Overview

Export your own data from the Data Lake, install UeduPAD, and participate in a group design challenge where teams of 3–4 design an Educational Omics study with selected teams presenting a 2-minute pitch.

Topics

Uedu Lab: Trusted Educational Data Lake

In this session, participants export their own data collected during the tutorial from the Trusted Educational Data Lake. The Data Lake is the data governance core of the Uedu platform, providing unified infrastructure to manage multimodal data across all six Educational Omics dimensions:

UeduPAD iOS App

UeduPAD is Uedu's iOS mobile application for connecting Garmin smartwatches to collect research-grade physiological data and export via Uedu Lab. Participants will install UeduPAD during this session. Key features include:

• Garmin Data Collection: Connect Garmin watches to collect raw physiological data for research export
• ClassroomGPT Chat: Interact with the AI tutor anytime, anywhere
• Garmin Health Summary: View personal physiological data trends
• Personalized Notifications: Course updates, learning reminders, and AI-driven suggestions

Group Design Challenge

In teams of 3–4, design an Educational Omics research study. Selected teams will deliver a 2-minute pitch presenting their research ideas. Use the following framework as a guide:

Takeaways

Each participant will leave with:

• Personal HRV Analysis Report: Analysis results from Garmin data collected during the tutorial
• Jupyter Notebooks: HRV analysis and multimodal biosignal visualization
• PALM Prompt Templates: Templates for injecting physiological context into LLM system prompts
• Free Uedu Faculty Account: One-year access (10 courses, up to 100 students each, funded by Taiwan's MOE grants)
• UeduPAD iOS App: Connect Garmin watches for research-grade physiological data export
• Sample Datasets: Anonymized research data from the Educational Omics Data Lake

Related Research

• Chang & Li (2025). Designing an Educational Omics Data Lake: A Multimodal Infrastructure for Technology-Enhanced Learning. ICMET.
• Blikstein & Worsley (2016). Multimodal Learning Analytics and Education Data Mining. JLA.
• Cohn et al. (2025). A Multimodal Approach to Support Teacher, Researcher and AI Collaboration in STEM+C Learning Environments. BJET.
• Fernández-Herrero (2024). Evaluating Recent Advances in Affective Intelligent Tutoring Systems. Education Sciences.

Materials