Survival Prediction Model for Patients with Esophageal Squamous Cell Carcinoma Based on the Parameter-Optimized Deep Belief Network Using the Improved Archimedes Optimization Algorithm

Algorithm 2

Framework of IAOA.

Input: Initialize algorithm related parameters: the maximum number of iterations , population search boundary , parameters , , , , density (), volume (), and acceleration ().

1: The population is initialized by using the Sine chaos reverse learning strategy

2:

3: fordo

4: The and are updated by Equations (5) and (6);

5: The is calculated by Equation (7);

6: The is calculated by Equation (12);

7:

8: The is updated by Equation (8);

9: The is updated by Equation (10);

10: The position is updated by Equation (11);

11: else

12: The is updated by Equation (9);

13: The is updated by Equation (10);

14: The position is updated by Equation (13);

15: end if;

16: end for

17: The population position is perturbed according to Equation (17)

18: The position is updated when the new position is better than the previous one;

19:

20: end while

21: The global optimal solution is output