced in this paper and four that have been proposed in the past. We present a comprehensive experimental evaluation involving 15 different datasets, as well as an analysis of the characteristics of the various criterion functions and their effect on the clusters they produce. Our experimental results show that there are a set of criterion functions that consistently outperform the rest, and that some of the newly proposed criterion functions lead to the best overall results. Our theoretical analysis shows that the relative performance of the criterion functions depends on (i) the degree to which they can correctly operate when the clusters are of different tightness, and (ii) the degree to which they can lead to reasonably balanced clusters.

W-efficient partitions and the solution of the sequential clustering problem

Clustering involves partitioning a set of related objects into a set of mutually exclusive and completely exhaustive clusters. The objective is to form clusters which reflect minimum difference among objects as measured by the relevant clustering criterion. Most statements of clustering problems assume that the number of clusters, g, in the partition is known. In reality, a value for g may not be immediately obvious. It is known that as g increases, there is an improvement in the value of the clustering criterion function. However, for some values of g, this rate of improvement may be less than expected. Because there may be a cost factor involved, there is also interest in identifying those values of g that offer attractive rates of improvement. Partitions that are optimal for a given g, and for which the given g offer an attractive rate of improvement, are referred to as being w-efficient; other partitions, even if optimal for a given g, are referred to as being w-inefficient. We present a linear programming approach for generating the w-efficient partitions of the sequential clustering problem, and demonstrate the importance of w-efficient partitions to the efficient solution of the sequential clustering problem.