Robust Prediction of the Bandwidth of Metamaterial Antenna Using Deep Learning

作     者：Abdelaziz A.Abdelhamid Sultan R.Alotaibi 

作者机构：Department of Computer ScienceCollege of Computing and Information TechnologyShaqra UniversityShaqraSaudi Arabia Department of Computer ScienceCollege of Science and Human StudiesShaqra UniversitySaudi Arabia Department of Computer ScienceFaculty of Computer and Information SciencesAin Shams UniversityEgypt 

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

年 卷 期：2022年第72卷第8期

页      面：2305-2321页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081001[工学-通信与信息系统] 

基　　金：The authors extend their appreciation to the Deputyship for Research&Innovation Ministry of Education in Saudi Arabia for funding this research work through the Project Number(IFP2021-033) 

主　　题：Metamaterial antenna deep learning bandwidth prediction regression models 

摘      要：The design ofmicrostrip antennas is a complex and time-consuming process,especially the step of searching for the best design ***,the performance ofmicrostrip antennas can be improved usingmetamaterial,which results in a new class of antennas called metamaterial *** parameters affect the radiation loss and quality factor of this class of antennas,such as the antenna ***,the optimal values of the design parameters of metamaterial antennas can be predicted using machine learning,which presents a better alternative to simulation tools and trialand-error ***,the prediction accuracy depends heavily on the quality of the machine learning *** this paper,and benefiting from the current advances in deep learning,we propose a deep network architecture to predict the bandwidth of metamaterial *** results show that the proposed deep network could accurately predict the optimal values of the antenna bandwidth with a tiny value of mean-square error(MSE).In addition,the proposed model is comparedwith current competing approaches that are based on support vector machines,multi-layer perceptron,K-nearest neighbors,and ensemble *** results show that the proposed model is better than the other approaches and can predict antenna bandwidth more accurately.