An Empirical Mode Decomposition Fuzzy Forecast Model for COVID-19

Area of Science:

• Epidemiology
• Artificial Intelligence
• Signal Analysis
• Public Health

Background:

• The COVID-19 pandemic significantly impacts global health, economies, and societies.
• Accurate prediction of epidemic development trends is crucial for effective prevention and control.
• Existing methods may struggle with the complex and variable nature of epidemic data.

Purpose of the Study:

• To develop and evaluate an artificial intelligence and signal analysis-based model for predicting epidemic trends.
• To address the challenge of unknown epidemic transmission principles by employing advanced data processing techniques.
• To provide a robust framework for enhancing public emergency health systems.

Main Methods:

• Empirical Mode Decomposition (EMD) model to smooth complex epidemic data and identify trends at various time scales.
• Extreme Learning Machine (ELM) for training time-scale trends and generating intermediate prediction values.
• Adaptive Network-based Fuzzy Inference System (ANFIS) for final epidemic prediction result fitting.

Main Results:

• The proposed algorithm demonstrates strong learning capabilities for time-series prediction.
• High accuracy rates were achieved in predicting epidemic time-series sequences.
• The method exhibits low time complexity, making it computationally efficient.

Conclusions:

• The integrated EMD-ELM-ANFIS approach offers a reliable method for epidemic trend prediction.
• This research provides theoretical support for ongoing and future epidemic prevention and control efforts.
• The findings contribute to the long-term development of robust public emergency health systems.