Table 2.
Proposed solution approaches for forecasting coronavirus 2019 (COVID-19)
| Algorithm | ||||||||
|---|---|---|---|---|---|---|---|---|
| Epidemic models | Time-series models | Nature-inspired algorithms | ||||||
| SIR | [11] | Autoregressive model | Moving average | Autoregressive integrated moving average [19, 22, 26, 30, 31] | Genetic programming [30–34] | |||
| Simple moving average [23] | ||||||||
| Other models | [35] | |||||||
| SEIR | [12, 36] | Exponential models | Logistic growth model [24, 37, 38] | Flower pollination algorithm [29] | ||||
| SIRD | [13, 14] | Deep learning | Long short-term memory (LSTM) networks [25] | Polynomial Neural Network [39] | ||||
| Neural network [31, 40] | Ecological Niche models [41] | |||||||
| Regression methods | [42–44] | |||||||
| Prophet algorithm | [45] | |||||||
| Phenomenological model | [46] | Other models | Adaptive neuro-fuzzy inference system [29] | Regression tree algorithm [22] | Support vector machine [39, 47] | Iteration method [48] | Support vector Kuhn-tucker [47] | |