Analysing Heart Rate Dynamics in Collaborative Learning Situations Using Wearables and AI/Analytics

Primary supervisor

Roberto Martinez-Maldonado

This project focuses on modeling heart rate data captured via FitBit Sense devices worn by team members in collaborative situations such as supervision meetings, group teaching, or nursing simulation scenarios. The primary goal is to identify stressful situations or similar events by analysing heart rate variations.

    This project offers a rich opportunity for IT, CS, AI, or software engineering students to delve into the practical applications of data modeling, wearable technology, and user interface design. The insights gained from this exploration can significantly enhance our understanding of stress dynamics in collaborative environments, providing valuable feedback for improving team performance and well-being.

    As a participant in this project, you will be part of the Centre for Learning Analytics at Monash (CoLAM), the largest learning analytics group in the world. Our center focuses on applying AI in education and developing advanced analytics to support students and teachers. By joining our team, you will have the opportunity to work alongside leading researchers and contribute to cutting-edge projects that aim to transform educational practices through data-driven insights. This environment provides a unique platform for you to develop your skills and make a meaningful impact in the field of learning analytics and educational technology.

    Student cohort

    Double Semester

    Aim/outline

    Exploration Focus:

    • Stressful Situations Identification: Use heart rate data to pinpoint moments of high stress or intensity during collaborative activities.
    • Event Correlation: Correlate heart rate changes with specific events or interactions to understand their impact on stress levels.

    Technical Objectives:

    • Heart Rate Modeling: Develop models to accurately capture and analyse heart rate data from FitBit devices.
    • Data Integration: Integrate heart rate data with positioning data (if available) to provide spatial context to the analysis.
    • User Interface Design: Create intuitive interfaces to visualise heart rate variations, maximum values, and stress indicators over time or within specific spaces.

    URLs/references

    This is an example recent publication from our centre (The Centre for Learning Analytics at Monash): 

    Yan, L., Martinez-Maldonado, R., Zhao, L., Li, X., & Gašević, D. (2023, June). Physiological synchrony and arousal as indicators of stress and learning performance in embodied collaborative learning. In International Conference on Artificial Intelligence in Education (pp. 602-614). Cham: Springer Nature Switzerland. PDF

    Required knowledge

    • Basic understanding of machine learning OR visualisation concepts and algorithms.
    • Skills in data cleaning, preprocessing, and analysis, especially with physiological data.
    • Proficiency in programming languages such as Python.
    • Interest in working with data from wearable devices like FitBit.
    • Ability to create and interpret data visualisations.
    • Some familiarity with software development practices, including version control.
    • Good communication skills.
    • Some awareness of ethical issues in data privacy and AI usage.