Journal of advanced research · 2026
Dynamic feature selection improves influenza forecasting accuracy and generalization across countries.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Liang Jingyi, Zeng Zhiqi, Liao Kai, Liao Min, Fang Zhonghao, Kong Lesi, Feng Jianlin, Yu Na, Lin Zhengshi, Hon Chitin, Oliveira Arlindo, Yang Zifeng
Аннотация
INTRODUCTION: The differentiation in epidemic patterns and multiple influencing factors pose significant challenges to influenza forecasting, highlighting the need for novel methods to improve predictive accuracy and cross-regional generalizability.
OBJECTIVES: This study aims to develop an adaptive feature selection model named AdaFluDR to address the time-varying nature of influenza transmission drivers across different periods and regions.
METHODS: AdaFluDR integrates the SpaceTime and Crossformer models and utilizes a correlation-driven mechanism. This mechanism constructs a comprehensive score by integrating the temporal, frequency, and time domain information of features, and dynamically adjusts feature processing pathways based on this score. Subsequently, a multilayer perceptron (MLP) will be employed to model the nonlinear mapping relationship between the integrated features and the target variable for prediction generation.
RESULTS: The AdaFluDR model outperforms traditional methods and other machine learning approaches, demonstrating robust predictive performance across multiple forecasting horizons (1-4 weeks), and strong generalization ability across the United States, Canada, and Portugal.
CONCLUSION: Our study provides a novel and practical framework for forecasting influenza activity with reliable accuracy and cross-national applicability, providing a valuable tool for improving global epidemic preparedness and response strategies.
OBJECTIVES: This study aims to develop an adaptive feature selection model named AdaFluDR to address the time-varying nature of influenza transmission drivers across different periods and regions.
METHODS: AdaFluDR integrates the SpaceTime and Crossformer models and utilizes a correlation-driven mechanism. This mechanism constructs a comprehensive score by integrating the temporal, frequency, and time domain information of features, and dynamically adjusts feature processing pathways based on this score. Subsequently, a multilayer perceptron (MLP) will be employed to model the nonlinear mapping relationship between the integrated features and the target variable for prediction generation.
RESULTS: The AdaFluDR model outperforms traditional methods and other machine learning approaches, demonstrating robust predictive performance across multiple forecasting horizons (1-4 weeks), and strong generalization ability across the United States, Canada, and Portugal.
CONCLUSION: Our study provides a novel and practical framework for forecasting influenza activity with reliable accuracy and cross-national applicability, providing a valuable tool for improving global epidemic preparedness and response strategies.