Search

Estimation of a precision matrix (i.e. inverse covariance matrix) is widely used to exploit conditional independence among continuous variables. The influence of abnormal observations is exacerbated in a high dimensional setting as the dimensionality increases. In this work, we propose robust estimation of the inverse covariance matrix based on an l 1 regularised objective function with a weighted sample covariance matrix. The robustness of the proposed objective function can be justified by a nonparametric technique of the integrated squared error criterion. To address the non-convexity of the objective function, we develop an efficient algorithm in a similar spirit of majorisation-minimisation. Asymptotic consistency of the proposed estimator is also established. The performance of the proposed method is compared with several existing approaches via numerical simulations. We further demonstrate the merits of the proposed method with application in genetic network inference. [ABSTRACT FROM AUTHOR]

In the pricing of customized products, it is challenging to accurately predict the purchase likelihood of potential clients for each personalized request. The heterogeneity of customers and their responses to the personalized products leads to very different purchase behavior. Thus, it is often not appropriate to use a single model to analyze all the pricing data. There is a great need to construct distinctive models for different data segments. In this work, we propose an adaptive convex clustering method to perform data segmentation and model fitting simultaneously for generalized linear models. The proposed method segments data points using the fused penalty to account for the similarity in model structures. It ensures that the data points sharing the same model structure are grouped into the same segment. Accordingly, we develop an efficient algorithm for parameter estimation and study its consistency properties in estimation and clustering. The performance of our approach is evaluated by both numerical examples and case studies of real business data. [ABSTRACT FROM AUTHOR]

Data center thermal management has become increasingly important because of massive computational demand in information technology. To advance the understanding of the thermal environment in a data center, complex computer models are extensively used to simulate temperature distribution maps. However, due to management policies and time constraints, it is not practical to execute such models in a real time fashion. In this article, we propose a novel statistical modeling method to perform real-time simulation by dynamically fusing a base, steady-state solution of a computer model, and real-time thermal sensor data. The proposed method uses a Kalman filter and stochastic gradient descent method as computational tools to achieve real-time updating of the base temperature map. We evaluate the performance of the proposed method through a simulation study and demonstrate its merits in a data center thermal management application. Supplementary materials for this article are available online. [ABSTRACT FROM AUTHOR]

In this article, we investigate clustering methods for multilevel functional data, which consist of repeated random functions observed for a large number of units (e.g., genes) at multiple subunits (e.g., bacteria types). To describe the within- and between variability induced by the hierarchical structure in the data, we take a multilevel functional principal component analysis (MFPCA) approach. We develop and compare a hard clustering method applied to the scores derived from the MFPCA and a soft clustering method using an MFPCA decomposition. In a simulation study, we assess the estimation accuracy of the clustering membership and the cluster patterns under a series of settings: small versus moderate number of time points; various noise levels; and varying number of subunits per unit. We demonstrate the applicability of the clustering analysis to a real data set consisting of expression profiles from genes activated by immunity system cells. Prevalent response patterns are identified by clustering the expression profiles using our multilevel clustering analysis. [ABSTRACT FROM AUTHOR]

Service accessibility is defined as the access of a community to the nearby site locations in a service network consisting of multiple geographically distributed service sites. Leveraging new statistical methods, this article estimates and classifies service accessibility patterns varying over a large geographic area (Georgia) and over a period of 16 years. The focus of this study is on financial services but it generally applies to any other service operation. To this end, we introduce a model-based method for clustering random time-varying functions that are spatially interdependent. The underlying clustering model is nonparametric with spatially correlated errors. We also assume that the clustering membership is a realization from a Markov random field. Under these model assumptions, we borrow information across functions corresponding to nearby spatial locations resulting in enhanced estimation accuracy of the cluster effects and of the cluster membership as shown in a simulation study. Supplementary materials including the estimation algorithm, additional maps of the data, and the C++ computer programs for analyzing the data in our case study are available online. [ABSTRACT FROM AUTHOR]

The article focuses on the discussions regarding the limitations and challenges of the proposed methodology in clustering spatially interdependent data. It says that the discussions are related to the potential sensitivity in the estimates of cluster membership to the model of statements. It mentions that the use of wavelet basis in the clustering approach might furnish specific results for the simulation example in the discussion.

When it passed over the surface of Fe2O3, H2S was catalytically oxidized by O2 in air that resulted in intensive chemiluminescence (CL). A novel H2S sensor based on this kind of CL was developed. Six catalysts were examined and the results showed that the CL intensity based on Fe2O3 was almost 10 times higher than that of the other five. An important advantage of the novel CL H2S sensor was its high selectivity to H2S without the response to other 12 kinds of gases such as hydrocarbon, alcohol, NO2, etc. The response time of the CL sensor to H2S was within 15 s and the recovery time was within 120 s. The linear range of the CL sensor under the optimal conditions was in the range from 8 to 2000 ppm over two orders of magnitude with the detection limit of 3 ppm. The stability of the sensor was examined for 100 h by introduction of 100 ppm H2S into the sensor. No significant decrease of CL signals has been recorded during the time. [Copyright &y& Elsevier]

Diabetes is a complicated endocrine and metabolic disorder, which has become an epidemic health issue worldwide. Fucoidan is extensively distributed in the brown algae and several marine invertebrates exhibiting diverse biological activities. In the present study, the physicochemical property of Sargassum fusiforme fucoidan (SFF) and its effects on streptozotocin (STZ)-induced diabetic mice and gut microbiota were investigated. Diabetes mice not only showed abnormal blood glucose, but also accompanied by multiple symptoms, such as gradual emaciation, decreased body weight, increased food and water intake. Compared with diabetic mice after 6-week treatment, administration of SFF significantly decreased the fasting blood glucose, diet and water intake. Furthermore, SFF attenuated the pathological change in the heart and liver, improved the liver function, and suppressed oxidative stress in STZ-induced diabetic mice. Simultaneously, SFF significantly altered the gut microbiota in the faeces of diabetic mice, decreased the relative abundances of the diabetes-related intestinal bacteria, which is a potential mechanism for relieving the symptoms of diabetes. Therefore, SFF might be considered as one of the promising complementary and alternative medicines for the management of diabetes mellitus in future. [ABSTRACT FROM AUTHOR]