Optimization Method for Forecasting Confirmed Cases of COVID-19 in China

Area of Science:

• Epidemiology
• Computational Intelligence
• Infectious Disease Modeling

Background:

• The COVID-19 pandemic, caused by a novel coronavirus, emerged in late 2019 and rapidly spread globally.
• Accurate forecasting of infectious disease outbreaks is crucial for public health response and resource allocation.

Purpose of the Study:

• To develop and evaluate a novel forecasting model for predicting the number of confirmed COVID-19 cases.
• To enhance the performance of the adaptive neuro-fuzzy inference system (ANFIS) for disease prediction.

Main Methods:

• A new hybrid optimization algorithm, the Flower Pollination Algorithm optimized by the Salp Swarm Algorithm (FPASSA), was developed.
• The FPASSA algorithm was used to optimize the parameters of the ANFIS model, creating the FPASSA-ANFIS model.
• The FPASSA-ANFIS model was trained and validated using official COVID-19 case data from the World Health Organization (WHO).

Main Results:

• The FPASSA-ANFIS model demonstrated superior performance compared to existing models in forecasting COVID-19 confirmed cases.
• Performance was evaluated using metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Squared Relative Error (RMSRE), and coefficient of determination (R²).
• The model also showed good performance when tested on weekly influenza case data from the USA and China.

Conclusions:

• The proposed FPASSA-ANFIS model offers a robust and accurate approach for short-term forecasting of infectious disease outbreaks like COVID-19.
• The hybrid optimization strategy effectively improves ANFIS performance, addressing limitations like local optima entrapment.
• This model has potential applications in public health surveillance and pandemic preparedness.