Daily Activities Wearable Dataset for Cardiorespiratory Fitness — IMU + HR + SpO2 [Zenodo, July 2025]
Abstract
"Multi-site IMU dataset (chest, hands, knees) with heart rate and SpO2 recorded at 0.5 Hz during structured daily activities and a 3-minute step test. Raw + preprocessed IMU (accelerometer, gyroscope, quaternions) + demographic metadata. Zenodo, July 2025. Used for cardiorespiratory fitness (CRF) estimation and HAR."
Description
Overview
Published on Zenodo in July 2025 (version v3, record 15857137) as part of the study "Indirect AI-Based Estimation of Cardiorespiratory Fitness from Daily Activities Using Wearables" (University of Puerto Rico-Mayaguez). Participants performed a structured sequence of daily activities followed by a 3-minute step test designed to elicit a measurable cardiorespiratory response. They wore IMUs at multiple body sites — chest, both hands, and both knees — capturing raw and preprocessed accelerometer, gyroscope, and quaternion data. Heart rate (bpm) and SpO2 (%) were recorded simultaneously at 0.5 Hz from biometric wearable sensors.
The step test HR serves as the regression target for indirect cardiorespiratory fitness (CRF) estimation — a non-invasive alternative to VO2max testing. The dataset further includes rich demographic metadata (age, height, weight, gender, BMI, body fat percentage) enabling multivariate physiological modeling. Frame-level activity labels allow it to be used both for HAR classification and CRF regression. Total data archive size: 423.7 MB (RAR).
Column Schema
| Column | Description |
|---|---|
| timestamp | Synchronized timestamp across all sensor modalities. |
| acc_chest_x/y/z | Raw accelerometer from chest IMU (m/s²). |
| gyro_chest_x/y/z | Raw gyroscope from chest IMU (rad/s). |
| quat_chest_w/x/y/z | Quaternion orientation from chest IMU. |
| acc_hand_* / gyro_hand_* | IMU data from hand-worn sensors. |
| acc_knee_* / gyro_knee_* | IMU data from knee-worn sensors. |
| heart_rate_bpm | Heart rate in bpm, sampled at 0.5 Hz. |
| spo2_pct | Blood oxygen saturation (SpO2, %), sampled at 0.5 Hz. |
| activity_label | Frame-level activity label (HAR target). |
| step_test_hr | HR after 3-minute step test (CRF regression target). |
| age / height / weight / bmi / body_fat_pct | Subject demographic metadata. |
Key Statistics
- IMU Placements: Chest, hands, knees
- IMU Data: Accelerometer + gyroscope + quaternions (raw and preprocessed)
- Biomarkers: Heart rate + SpO2 at 0.5 Hz
- Protocol: Structured daily activities + 3-minute step test
- Regression Target: Step test HR (CRF proxy)
- File Size: 423.7 MB (RAR archive)
- Published: July 2025, Zenodo record 15857137
Use Cases
- Indirect cardiorespiratory fitness (CRF) estimation from wearable IMU + HR data
- HAR classification using multi-site IMU fusion
- SpO2 and heart rate dynamics analysis during physical effort
- Fatigue and training readiness assessment from synchronized biosignals
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Zenodo.
Preview on ZenodoCite This Dataset
Saldaña-Aristizabal, Laura, Rivas-Caicedo, Jhonathan L., Niño-Tejada, Kevin, & Patarroyo-Montenegro, Juan F. (2025). Daily Activities Wearable Dataset for Cardiorespiratory Fitness — IMU + HR + SpO2 [Zenodo, July 2025]. [Dataset]. Zenodo. https://doi.org/10.5281/ZENODO.15769101
Source: Zenodo (2025) · DOI: 10.5281/ZENODO.15769101
Indexed by IoTDataset.com on May 10, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.