ErgoPose-DeskWork: Ergonomic Sitting Posture Dataset for Machine Learning Classification

ErgoPose-DeskWork Dataset A labeled dataset of seated human postures for machine learning classification, developed for ergonomic risk detection in desk-based environments (e.g., IT professionals, gamers). Description This dataset contains 200 labeled observations of seated posture (ideal vs non-ideal), with features extracted using MediaPipe Pose. Data were collected in July 2024 during controlled posture observation sessions. Features: Neck angle Back angle Arm angle Leg angle Shoulder height difference Sitting duration Label: ideal: ergonomically correct posture non-ideal: postures deviating from ISO/NIOSH standards Access 📦 Zenodo: https://doi.org/10.5281/zenodo.15250540 💾 IEEE DataPort: https://ieee-dataport.org/documents/ergopose-deskwork Both versions are synchronized and contain the same dataset and metadata. License This dataset is released under Creative Commons Attribution 4.0 International (CC BY 4.0). Acknowledgment Developed by AONO Research and Consultant. We thank all contributors and participants involved in the data preparation process.