Solving Optimization Problems of Metamaterial and Double T-Shape Antennas Using Advanced Meta-Heuristics Algorithms
Doaa Sami Khafaga, Amel Ali Alhussan, El‐Sayed M. El‐kenawy, Abdelhameed Ibrahim, Marwa M. Eid, Abdelaziz A. Abdelhamid
Abstract
This study offers an adaptive dynamic sine cosine fitness grey wolf optimizer (ADSCFGWO) for optimizing the parameters of two types of antennas. The two types of antennas are metamaterial and double T-shape monopoles. The ADSCFGWO algorithm is based on an adaptive dynamic technique and two recently developed and powerful optimization techniques: a modified grey wolf optimization (GWO) based on fitness value and a sine cosine algorithm (SCA). The suggested approach utilizes the capabilities of both algorithms to balance better the exploration and exploitation responsibilities of the optimization process while achieving rapid convergence. First, a new feature selection approach is proposed to choose the most significant features from the metamaterial dataset using the suggested ADSCFGWO-based ensemble model for optimal performance. The ADSCFGWO algorithm also optimizes a bidirectional recurrent neural network (BRNN) to estimate the double T-shape monopole antenna characteristics. Several experiments were undertaken to demonstrate the superiority of the suggested algorithms by comparing their results to those of existing optimization algorithms, feature selectors, and regression models. In addition, a statistical analysis is offered to evaluate the algorithm’s effectiveness and stability. The achieved findings demonstrate the efficacy and superiority of the suggested method over numerous competing algorithms.