WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909762661122048 |
|---|---|
| author | Burzer, Maximilian King, Tobias Riedel, Till Beigl, Michael Röddiger, Tobias |
| author_facet | Burzer, Maximilian King, Tobias Riedel, Till Beigl, Michael Röddiger, Tobias |
| contents | The lack of standardization across Wearable Human Activity Recognition (WHAR) datasets limits reproducibility, comparability, and research efficiency. We introduce WHAR datasets, an open-source library designed to simplify WHAR data handling through a standardized data format and a configuration-driven design, enabling reproducible and computationally efficient workflows with minimal manual intervention. The library currently supports 9 widely-used datasets, integrates with PyTorch and TensorFlow, and is easily extensible to new datasets. To demonstrate its utility, we trained two state-of-the-art models, TinyHar and MLP-HAR, on the included datasets, approximately reproducing published results and validating the library's effectiveness for experimentation and benchmarking. Additionally, we evaluated preprocessing performance and observed speedups of up to 3.8x using multiprocessing. We hope this library contributes to more efficient, reproducible, and comparable WHAR research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16604 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition Burzer, Maximilian King, Tobias Riedel, Till Beigl, Michael Röddiger, Tobias Human-Computer Interaction Machine Learning I.2.6 The lack of standardization across Wearable Human Activity Recognition (WHAR) datasets limits reproducibility, comparability, and research efficiency. We introduce WHAR datasets, an open-source library designed to simplify WHAR data handling through a standardized data format and a configuration-driven design, enabling reproducible and computationally efficient workflows with minimal manual intervention. The library currently supports 9 widely-used datasets, integrates with PyTorch and TensorFlow, and is easily extensible to new datasets. To demonstrate its utility, we trained two state-of-the-art models, TinyHar and MLP-HAR, on the included datasets, approximately reproducing published results and validating the library's effectiveness for experimentation and benchmarking. Additionally, we evaluated preprocessing performance and observed speedups of up to 3.8x using multiprocessing. We hope this library contributes to more efficient, reproducible, and comparable WHAR research. |
| title | WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition |
| topic | Human-Computer Interaction Machine Learning I.2.6 |
| url | https://arxiv.org/abs/2508.16604 |