Evaluating the effectiveness of self-attention mechanism in tuberculosis time series forecasting
Zhihong Lv, Rui Sun, Xin Liu, Shuo Wang, Xiaowei Guo, Yuan Lv, Min Yao, Junhua Zhou · 2024
Read Evaluating the effectiveness of self-attention mechanism in tuberculosis time series forecasting by Zhihong Lv, Rui Sun, Xin Liu, Shuo Wang, Xiaowei Guo, Yuan Lv, Min Yao, Junhua Zhou (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11613505.txt.
Description
Zhihong Lv and co-authors test whether a self-attention model can forecast tuberculosis cases better than older time series tools, in a 2024 study. Monthly case counts from one Chinese city across twelve years were fed to three rivals: the attention model, a memory-based neural network, and a classic statistical forecaster. Accuracy was judged on held-out data by three error measures.
The attention model won on all three, cutting error by roughly a tenth against the neural rival and by about a third against the statistical one. The authors offer it to health departments for planning beds, drugs, and staff. Attention, they argue, reads the rhythm of the disease better.
Catalog record
| CREATOR | Zhihong Lv, Rui Sun, Xin Liu, Shuo Wang, Xiaowei Guo, Yuan Lv, Min Yao, Junhua Zhou |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |