Abstract: Optimizing sensor placement is crucial for enhancing the coverage and data-acquisition efficiency of ocean monitoring systems. Traditional approaches primarily rely on univariate ocean data ...

Abstract: Accurate real-time prediction of key quality variables is critical for complex industrial processes like hydrocracking, where data exhibits multivariate nonlinearity, time delays, and ...

A Lightweight Self-Supervised Representation Learning Framework for Depression Risk Profiling from Synthetic Daily ...

My work has focused on biostatistical methodology and its applied translation to research in mental health, substance use, obesity, and health services, policy, and equity. I have worked extensively ...