A deep hybrid learning framework with attention-enhanced feature extraction for BMI prediction based on physical fitness
This study establishes the first unified solution for fitness-informed BMI prediction, though limited by male-only sampling. Implementation should prioritize integration with campus health systems and expansion to diverse populations. Future work should incorporate psychosocial factors and multi-regional validation.
Authors
- Ye Yang (ORCID: https://orcid.org/0000-0003-0228-5102)
- Guoqing Wu (ORCID: https://orcid.org/0000-0003-4812-8890)
- Jinfeng Deng
- Jun Wang (ORCID: https://orcid.org/0000-0001-9223-2615)
- Wen Luo (ORCID: https://orcid.org/0000-0001-5298-8557)
- Libo Xie
- Qiao Hu (ORCID: https://orcid.org/0000-0002-6483-1431)
- Tingting Jiao (ORCID: https://orcid.org/0009-0008-9785-5959)
- M. Mo
- Xuyin Xu
Institutions
- Hunan University (CN)
- Education Department of Hunan Province (CN)
- Department of Science and Technology of Hunan Province (CN)
- Hunan First Normal University (CN)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-09-02
- DOI
- https://doi.org/10.3389/fpubh.2025.1640226
- Primary Topic
- Physical Activity and Health
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province