Video Experimental Relacionado
Updated: Feb 19, 2026
10:05
High-throughput Detection Method for Influenza Virus
Published on: February 4, 2012
26.8K
FaXNet: una red neuronal adaptativa a la frecuencia, explicable y consciente de la incertidumbre para la predicción
Wei He1,2, Xuanfeng Li1,2, Xiaolin Liang3
1Faculty of Innovation Engineering, Macau University of Science and Technology, Macao, Macao SAR, China.
Frontiers in public health
|February 18, 2026
Resumen
La predicción precisa de la influenza en China mejora con FaXNet, un novedoso marco de aprendizaje profundo. Este modelo proporciona predicciones confiables e interpretables y estimaciones de incertidumbre para la planificación de la salud pública.
Área de la Ciencia:
- Epidemiología
- Biología Computacional
- Aprendizaje Automático
Sus antecedentes:
- La predicción precisa de la influenza es crucial para la preparación de la salud pública.
- Los modelos existentes tienen dificultades con las dinámicas temporales multiescala y la estimación de la incertidumbre, especialmente en las diversas regiones climáticas de China.
- Las diferencias regionales en la estacionalidad de la influenza entre el norte y el sur de China plantean desafíos de predicción.
Objetivo del estudio:
- Desarrollar un marco de aprendizaje profundo (FaXNet) para la predicción precisa e interpretable de la influenza en China.
- Abordar los desafíos en la captura de dinámicas temporales multiescala y la provisión de estimaciones de incertidumbre confiables.
- Permitir la evaluación de riesgos y la planificación de recursos específicos de la región a través de plazos de entrega factibles.
Principales métodos:
- Se desarrolló FaXNet, un marco de aprendizaje profundo adaptativo a la frecuencia, explicable y consciente de la incertidumbre.
- Se integró la representación espectral impulsada por datos con la selección interpretable de componentes y la predicción probabilística.
- Se utilizaron tasas semanales de positividad de la influenza de China y datos meteorológicos ERA5-Land (temperatura, punto de rocío, precipitación) de 2011-2023 para las regiones del norte y del sur.
Principales resultados:
- FaXNet demostró un rendimiento superior tanto en el norte como en el sur de China en horizontes de predicción de 1 a 4 semanas.
- Se lograron altos valores de R-cuadrado, por ejemplo, 0.9319 (norte) y 0.8665 (sur) para predicciones con 1 semana de antelación.
- Las explicaciones del modelo identificaron la precipitación como un factor clave en el norte y la temperatura en el sur, validando el modelado adaptativo a la frecuencia.
Conclusiones:
- FaXNet ofrece predicciones de influenza precisas e interpretables con intervalos de predicción calibrados.
- El marco proporciona plazos de entrega factibles para la planificación de la salud pública y la asignación de recursos específicos de la región.
- El trabajo futuro puede incorporar impulsores adicionales como datos de movilidad y vacunación para mejorar la predicción.
Videos de Conceptos Relacionados
00:59Propagation of Uncertainty from Random Error
2.0K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
2.0K
01:18Steps in Outbreak Investigation
613
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
613
01:10Propagation of Uncertainty from Systematic Error
1.5K
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
1.5K
00:59Uncertainty: Overview
1.8K
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
1.8K
00:54Uncertainty: Confidence Intervals
11.8K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
11.8K
01:03Prediction Intervals
3.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.5K