Algorithm 1.

Progressive Partial Derivative Linear feature representation.

Input: Dataset ‘DS’ time interval, ‘t’, population size, ‘N’, samples tested, ‘$S=s_1,s_2,\dots ,s_n$’

Output: computationally efficient normalized features: ‘$NF=f_1,f_2,\dots .,f_n$’

1: Begin

2: For each population size, ‘N’

3: Evaluate number of exposed ‘E(t)’ persons using Eq. (1).

4: Evaluate number of affected ‘A(t)’ persons using Eq. (2).

5: Evaluate the number of cured ‘C(t)’ persons using Eq. (3).

6: Evaluate number of dead ‘D(t)’ persons using Eq. (4).

7: Measure progressive number of cases at time ‘t’ using Eq. (5).

8: Associate describing and dependent variable using Eq. (6).

9: Evaluate first partial derivatives with respect to ‘α’ using Eq. (8).

10: Evaluate first partial derivatives with respect to ‘β’ using Eq. (9).

11: Measure ‘α’ and ‘β’ using Eqs. (10) and (11).

12: Return (α)

13: End for

14: End