4 papers
WHAR Arena: Benchmarking the State of the Art in Efficient Wearable Human Activity Recognition
Maximilian Burzer, Tobias King, Till Riedel +2
Deep learning has become the dominant paradigm in Wearable Human Activity Recognition (WHAR), yet progress is obscured by a comparability crisis. Results are often reported using i…
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
Maximilian Burzer, Till Riedel, Michael Beigl +1
Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement. Practical weara…
CHOMP: Multimodal Chewing Side Detection with Earphones
Jonas Hummel, Maximilian Burzer, Felix Schlotter +6
Chewing side preference (CSP) has been identified both as a risk factor for temporomandibular disorders (TMD) and behavioral manifestation. Despite TMDs affecting roughly one third…
WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition
Maximilian Burzer, Tobias King, Till Riedel +2
The lack of standardization across Wearable Human Activity Recognition (WHAR) datasets limits reproducibility, comparability, and research efficiency. We introduce WHAR datasets, a…