A5070843841- Statistical Methods and Inference
- Bayesian Methods and Mixture Models
- Statistical Methods and Bayesian Inference
- Gaussian Processes and Bayesian Inference
- Blind Source Separation Techniques
- Sports Analytics and Performance
- Sports Performance and Training
- Spatial and Panel Data Analysis
- Statistical Methods in Clinical Trials
- Advanced Causal Inference Techniques
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Complex Network Analysis Techniques
- Sports Dynamics and Biomechanics
- Target Tracking and Data Fusion in Sensor Networks
- Face and Expression Recognition
- Natural Language Processing Techniques
- Single-cell and spatial transcriptomics
- Spectroscopy and Chemometric Analyses
- Topic Modeling
- Image and Signal Denoising Methods
- Soil Geostatistics and Mapping
- SARS-CoV-2 and COVID-19 Research
- Markov Chains and Monte Carlo Methods
- COVID-19 Clinical Research Studies
University of California, Irvine
2016-2025
University of Toronto
2018
The University of Texas MD Anderson Cancer Center
2015
Donghua University
2015
North Carolina State University
2013
University of California System
1999
Journal Article Adaptive Bayesian multivariate density estimation with Dirichlet mixtures Get access Weining Shen, Shen Department of Statistics, North Carolina State University, 5109 SAS Hall, 2311 Stinson Drive, Raleigh, 27695, U.S.A., wshen2@ncsu.edu Search for other works by this author on: Oxford Academic Google Scholar Surya T. Tokdar, Tokdar Statistical Science, Duke 219A Old Chemistry Building, Box 90251, Durham, 27708, tokdar@stat.duke.edu Subhashis Ghosal sghosal@ncsu.edu...
Understanding sports presents a fascinating challenge for Natural Language Processing (NLP) due to its intricate and ever-changing nature. Current NLP technologies struggle with the advanced cognitive demands required reason over complex scenarios. To explore current boundaries of this field, we extensively evaluated mainstream emerging large models on various tasks addressed limitations previous benchmarks. Our study ranges from answering simple queries about basic rules historical facts...
Abstract We consider a general class of prior distributions for nonparametric Bayesian estimation which uses finite random series with number terms. A is constructed through on the basis functions and associated coefficients. derive result adaptive posterior contraction rates all smoothness levels target function in true model by constructing an appropriate ‘sieve’ applying theory rates. apply this several statistical problems such as density estimation, various regressions, classification,...
Merkel cell carcinoma (MCC) is a rare and highly aggressive cutaneous neuroendocrine with increasing incidence. Cytotoxic chemotherapy checkpoint inhibitors provide treatment options in the metastatic setting; however, there are no approved or standard of care targeted therapy options.To identify actionable alterations annotated by OncoKB database therapeutic evidence level association tumor mutation burden (TMB).This retrospective, cross-sectional study using data from American Association...
Hypertrophic response to pathological stimuli is a complex biological process that involves transcriptional and epigenetic regulation of the cardiac transcriptome. Although previous studies have implicated factors signaling molecules in hypertrophy, role RNA-binding protein this has received little attention.Here we used transverse aortic constriction vitro hypertrophy models characterize an evolutionary conserved Lin28a hypertrophy. Next-generation sequencing, RNA immunoprecipitation, gene...
Bloodstain Pattern Analysis (BPA) helps us understand how bloodstains form, with a focus on their size, shape, and distribution. This aids in crime scene reconstruction provides insight into victim positions investigation. One challenge BPA is distinguishing between different types of bloodstains, such as those from firearms, impacts, or other mechanisms. Our study focuses differentiating impact spatter bloodstain patterns gunshot patterns. We distinguish by extracting well-designed...
ABSTRACT Current literature on transfer learning has been focused improving the predictive performance corresponding to a small dataset by transferring information it from larger but possibly biassed dataset. However, methods currently available do not allow computation of prediction intervals, and hence, one rely using either alone or combining with obtain intervals traditional linear regression methods. In this article, we propose an E mpirical B ayes approach for P rediction I nterval T...
We propose a novel regularized mixture model for clustering matrix-valued data. The proposed method assumes separable covariance structure each cluster and imposes sparsity (eg, low rankness, spatial sparsity) the mean signal of cluster. formulate problem as finite matrix-normal distributions with regularization terms, then develop an expectation maximization type algorithm efficient computation. In theory, we show that estimators are strongly consistent various choices penalty functions....
Background: Incretin mimetics, including glucagon-like peptide-1 receptor agonists (GLP-1 agonist) and dipeptidyl peptidase-4 (DPP-4) inhibitors, have been increasingly utilized for glycemic control in patients with type 2 diabetes (T2D). Studies demonstrated additional improvements weight loss, cardiovascular health, renal outcomes. Animal studies shown an association between GLP-1 C-cell proliferation elevated calcitonin, resulting FDA black box. Insulin resistance T2D, along the use of...
We propose an evolutionary state space model (E-SSM) for analyzing high dimensional brain signals whose statistical properties evolve over the course of a non-spatial memory experiment. Under E-SSM, are modeled as mixtures components (e.g., AR(2) process) with oscillatory activity at pre-defined frequency bands. To account potential non-stationarity these (since responses could vary throughout entire experiment), parameters allowed to epochs. Compared classical approaches such independent...
AbstractWe propose a Bayesian nonparametric matrix clustering approach to analyze the latent heterogeneity structure in shot selection data collected from professional basketball players National Basketball Association (NBA). The proposed method adopts mixture of finite mixtures framework and fully uses spatial information via normal distribution representation. We an efficient Markov chain Monte Carlo algorithm for posterior sampling that allows simultaneous inference on both number...
Summary Time-dependent receiver operating characteristic (ROC) curves and their area under the curve (AUC) are important measures to evaluate prediction accuracy of biomarkers for time-to-event endpoints (e.g., time disease progression or death). In this article, we propose a direct method estimate AUC(t) as function t using flexible fractional polynomials model, without middle step modeling time-dependent ROC. We develop pseudo partial-likelihood procedure parameter estimation provide test...
Principal component analysis (PCA) is a well-established tool in machine learning and data processing. The principal axes PCA were shown to be equivalent the maximum marginal likelihood estimator of factor loading matrix latent model for observed data, assuming that factors are independently distributed as standard normal distributions. However, independence assumption may unrealistic many scenarios such modeling multiple time series, spatial processes, functional where outcomes correlated....
We propose a novel linear discriminant analysis (LDA) approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies. Motivated by equivalence conventional LDA and ordinary least squares, we consider an efficient nuclear norm penalized regression encourages low-rank structure. Theoretical properties including nonasymptotic risk bound rank consistency result are established. Simulation studies application to electroencephalography show...
<h3>Background</h3> Checkpoint inhibitors have shown improvement in recurrence-free survival the post-operative setting for node-positive melanoma and were first approved late 2015. However, single-agent checkpoint therapies yet to show benefit overall (OS) lower-risk stage III cancers. We evaluated OS of immunotherapy National Cancer Database (NCDB). <h3>Patients methods</h3> Patient cases selected from NCDB 2020 Participant Use File. Patients diagnosed with cutaneous between 2016 2019 who...
Schizophrenia is a severe mental disorder that distorts patients' perception of reality, and its treatment with antipsychotics can lead to significant side effects. Despite the heterogeneity in patient responses treatments, most existing studies on individualized regimes only focus optimizing efficacy, disregarding potential negative To fill this gap, we propose restricted outcome weighted learning method optimizes efficacy outcomes while adhering individual-level effect constraints. Our...
Both age and obesity are leading risk factors for severe coronavirus disease 2019 (COVID-19), which is caused by acute respiratory syndrome 2 (SARS-CoV-2). Specifically, although most infections occur in individuals under the of 55 years, 95% hospitalizations, admissions to intensive care unit, deaths those over years. Moreover, hospitalized COVID-19 patients have a higher prevalence obesity. It generally believed that chronic low-grade inflammation dysregulated innate adaptive immune...
Chronic alcohol drinking is associated with increased susceptibility to viral and bacterial respiratory pathogens. In this study, we use a rhesus macaque model of voluntary ethanol self-administration study the effects long-term on immunological landscape lung. We report heightened inflammatory state in alveolar macrophages (AMs) obtained from (EtOH)-drinking animals that accompanied by chromatin accessibility intergenic regions regulate genes contain binding motifs for transcription factors...
With the rapid growth of neuroimaging technologies, a great effort has been dedicated recently to investigate dynamic changes in brain activity. Examples include time course calcium imaging and functional connectivity. In this paper, we propose novel nonparametric matrix response regression model characterize nonlinear association between 2D image outcomes predictors such as patient information. Our estimation procedure can be formulated nuclear norm regularization problem, which capture...
Density regression provides a flexible strategy for modeling the distribution of response variable $Y$ given predictors $\mathbf{X}=(X_1,\ldots,X_p)$ by letting that conditional density $\mathbf{X}$ as completely unknown function and allowing its shape to change with value $\mathbf{X}$. The number $p$ may be very large, possibly much larger than observations $n$, but is assumed depend only on smaller predictors, which are unknown. In addition estimation, goal also select important actually...