Detection of COVID-19 Using Protein Sequence Data via Machine Learning Classification Approach

Table 3

Feature subset and fitness function using genetic algorithm.

Running	Feature subset	Total number of features	Fitness value (%)
1	1, 2, 7, 10, 11, 13, 18, 19, 21, 22, 24, 25	12	93.85
2	7, 8, 10, 11, 12, 17, 19, 22, 24, 25, 26, 27	12	93.9
3	2, 7, 10, 11, 12, 18, 19, 25, 26, 27	10	94.3
4	2, 4, 7, 10, 11, 14, 19, 23, 24, 25	10	93.85
5	1, 7, 10, 11, 13, 14, 17, 19, 23, 25	10	94.25
6	7, 8, 10, 11, 14, 17, 18, 22, 25, 26, 27	11	93.95
7	5, 7, 10, 11, 16, 17, 22, 25, 26	9	94.15
8	1, 2, 4, 7, 8, 10, 11, 12, 14, 16, 22, 24, 25	13	93.9
9	2, 4, 7, 10, 11, 17, 22, 23, 24, 25, 27	11	94.5
10	2, 4, 5, 7, 10, 11, 15, 19, 25	9	94

We have selected the 11 features with the highest fitness scores, which are indicated in boldface.