Table 4 Top 5 countries with the best and worst performance by percentage error with Models 1 and 2.
From: A novel bidirectional LSTM deep learning approach for COVID-19 forecasting
Model 1 | |||||
|---|---|---|---|---|---|
Top 5 countries with best results | Average cases per day during prediction period | In or out of infection wave | Part of infection wave | Number of infection waves | |
1 | Singapore | 30 | Out | NA | 2 |
2 | Montenegro | 438 | In | Increasing | 4 |
3 | Belgium | 2150 | Out | NA | 2 |
4 | Congo Kinhasa | 165 | In | Declining | 2 |
5 | Slovakia | 2120 | In | Declining | 2 |
Top 5 countries with worst results | Average cases per day during prediction period | In or out of infection wave | Part of infection wave | Number of Infection waves | |
|---|---|---|---|---|---|
1 | Tajikistan | 0 | Out | NA | 1 |
2 | Central African Republic | 1 | Out | NA | 1 |
3 | Uganda | 99 | In | Declining | 2 |
4 | Cyprus | 183 | In | Declining | 2 |
5 | Australia | 10 | Out | NA | 2 |
Model 2 | |||||
|---|---|---|---|---|---|
Top 5 countries with best results | Average cases per day during prediction period | In or out of infection wave | Part of infection wave | Number of infection waves | |
1 | Pakistan | 2,040 | In | Declining | 2 |
2 | Germany | 13,914 | In | Declining | 2 |
3 | Slovakia | 2120 | In | Declining | 2 |
4 | Estonia | 507 | In | Declining | 2 |
5 | Bhutan | 4 | In | Declining | 3 |
Top 5 countries with worst results | Average cases per day during prediction period | In or out of infection wave | Part of infection wave | Number of Infection waves | |
|---|---|---|---|---|---|
1 | Tajikistan | 0 | Out | NA | 1 |
2 | Azerbaijan | 296 | In | Declining | 2 |
3 | Trinidad and Tobago | 15 | Out | NA | 2 |
4 | Switzerland | 1884 | In | Declining | 2 |
5 | Iceland | 6 | Out | NA | 3 |
