Lala Yamazaki, Ramchandra Rimal (2026) — arXiv preprint 📄 Full text (arXiv)
Investigates ML models to predict exam outcomes from physiological data (electrodermal activity, heart rate, skin temperature) collected during exams. Evaluates logistic regression, random forest, SVM, transformers, LSTM, and GRU. Random forest often outperformed deep learning models while offering interpretability. Highlights value of physiological data for understanding student stress and real-time intervention potential.
Key Contributions
- Random forest predicts exam outcomes from physiological signals as well as deep learning, with better interpretability.
Related Pages
- ai-k12-evidence-base — Empirical evidence on AI in K-12 education outcomes
- intelligent-tutoring — Automated tutoring systems and their evaluation
- student-experience — Student perspectives on AI in education
- learning-analytics — Data-driven approaches to understanding learning
- llm-feedback-programming-classroom — LLM feedback in classroom settings
Citation
APA: Lala Yamazaki, Ramchandra Rimal (2026). Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning. arXiv:2606.14960. arXiv preprint.