CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916142190166016 |
|---|---|
| author | Chan, Shing Yuan, Hang Tong, Catherine Acquah, Aidan Schonfeldt, Abram Gershuny, Jonathan Doherty, Aiden |
| author_facet | Chan, Shing Yuan, Hang Tong, Catherine Acquah, Aidan Schonfeldt, Abram Gershuny, Jonathan Doherty, Aiden |
| contents | Existing activity tracker datasets for human activity recognition are typically obtained by having participants perform predefined activities in an enclosed environment under supervision. This results in small datasets with a limited number of activities and heterogeneity, lacking the mixed and nuanced movements normally found in free-living scenarios. As such, models trained on laboratory-style datasets may not generalise out of sample. To address this problem, we introduce a new dataset involving wrist-worn accelerometers, wearable cameras, and sleep diaries, enabling data collection for over 24 hours in a free-living setting. The result is CAPTURE-24, a large activity tracker dataset collected in the wild from 151 participants, amounting to 3883 hours of accelerometer data, of which 2562 hours are annotated. CAPTURE-24 is two to three orders of magnitude larger than existing publicly available datasets, which is critical to developing accurate human activity recognition models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19229 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition Chan, Shing Yuan, Hang Tong, Catherine Acquah, Aidan Schonfeldt, Abram Gershuny, Jonathan Doherty, Aiden Human-Computer Interaction Existing activity tracker datasets for human activity recognition are typically obtained by having participants perform predefined activities in an enclosed environment under supervision. This results in small datasets with a limited number of activities and heterogeneity, lacking the mixed and nuanced movements normally found in free-living scenarios. As such, models trained on laboratory-style datasets may not generalise out of sample. To address this problem, we introduce a new dataset involving wrist-worn accelerometers, wearable cameras, and sleep diaries, enabling data collection for over 24 hours in a free-living setting. The result is CAPTURE-24, a large activity tracker dataset collected in the wild from 151 participants, amounting to 3883 hours of accelerometer data, of which 2562 hours are annotated. CAPTURE-24 is two to three orders of magnitude larger than existing publicly available datasets, which is critical to developing accurate human activity recognition models. |
| title | CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2402.19229 |