Full
Outline
To explore the application of the advanced LSTM-Informer model in predicting and early warning of pulmonary tuberculosis incidence, providing a reference for relevant authorities to formulate prevention and control measures, and offering new methodologies and insights for forecasting other infectious diseases.
Pulmonary tuberculosis incidence data for Jining City from January 1, 2010, to December 31, 2022, were obtained from the National Notifiable Disease Reporting System (NNDRS). Monthly incidence rates were calculated by integrating demographic data from the Jining Statistical Yearbook (2010—2022). The final 12, 18, and 24 months of data were used as test sets to evaluate model performance, with the remaining data constituting the training set. The LSTM-Informer model was constructed and its reliability assessed through comparison with standalone LSTM and Informer models.
The predictive performance of the three models across different forecast horizons was evaluated using error metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the Coefficient of Determination(R2). Results demonstrated that the LSTM-Informer model consistently outperformed the single models. In the prediction of the 12-month length, the MSE of the model was 0.028, which was 59.4% lower than that of LSTM, the MAE value of 0.155 was 34.0% lower than that of LSTM, and the R2 value was 0.850. When the forecast horizon extended to 18 months, the model maintained a stable MAPE of 0.104 and an R2 of 0.808. Even at the 24-month horizon, the LSTM-Informer model retained significant advantages(R2=0.782).
Compared to single models, the LSTM-Informer model, leveraging both local and global feature extraction, significantly enhances prediction accuracy for medium-to-long-term forecasts. It shows considerable promise for providing novel theoretical support and reference for developing pulmonary tuberculosis incidence early-warning systems locally.
46
23
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
