A prediction approach to COVID-19 time series with LSTM integrated attention mechanism and transfer learning
The TLLA model has the best prediction performance for the time series of COVID-19 daily confirmed cases, and the new attention mechanism and transfer learning contribute to improve the prediction performance in the flatten part and the jagged part, respectively.
Authors
- Yaohui Han (ORCID: https://orcid.org/0009-0007-2201-7283)
- Lishun Xiao (ORCID: https://orcid.org/0000-0002-0879-252X)
- Wen Gu (ORCID: https://orcid.org/0000-0001-7722-5169)
- Qingyang Zhang (ORCID: https://orcid.org/0000-0001-6076-4764)
- Bin Hu (ORCID: https://orcid.org/0000-0003-2801-9873)
- Wenhui Zhang (ORCID: https://orcid.org/0000-0002-9459-8685)
- Bi Chen
- Jun Bi (ORCID: https://orcid.org/0000-0001-6278-825X)
Institutions
- University of Nottingham (GB)
- Xuzhou Medical College (CN)
- Second Affiliated Hospital of Xuzhou Medical College (CN)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2024-12-31
- DOI
- https://doi.org/10.1186/s12874-024-02433-w
- Citations
- 7
- Primary Topic
- Anomaly Detection Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.43
Funders
- Jiangsu Commission of Health
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Xuzhou Science and Technology Bureau