Research Article
Detection of COVID-19 Using Protein Sequence Data via Machine Learning Classification Approach
Table 7
Average sensitivity of different models for different training percentage.
| | Training percentage | GA+KNN | SVM-RFE+KNN | LASSO+KNN | GA+Naïve Bayes | SVM-RFE+Naïve Bayes | LASSO+Naïve Bayes | GA+XGBoost | SVM-RFE+XGBoost | LASSO+XGBoost |
| | 60% | 94.04% | 98.99% | 97.61% | 71.87% | 75.12% | 71.22% | 91.16% | 96.48% | 92.15% | | 70% | 94.13% | 99.34% | 97.29% | 71.45% | 75.79% | 72.53% | 93.75% | 96.64% | 93.83% | | 80% | 93.87% | 99.51% | 96.97% | 71.93% | 76.15% | 74.58% | 92.56% | 96.88% | 93.67% | | 90% | 95.78% | 99.55% | 96.17% | 72.07% | 76.46% | 71.97% | 92.91% | 95.92% | 93.34% |
|
|
Highest sensitivity achieved at a training percentage of 90% using the SVM-RFE+KNN model, reaching 99.55%, as observed from the boldfaced entries.
|
