Wei Zhong

About

Wei Zhong is an Assistant Professor of Political Science at Stony Brook University. She holds a Ph.D. in Political Science and an M.S. in Statistics from the University of Illinois Urbana-Champaign, an M.A. from New York University, and a B.A. from the University of International Business and Economics in China. Prior to joining Stony Brook, she was a Postdoctoral Fellow at New York University’s Center for Social Media and Politics and a Research Scientist at the Institute for Data, Democracy & Politics at George Washington University. Her research uses computational methods to investigate how digital media and emerging technologies shape political behavior, polarization, and democratic governance. She studies how individuals engage with online content, how extremist groups adapt to platform interventions, and how synthetic media influences public perception. Her work examines when, why, and among whom digital communication alters political attitudes and mobilization. Her current projects explore the effects of AI-generated content and labeling policies, the resilience of far-right networks after deplatforming, and the role of media strategies in audience building. She is especially interested in cross-platform dynamics and how social media architectures mediate political discourse in both democratic and authoritarian contexts.

Research topics

• Medicine
• Internal medicine
• Chemistry
• Biomedical engineering
• Surgery
• Pharmacology
• Immunology
• Anesthesia

Selected publications

• Multishot Dual Polarity GRAPPA: Robust Nyquist Ghost Correction for multishot EPI.

  PubMed · 2025-07-24 · 1 citations

  preprintOpen access

  PURPOSE: This work aims to develop a robust Nyquist ghost correction method for multishot echo-planar imaging (EPI). The method helps correct challenging Nyquist ghosts, particularly on scanners with high-performance gradients or ultra-high fields. METHODS: A method for multishot EPI ghost correction, called multishot dual-polarity GRAPPA (msDPG), is developed by extending the DPG concept to multishot readouts. msDPG employs tailored DPG kernels to address high-order phase differences between tw…

  PublisherOA PDF

• Stratified Bootstrap Validation and Bayesian-Grid Tuning for Robust Gradient Boosting Ensembles on Clinical Tabular Data

  Information Systems and Economics · 2026-01-01

  articleOpen accessSenior author

  Risk stratification on high-dimensional clinical tabular data poses fundamental challenges arising from feature heterogeneity, class imbalance, and the tension between predictive accuracy and interpretability required for principled decision support. This paper presents a two-stage ensemble learning framework that integrates gradient boosting machines with logistic regression baselines under a hybrid Bayesian-Grid hyperparameter optimization scheme reinforced by Bootstrap resampling validation.…

  PublisherOA PDFDOI

• Self-navigated simultaneous multi-slab 3D DWI

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  article

  Motivation: Simultaneous multi-slab imaging (SMSlab) facilitates high-resolution diffusion-weighted imaging (DWI) with enhanced signal-to-noise ratio (SNR) efficiency, but requires navigators that compromising the scan efficiency. Goal(s): To achieve navigator-free simultaneous multi-slab DWI. Approach: For slabs that are excited simultaneously, a multiband-specific GRAPPA is employed to separate the slabs. The trajectory was optimized by an extended CAIPI sampling to ensure intersections with t…

  PublisherDOI

• Robust Nyquist ghost correction for high-resolution EPI using multishot dual-polarity GRAPPA reconstruction

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  article

  Motivation: Multishot EPI acquisition improves image fidelity and reduces distortion but is prone to Nyquist ghosts. Dual-polarity GRAPPA (DPG) effectively addresses ghosts in single-shot EPI but has not been extended to multishot acquisitions. Goal(s): To develop a robust Nyquist ghost correction method for multishot EPI by tailoring DPG. Approach: We introduce multishot DPG (msDPG), which uses DPG kernels to synthesize polarity-free data and permits incorporation with advanced regularized reco…

  PublisherDOI

Frequent coauthors

• Malcolm Xing

  University of Manitoba

  148 shared

• Pei Hu

  56 shared

• Ji Jiang

  Peking Union Medical College Hospital

  50 shared

• Qian Zhao

  35 shared

• Kaige Xu

  University of Manitoba

  34 shared

• Yuqing Liu

  33 shared

• Hongzhong Liu

  Xi'an Jiaotong University

  25 shared

• Gaoxing Luo

  Army Medical University

  22 shared

Education

• Ph.D., Political Science

  University of Illinois at Urbana-Champaign

Similar researchers at Stony Brook University

• Stanley Feldmanh-48
• Leonie Huddyh-44
• Andrew Deltonh-27