|
|
|
 |
Search published articles |
 |
|
Showing 7 results for Clustering
Mahnaz Nabil, Mousa Golalizadeh,
Volume 8, Issue 2 (3-2015)
Abstract
Recently, employing multivariate statistical techniques for data, that are geometrically random, made more attention by the researchers from applied disciplines. Shape statistics, as a new branch of stochastic geometry, constitute batch of such data. However, due to non-Euclidean feature of such data, adopting usual tools from the multivariate statistics to proper statistical analysis of them is not somewhat clear. How to cluster the shape data is studied in this paper and then its performance is compared with the traditional view of multivariate statistics to this subject via applying these methods to analysis the distal femur.
Meysam Tasallizadeh Khemes, Zahra Rezaei Ghahroodi,
Volume 11, Issue 2 (3-2018)
Abstract
There are several methods for clustering time course gene expression data. But, these methods have limitations such as the lack of consideration of correlation over time and suffering of high computational. In this paper, by introducing the non-parametric and semi parametric mixed effects model, this correlation over time is considered and by using penalized splines, computation burden dramatically reduced. At the end, using a simulation study the performance of the presented method is compared with previous methods and by using BIC criteria, the most appropriate model is selected. Also the proposed approach is illustrated in a real time course gene expression data set.
Farzad Eskandari, Hamid Haji Aghabozorgi,
Volume 16, Issue 1 (9-2022)
Abstract
Graphical mixture models provide a powerful tool to visually depict the conditional independence relationships between high-dimensional heterogeneous data. In the study of these models, the distribution of the mixture components is mostly considered multivariate normal with different covariance matrices. The resulting model is known as the Gaussian graphical mixture model. The nonparanormal graphical mixture model has been introduced by replacing the limiting normal assumption with a semiparametric Gaussian copula, which extends the nonparanormal graphical model and mixture models. This study proposes clustering based on the nonparanormal graphical mixture model with two forms of $ell_1$ penalty function (conventional and unconventional), and its performance is compared with the clustering method based on the Gaussian graphical mixture model. The results of the simulation study on normal and nonparanormal datasets in ideal and noisy settings, as well as the application to breast cancer data set, showed that the combination of the nonparanormal graphical mixture model and the penalty term depending on the mixing proportions, both in terms of cluster reconstruction and parameters estimation, is more accurate than the other model-based clustering methods.
Mousa Golalizadeh, Sedigheh Noorani,
Volume 16, Issue 1 (9-2022)
Abstract
Nowadays, the observations in many scientific fields, including biological sciences, are often high dimensional, meaning the number of variables exceeds the number of samples. One of the problems in model-based clustering of these data types is the estimation of too many parameters. To overcome this problem, the dimension of data must be first reduced before clustering, which can be done through dimension reduction methods. In this context, a recent approach that is recently receiving more attention is the random Projections method. This method has been studied from theoretical and practical perspectives in this paper. Its superiority over some conventional approaches such as principal component analysis and variable selection method was shown in analyzing three real data sets.
Najmeh Rezaeerad, Mahnaz Khalafi, Mohsen Hoseinalizadeh, Majid Azimmohseni,
Volume 17, Issue 2 (2-2024)
Abstract
The analysis of spatio-temporal series is crucial but a challenge in different sciences. Accurate analyses of spatio-temporal series depend on how to measure their spatial and temporal relation simultaneously. In this article, one-sided dynamic principal components (ODPC) for spatio-temporal series are introduced and used to model the common structure of their relation. These principal components can be used in the data set, including many spatio-temporal series. In addition to spatial relations, trends, and seasonal trends, the dynamic principal components reflect other common temporal and spatial factors in spatio-temporal series. In order to evaluate the capability of one-sided dynamic principal components, they are used for clustering and forecasting in spatio-temporal series. Based on the precipitation time series in different stations of Golestan province, the efficiency of the principal components in the clustering of hydrometric stations is investigated. Moreover, forecasting for the SPI index, an essential indicator for detecting drought, is conducted based on the one-sided principal components.
Mozhgan Moradi, Shaho Zarei,
Volume 18, Issue 1 (8-2024)
Abstract
Model-based clustering is the most widely used statistical clustering method, in which heterogeneous data are divided into homogeneous groups using inference based on mixture models. The presence of measurement error in the data can reduce the quality of clustering and, for example, cause overfitting and produce spurious clusters. To solve this problem, model-based clustering assuming a normal distribution for measurement errors has been introduced. However, too large or too small (outlier) values of measurement errors cause poor performance of existing clustering methods. To tackle this problem {and build a stable model against the presence of outlier measurement errors in the data}, in this article, a symmetric $alpha$-stable distribution is proposed as a replacement for the normal distribution for measurement errors, and the model parameters are estimated using the EM algorithm and numerical methods. Through simulation and real data analysis, the new model is compared with the MCLUST-based model, considering cases with and without measurement errors, and the performance of the proposed model for data clustering in the presence of various outlier measurement errors is shown.
Alireza Beheshty, Hosein Baghishani, Mohammadhasan Behzadi, Gholamhosein Yari, Daniel Turek,
Volume 19, Issue 1 (9-2025)
Abstract
Financial and economic indicators, such as housing prices, often show spatial correlation and heterogeneity. While spatial econometric models effectively address spatial dependency, they face challenges in capturing heterogeneity. Geographically weighted regression is naturally used to model this heterogeneity, but it can become too complex when data show homogeneity across subregions. In this paper, spatially homogeneous subareas are identified through spatial clustering, and Bayesian spatial econometric models are then fitted to each subregion. The integrated nested Laplace approximation method is applied to overcome the computational complexity of posterior inference and the difficulties of MCMC algorithms. The proposed methodology is assessed through a simulation study and applied to analyze housing prices in Mashhad City.
|
|
