Improved Prediction of Metamaterial Antenna Bandwidth Using Adaptive Optimization of LSTM

作     者：Doaa Sami Khafaga Amel Ali Alhussan El-Sayed M.El-kenawy Abdelhameed Ibrahim Said H.Abd Elkhalik Shady Y.El-Mashad Abdelaziz A.Abdelhamid 

作者机构：Department of Computer SciencesCollege of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Communications and ElectronicsDelta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial IntelligenceDelta University for Science and TechnologyMansoura35712Egypt Computer Engineering and Control Systems DepartmentFaculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Systems EngineeringFaculty of Engineering at ShoubraBenha UniversityEgypt Department of Computer ScienceFaculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer ScienceCollege of Computing and Information TechnologyShaqra University11961Saudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第73卷第10期

页      面：865-881页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R308) Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia 

主　　题：Metamaterial antenna long short term memory(LSTM) guided whale optimization algorithm(Guided WOA) adaptive dynamic particle swarm algorithm(AD-PSO) 

摘      要：The design of an antenna requires a careful selection of its parameters to retain the desired ***,this task is time-consuming when the traditional approaches are employed,which represents a significant *** the other hand,machine learning presents an effective solution to this challenge through a set of regression models that can robustly assist antenna designers to find out the best set of design parameters to achieve the intended *** this paper,we propose a novel approach for accurately predicting the bandwidth of metamaterial *** proposed approach is based on employing the recently emerged guided whale optimization algorithm using adaptive particle swarm optimization to optimize the parameters of the long-short-term memory(LSTM)deep *** optimized network is used to retrieve the metamaterial bandwidth given a set of *** addition,the superiority of the proposed approach is examined in terms of a comparison with the traditional multilayer perceptron(ML),Knearest neighbors(K-NN),and the basic LSTM in terms of several evaluation criteria such as root mean square error(RMSE),mean absolute error(MAE),and mean bias error(MBE).Experimental results show that the proposed approach could achieve RMSE of(0.003018),MAE of(0.001871),and MBE of(0.000205).These values are better than those of the other competing models.