Research & Study

High school students often experience reduced productivity during study sessions due to environmental distractions — noise, poor lighting, temperature fluctuations — and unmanaged emotional states. Commercial affective computing systems are typically expensive and inaccessible. This study develops and evaluates a low-cost Raspberry Pi-based IoT desk assistant that monitors ambient conditions and delivers real-time visual feedback to enhance emotional awareness and focus. The system integrates multiple sensors with a custom animated dashboard, applying emotional modeling, sensor calibration, and UI/UX design principles to promote sustained productivity.

Selected from a competitive national applicant pool for the 2026 MIT Critical Data × NSRI research cohort, affiliated with the MIT Laboratory for Computational Physiology. Serving as Lead Researcher on a large-scale scientometric audit of the 2022 VA/DoD Clinical Practice Guideline for Major Depressive Disorder (MDD), one of the most comprehensive federal clinical references in the United States.

• Screened and classified 239 guideline-cited studies across interventional, observational, and review categories using standardized inclusion/exclusion criteria
• Identified that race/ethnicity was reported in only 0.8% of cited references, revealing a critical lack of demographic representation across the evidentiary base
• Extracting and standardizing demographic data across clinical studies, analyzing reporting completeness for sex, age, and race/ethnicity using ISO 3166 geographic coding
• Generating pooled demographic estimates using study-weighted and participant-weighted statistical methods
• Participating in weekly research seminars with an international cohort addressing real-world clinical data challenges

Research conducted under mentorship of Leo Anthony Celi, MD, MPH, MSc — MIT Laboratory for Computational Physiology, Beth Israel Deaconess Medical Center, and Harvard T.H. Chan School of Public Health.