TY - DATA T1 - Design of Waveguide Structures Using Improved Neural Networks PY - 2018/01/10 AU - Chahrazad Erredir AU - Mohamed Lahdi Riabi AU - Halima Ammari AU - Emir Bouarroudj UR - https://scielo.figshare.com/articles/dataset/Design_of_Waveguide_Structures_Using_Improved_Neural_Networks/5772513 DO - 10.6084/m9.figshare.5772513.v1 L4 - https://ndownloader.figshare.com/files/10180323 L4 - https://ndownloader.figshare.com/files/10180335 L4 - https://ndownloader.figshare.com/files/10180344 L4 - https://ndownloader.figshare.com/files/10180350 L4 - https://ndownloader.figshare.com/files/10180356 L4 - https://ndownloader.figshare.com/files/10180359 L4 - https://ndownloader.figshare.com/files/10180365 L4 - https://ndownloader.figshare.com/files/10180368 L4 - https://ndownloader.figshare.com/files/10180371 L4 - https://ndownloader.figshare.com/files/10180377 L4 - https://ndownloader.figshare.com/files/10180386 KW - Improved neural networks KW - modeling KW - teaching–learning-based optimization KW - waveguide filters N2 - Abstract In this paper, an improved neural networks (INN) strategy is proposed to design two waveguide filters (Pseudo-elliptic waveguide filter and Broad-band e-plane filters with improved stop-band). INN is trained by an efficient optimization algorithm called teaching–learning-based optimization (TLBO). To validate the effective of this proposed strategy, we compared the results of convergence and modeling obtained with a population based algorithm that is widely used in training NN namely Particle Swarm Optimization (PSO-NN). The results show that the proposed INN has given better results. ER -