Abstract
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 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.
Highlights
With the advent of nature inspired computing, a variety of algorithms have been developed in the recent past
This section deals with the performance evaluation of the proposed new hybrid algorithm tunicate swarm naked mole-rat algorithm (TSNMRA) for ten 100-digit challenge (CEC 2019) test problems and real image thresholding optimization problem
The proposed methodology will be evaluated in terms of parametric evaluation of peak signal to noise ratio (PSNR), standard deviation (STD) and mean square error (MSE) along with number of iterations for segmented results
Summary
With the advent of nature inspired computing, a variety of algorithms have been developed in the recent past. Naked mole-rat algorithm (NMRA) [13] is another swarm intelligent algorithm proposed in the recent past and based upon matting pattern of mole-rats live in a single colony with size varies from 50 to 295 This colony is leaded by a single female (queen) and categorized into two types of mole-rats (workers and breeders). The queen performs breeding with best performer rats (breeders) while low performer rats (workers) perform some essential tasks Both of these algorithms have proved their worthiness and it has been found that TSA has better exploration properties due to avoidance of conflicts among various search candidates and approaching best search candidate. Been analyzed that proposed TSNMRA is better than classical NMRA and TSA for CEC 2019 test problems and GA, PSO, MTEMO and BF for image segmentation problem.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
