Leopard seal optimization (LSO): A natural inspired meta-heuristic algorithm

Abstract

The main objective of this paper is to introduce a new NIO algorithm inspired from the hunting strategy of the leopard seals called Leopard Seal Optimization (LSO)to provide a simple swarm intelligence algorithm that have a high flexibility to solve real-time engineering problems in a fast and more accurate manner without falling into local optima problem. LSO is compared against recent NIO algorithms considering feature selection for disease diagnosing as the underlying optimization problem. In experimental results, LSO has been statistically tested against a recent six swarm intelligence algorithms using Wilcoxon test and t-test with significance level equals 0.05 based on the common five benchmark functions. These recent algorithms are called Tuna Swarm Optimization (TSO), Pelican Optimization Algorithm (POA), Cat and Mouse-Based Optimization (CMBO), Aphid–Ant Mutualism (AAM), White Shark Optimizer (WSO), and Red Piranha Optimization (RPO). The statistical analysis proved that LSO outperforms other recent techniques in most cases where the most tested results are less than 0.05. Then, LSO has been tested against the same algorithms in binary version as feature selection algorithms using two metrics called accuracy and execution time. It is noted that LSO is faster and more accurate than other algorithms to determine the optimal set of features at all numbers of search agents. Finally, it is concluded that LSO outperforms other techniques using accuracy, execution time, Wilcoxon test, and t-test metrics. Compared to the recent techniques using the maximum iteration number=400, LSO provided the maximum accuracy value that equals 97.62% at the search agents number=120 and the minimum execution time that equals 1314 at the search agents number= 40.