SynHAR: Augmenting Human Activity Recognition With Synthetic Inertial Sensor Data Generated From Human Surface Models

Lena Uhlenberg, Lars Ole Haeusler, Oliver Amft (Hahn-Schickard / University of Freiburg)

Summary

Amft-lab SynHAR synthesises IMU time series from combined personalised biomechanical dynamics models and human surface models, then uses that synthetic ACC/gyro to augment HAR training (not synthetic-only foundation pretrain). Two scenarios: (1) fuse synthetic + measured IMU for direct HAR training; (2) pretrain on synthetic+measured then transfer-learn on public benchmarks. Low-data configs (fewer participants / IMUs) are stress-tested.