A Wearable Exam Stress Dataset for Predicting Cognitive Performance in Real-World Settings¶
Product or Programme · All products and programmes
Evidence · 4 claims (3 for, 1 mixed) · 1 study (1 associational),q2· 0 of 1 report an effect size · 4 claims rest on one study
Description¶
An open-access PhysioNet dataset of Empatica E4 physiological signals collected from college students during exams, released for studying stress and predicting cognitive performance.
Components¶
- Wearable Exam Stress Dataset (PhysioNet) processed into a balanced 328,655-sample multivariate classification dataset: The study uses the open-access "A Wearable Exam Stress Dataset for Predicting Cognitive Performance in Real-World Settings" from PhysioNet, collected from 10 college students wearing the Empatica E4 wristband during Midterm 1, Midterm 2, and a Final exam. After preprocessing (pivoting to wide format, removing rows with missing values, grade normalization and categorization into A–F, and undersampling to balance classes at 65,731 observations per grade category), "The final processed dataset contains 328,655 samples" with five physiological predictors (ACC, BVP, EDA, HR, TEMP), three exam-participation indicators, and the grade category as target. (Lala Yamazaki et al. (2026))
Claims¶
- Using all collected physiological features improves exam-grade prediction accuracy to 96% over the 80% achieved by prior EDA-only analyses [+M]
- Logistic regression performs poorly (mean accuracy 0.4243) and SVM moderately (0.7374) on physiological exam-outcome prediction [~W]
- Random forest achieves the highest mean test accuracy (0.9590) of all models compared for predicting exam grade categories from physiological signals [+W]
- Random forest feature importance identifies EDA, ACC, and TEMP as the top three physiological predictors of exam outcomes [+W]
Related Products and Programmes¶
-
Key Sources¶
- Lala Yamazaki and Ramchandra Rimal. (2026). Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning. https://arxiv.org/abs/2606.14960
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
a-wearable-exam-stress-dataset-for-predicting-cognitive-performance-in-real-world-settings |
title |
A Wearable Exam Stress Dataset for Predicting Cognitive Performance in Real-World Settings |
description |
An open-access PhysioNet dataset of Empatica E4 physiological signals collected from college students during exams, released for studying stress and predicting cognitive performance. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.