Abstract
In order to overcome some defects of the traditional immune algorithm, the immune algorithm was improved for solving a path optimization problem in deep immune learning of a gene network. Firstly, the diversity of the solution population was enhanced in the evolution process by improving the memory cell processing method. Moreover, effective gene information was dynamically extracted from the genes of the excellent antibodies to make good vaccines in the process of immune evolution. Worse antibodies were optimized by vaccinating these antibodies, and the convergence of the immune algorithm to the optimal solution was improved. Finally, the feasibility of the improved immune algorithm was verified in the experimental simulation for solving the classic NP problem in deep immune learning of the gene network.
Highlights
The biological immune system is a complex distributed information-processing/ learning system with good inherent advantages such as diversity, adaptability, immune tolerance, and immune memory
In order to overcome some defects of the traditional immune algorithm, the immune algorithm was improved for solving a path optimization problem in deep immune learning of a gene network
The feasibility of the improved immune algorithm was verified in the experimental simulation for solving the classic NP problem in deep immune learning of the gene network
Summary
The biological immune system is a complex distributed information-processing/ learning system with good inherent advantages such as diversity, adaptability, immune tolerance, and immune memory. Inspired by the biological immune system, intelligent optimization algorithms simulate the complex information processing mechanisms of immune system, such as identification, learning, memory and etc. The robustness of the immune algorithm is better in solving the distributed complex problems, with better intelligence and better convergence to the global optimal solution in the solution-searching procedure [1]. The dynamic vaccine extraction strategy was adopted to improve the immune algorithm for solving the TSP problem [8]. Step 8: Antibody group updating: A new antibody is randomly generated to form a new antibody group with a high affinity antibody in the original antibody group, and the process returns to step 3
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have