The effect of training data size on real-time respiration prediction using long short-term memory model
TDS selection could influence the respiration signal prediction accuracy of the LSTM model. The relationship between TDS and the prediction accuracy of the LSTM model was not linear. The 90 s seemed to be an optimal TDS for the respiration signal prediction tasks using the LSTM model, as it was the shortest time at which a favorable prediction accuracy was maintained in this study.
Authors
- Qichun Wei
- Jing Huang (ORCID: https://orcid.org/0000-0001-8704-154X)
- Yuanpeng Zhang (ORCID: https://orcid.org/0000-0003-1736-3425)
- Wenzheng Sun (ORCID: https://orcid.org/0000-0003-2629-744X)
- Lei Zhang (ORCID: https://orcid.org/0000-0001-8749-7459)
- Chao Li (ORCID: https://orcid.org/0000-0003-1568-9704)
- Ye Liu (ORCID: https://orcid.org/0000-0003-2511-5413)
- Bing Li (ORCID: https://orcid.org/0009-0003-7645-149X)
- Kanghua Huang (ORCID: https://orcid.org/0000-0003-4504-080X)
- Jun Dang (ORCID: https://orcid.org/0000-0002-9077-6544)
Institutions
- Nantong University (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Zhengzhou University (CN)
- National Cancer Center (US)
- Henan Cancer Hospital (CN)
- Second Affiliated Hospital of Zhejiang University (CN)
- Duke Kunshan University (CN)
Publication Details
- Journal
- Radiation Oncology
- Published
- 2025-06-06
- DOI
- https://doi.org/10.1186/s13014-025-02676-x
- Primary Topic
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Hainan Province
- Natural Science Foundation of Henan Province
- Duke Kunshan University
- Basic and Applied Basic Research Foundation of Guangdong Province