Abstract We investigate regional features nearby the subway station using clustering method called funFEM and propose a two-step procedure to predict passenger transport flow by incorporating geographical information from cluster analysis functional time series prediction. A massive smart card transaction dataset is used analyze daily number of passengers for each in Seoul Metro. First, we stations into six categories with respect their patterns transport. Then, forecast cluster. By...

Abstract Background Changes in microRNA (miRNA) expression patterns have been extensively characterized several cancers, including human colon cancer. However, how these miRNAs and their putative mRNA targets contribute to the etiology of cancer is poorly understood. In this work, a bioinformatics computational approach with miRNA data was used identify construct association networks between mRNAs gain some insights into underlined molecular mechanisms Method The microarray profiles from...

Purpose In this study, we sought to identify critical linguistic markers that can differentiate sentence processing of individuals with mild cognitive impairment (MCI) from the normal-aging populations by manipulating sentences' complexity. We investigated whether passive sentences, as linguistically complex structures, serve contribute diagnoses distinguish MCI normal aging. Method total, 52 participants, including 26 adults amnestic and cognitively unimpaired adults, participated in study....

Purpose To attempt to determine whether group audiologic rehabilitation (AR) content affected psychosocial outcomes. Method A randomized controlled trial with at least 17 participants per was completed. The 3 treatment groups included a communication strategies training group, plus exercise and an informational lecture group. Evaluations were conducted preclass, postclass, 6-months postclass; they hearing loss–related generic quality of life scales, class evaluation form. Results All...

ABSTRACT Background: The purpose of the current study was to investigate effects working-memory (WM) capacity on age-related changes in abilities comprehend passive sentences when word order systematically manipulated. Methods: A total 134 individuals participated study. sentence-comprehension task consisted canonical and non-canonical word-order conditions. composite measure WM scores used as an index capacity. Results: Participants exhibited worse performance with than order. two-way...

This study investigates the impact of advanced driver-assistance systems on drivers' mental workload. Using a combination physiological signals including ECG, EMG, EDA, EEG (af4 and fc6 channels from theta band), eye diameter data, this aims to predict categorize workload into low, adequate, high levels. Data were collected five different driving situations with varying cognitive demands. A functional linear regression model was employed for prediction, accuracy rate calculated. Among 31...

Generalized linear models with random effects are often used to explain the serial dependence of longitudinal categorical data. Marginalized (MREMs) permit likelihood-based estimations marginal mean parameters and also In this paper, we extend MREM accommodate multivariate binary data using a new covariance matrix Kronecker decomposition, which easily explains both time-specific response correlation. A maximum likelihood estimation is proposed utilizing quasi-Newton algorithm quasi-Monte...

When analyzing multivariate longitudinal binary data, we estimate the effects on responses of covariates while accounting for three types complex correlations present in data. These include within separate over time, cross-correlations between different at times, and each time point. The number parameters thus increases quadratically with dimension correlation matrix, making parameter estimation difficult; estimated matrix must also meet positive definiteness constraint. may additionally be...

In the paper, we discuss dimension reduction of predictors <TEX>${\mathbf{X}}{\in}{{\mathbb{R}}^p}$</TEX> in a regression <TEX>$Y{\mid}{\mathbf{X}}$</TEX> with notion sufficiency that is called sufficient reduction. reduction, original <TEX>${\mathbf{X}}$</TEX> are replaced by its lower-dimensional linear projection without loss information on selected aspects conditional distribution. Depending aspects, central subspace, mean subspace and <TEX>$k^{th}$</TEX>-moment defined investigated as...

The purpose of this paper is to define the central informative predictor subspace contain and develop methods for estimating former subspace. Potential advantages proposed are no requirements linearity, constant variance coverage conditions in methodological developments. Therefore, gives us benefit restoring exhaustively despite failing conditions. Numerical studies confirm theories, real data analyses presented.

In the paper, as a sequence of first tutorial, we discuss sufficient dimension reduction methodologies used to estimate central subspace (sliced inverse regression, sliced average variance estimation), mean (ordinary least square, principal Hessian direction, iterative transformation), and <TEX>$k^{th}$</TEX>-moment (covariance method). Large-sample tests determine structural dimensions three target subspaces are well derived in most methodologies; however, permutation test (which does not...

In this paper, a model-based approach to reduce the dimension of response variables in multivariate regression is newly proposed, following existing context reduction developed by Yoo and Cook [Response for conditional mean regression. Comput Statist Data Anal. 2008;53:334–343]. The related subspace estimated maximum likelihood, assuming an additive error. new approach, linearity condition, which assumed methodological development (2008), understood through covariance matrix random Numerical...

The K-means clustering algorithm has had successful application in sufficient dimension reduction. Unfortunately, the does have reproducibility and nestness, which will be discussed this paper. These are clear deficits for algorithm; however, hierarchical both but intensive comparison between not yet been done a reduction context. In paper, we rigorously study two algorithms popular methodology of inverse mean methods throughout numerical studies. Simulation studies real data examples...

In this paper, we introduce linear modeling of canonical correlation analysis, which estimates direction matrices by minimising a quadratic objective function. The results in class estimators matrices, and an optimal is derived the sense described herein. guarantees several following desirable advantages: first, its are asymptotically efficient; second, test statistic for determining number covariates always has chi-squared distribution asymptotically; third, it straight forward to construct...