This paper provides a new optimization algorithm named as tunicate swarm naked mole-rat algorithm(TSNMRA)which uses hybridization concept of tunicate swarm algorithm(TSA)and naked mole-rat algorithm(NMRA).This newly d...This paper provides a new optimization algorithm named as tunicate swarm naked mole-rat algorithm(TSNMRA)which uses hybridization concept of tunicate swarm algorithm(TSA)and naked mole-rat algorithm(NMRA).This newly developed algorithm uses the characteristics of both algorithms(TSA and NMRA)and enhance the exploration abilities of NMRA.Apart from the hybridization concept,important parameter of NMRA such as mating factor is made to be self-adaptive with the help of simulated annealing(sa)mutation operator and there is no need to define its value manually.For evaluating the working capabilities of proposed TSNMRA,it is tested for 100-digit challenge(CEC 2019)test problems and real multi-level image segmentation problem.From the results obtained for CEC 2019 test problems,it can be seen that proposed TSNMRA performs well as compared to original TSA and NMRA.In case of image segmentation problem,comparison of TSNMRA is performed with multi-threshold electro magnetism-like optimization(MTEMO),particle swarm optimization(PSO),genetic algorithm(GA),bacterial foraging(BF)and found superior results for TSNMRA.展开更多
基金The authors would like to thank for the support from Taif university Researchers Supporting Project Number(TURSP-2020/114),Taif University,Taif,Saudi Arabia.
文摘This paper provides a new optimization algorithm named as tunicate swarm naked mole-rat algorithm(TSNMRA)which uses hybridization concept of tunicate swarm algorithm(TSA)and naked mole-rat algorithm(NMRA).This newly developed algorithm uses the characteristics of both algorithms(TSA and NMRA)and enhance the exploration abilities of NMRA.Apart from the hybridization concept,important parameter of NMRA such as mating factor is made to be self-adaptive with the help of simulated annealing(sa)mutation operator and there is no need to define its value manually.For evaluating the working capabilities of proposed TSNMRA,it is tested for 100-digit challenge(CEC 2019)test problems and real multi-level image segmentation problem.From the results obtained for CEC 2019 test problems,it can be seen that proposed TSNMRA performs well as compared to original TSA and NMRA.In case of image segmentation problem,comparison of TSNMRA is performed with multi-threshold electro magnetism-like optimization(MTEMO),particle swarm optimization(PSO),genetic algorithm(GA),bacterial foraging(BF)and found superior results for TSNMRA.
