Longitudinal study where 10 adults completed standardized psychology tests across three weekly sessions while wearing multiple biometric sensors. Combines self-report psychometric data with real-time physiological recordings.
| Parameter | Detail |
|---|---|
| Participants | 10 adults |
| Sessions | 3 per participant (weekly intervals) |
| Design | Longitudinal, within-subjects |
| Key finding | People differed a lot from each other, but each person's pattern stayed consistent across sessions |
- HADS — Hospital Anxiety and Depression Scale
- STAI-S — State-Trait Anxiety Inventory (State subscale)
- BFI-10 — Big Five Inventory (10-item short form)
- Fear Questionnaire — Marks-Mathews phobia assessment
| Modality | Sensor | What it measures |
|---|---|---|
| Eye tracking | Pupil Labs Core | Gaze position, pupil dilation, fixations, saccades |
| Cardiac | Polar H10+ | Heart rate, HRV (SDNN, RMSSD), inter-beat intervals |
| Electrodermal | TEA GSR | Galvanic skin response, skin conductance level |
| Facial analysis | OpenFace | Action units, head pose, gaze direction |
| Hardware and sensors | Setup |
|---|---|
 |
 |
| Participant in session | Session in progress |
|---|---|
 |
 |
- Recruitment — Adult participants screened and enrolled
- Baseline — Resting-state sensor calibration before each session
- Assessment — Psychometric tests administered while all sensors record simultaneously
- Data collection — Synchronized multimodal streams captured per participant per session
- Analysis — Individual and group-level correlations between self-report and physiological data
How stable are these patterns within a person across sessions? A test–retest reliability check (ICC(1), n = 10, 3 sessions) on the committed summaries gives ICC = 0.22 for HRV SDNN, 0.45 for pupil-dilation variability, and 0.61 for response-duration variability — poor for the physiological measures, moderate at best. So the data do not support a strong "stable individual traits" reading: with only 10 participants, these measures look closer to session-to-session fluctuation than to reliable traits. Any stability claim should be read as tentative and underpowered.
| Standard deviation of HRV (SDNN) | Standard deviation of pupil dilation |
|---|---|
 |
 |
| K-Means clusters in PCA space | Optimal cluster selection |
|---|---|
 |
 |
Python · Jupyter · pandas · NumPy · SciPy · Matplotlib · Seaborn · scikit-learn
IoT · Machine Learning · Multimodal · Neurophysiological · Multi-Sensors · Psychometrics
This repository contains human-subjects data (psychometric responses and physiological recordings from 10 adult participants). All participants gave written informed consent, including consent to share the data openly for research and educational use. Released records are pseudonymised — no names, contact details, dates of birth, or device identifiers — and are handled as special-category personal data under the GDPR and the French Data Protection Act. No IRB number applies; governance rests on that data-protection framework plus explicit consent. Intended for research and educational use only; do not attempt to re-identify participants. Full statement: DATA_ETHICS.md.
- Sensor — Review of the biometric sensors used here
- Psychometric — Web app for the psychometric tests used in this study
- CalmSense — ML/DL stress detection from physiological signals