An improved naked-mole rat algorithm for numerical optimization.

Naked mole-rat algorithm (NMRA) is a recently developed swarm intelligence-based algorithm that is inspired by mole rats' (workers and breeders) mating behaviour. This algorithm has been used to solve optimization problems and is based on breeding capability of breeders to breed with the queen. However, the algorithm has issues with inadequate exploration and less speed of convergence to optimal solution. The improved NMRA (INMRA) is proposed in this research to boost its exploration's ability. The new version is based on trigonometric mutation and used for generation of new worker solution This attribute has been introduced to increase NMRA's exploration properties by keeping the search agents diverse. On CEC2005 benchmark problems, the proposed technique INMRA was tested and demonstrate its superiority to other algorithms, including well-known algorithms such as whale optimization based on opposition learning (OEWOA), differential evolution with self-adaptive properties (SaDE), external archive based differential evolution (JADE), extended grey wolf optimization (GWO-E), hybrid sine cosine crow search algorithm and NMRA. Further, performance of proposed version is also better than the original NMRA for CEC 2019 test problems according to the experimental data. The results are further validated by statistical testing and convergence profiles. [ABSTRACT FROM AUTHOR]