Hostname: page-component-cd9895bd7-jkksz Total loading time: 0 Render date: 2024-12-18T12:12:39.890Z Has data issue: false hasContentIssue false
  • English
  • Français

Hyperparameters optimization of neural network using improved particle swarm optimization for modeling of electromagnetic inverse problems

Published online by Cambridge University Press:  17 December 2021

Debanjali Sarkar ,
Taimoor Khan Open the ORCID record for Taimoor Khan [Opens in a new window]  and
Fazal Ahmed Talukdar
Debanjali Sarkar
Affiliation:
Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, India
Taimoor Khan*
Affiliation:
Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, India
Fazal Ahmed Talukdar
Affiliation:
Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, India
*
Author for correspondence: Taimoor Khan, E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Optimization of hyperparameters of artificial neural network (ANN) usually involves a trial and error approach which is not only computationally expensive but also fails to predict a near-optimal solution most of the time. To design a better optimized ANN model, evolutionary algorithms are widely utilized to determine hyperparameters. This work proposes hyperparameters optimization of the ANN model using an improved particle swarm optimization (IPSO) algorithm. The different ANN hyperparameters considered are a number of hidden layers, neurons in each hidden layer, activation function, and training function. The proposed technique is validated using inverse modeling of two meander line electromagnetic bandgap unit cells and a slotted ultra-wideband antenna loaded with EBG structures. Three other evolutionary algorithms viz. hybrid PSO, conventional PSO, and genetic algorithm are also adopted for the hyperparameter optimization of the ANN models for comparative analysis. Performances of all the models are evaluated using quantitative assessment parameters viz. mean square error, mean absolute percentage deviation, and coefficient of determination (R2). The comparative investigation establishes the accurate and efficient prediction capability of the ANN models tuned using IPSO compared to other evolutionary algorithms.

Keywords

Artificial neural network (ANN)electromagnetic bandgap (EBG)genetic algorithm (GA)monopole antennaparticle swarm optimization (PSO)ultra-wideband (UWB)
Type
Antenna Design, Modelling and Measurements
Information
International Journal of Microwave and Wireless Technologies , Volume 14 , Issue 10 , December 2022 , pp. 1326 - 1337
Check for updates
Copyright
Copyright © The Author(s), 2021. Published by Cambridge University Press in association with the European Microwave Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Nikookar, H and Prasad, R (2009) Introduction to Ultra Wideband for Wireless Communications. Dordrecht, The Netherlands: Springer.Google Scholar
Ghahremani, M, Ghobadi, C, Nourinia, J, Ellis, MS, Alizadeh, F and Mohammadi, B (2019) Miniaturized UWB antenna with dual-band rejection of WLAN/WiMAX using slitted EBG structure. IET Microwaves, Antennas & Propagation 13, 360–366.CrossRefGoogle Scholar
Yadav, D, Abegaonkar, MP, Koul, SK, Tiwari, V and Bhatnagar, D (2018) A compact dual band-notched UWB circular monopole antenna with parasitic resonators. International Journal of Electronics Communications 84, 313–320.Google Scholar
Lee, DH, Yang, HY and Cho, YK (2014) Ultra-wideband tapered slot antenna with dual band-notched characteristics. IET Microwaves, Antennas & Propagation 8, 29–38.CrossRefGoogle Scholar
Alam, MS, Islam, MT and Misran, N (2012) A novel compact split ring slotted electromagnetic bandgap structure for microstrip patch antenna performance enhancement. Progress in Electromagnetics Research 130, 389–409.Google Scholar
Bhavarthe, PP, Rathod, SS and Reddy, KTV (2017) A compact two via slot-type electromagnetic bandgap structure. IEEE Microwave and Wireless Components Letters 27, 446–448.CrossRefGoogle Scholar
Bhavarthe, PP, Rathod, SS and Reddy, KTV (2019) A compact dual-band gap electromagnetic band gap structure. IEEE Transactions on Antennas and Propagation 67, 596–600.CrossRefGoogle Scholar
Dalal, P and Dhull, SK (2020) Upper WLAN band-notched UWB monopole antenna using compact two via slot electromagnetic band gap structure. Progress In Electromagnetics Research C 100, 161–171.CrossRefGoogle Scholar
Wang, Z and Fang, S (2014) ANN synthesis model of single-feed corner-truncated circularly polarized microstrip antenna with an air gap for wideband applications. International Journal of Antennas and Propagation 2014, 1–7.Google Scholar
Gosal, G, Almajali, E, McNamara, D and Yagoub, M (2016) Transmitarray antenna design using forward and inverse neural network modeling. IEEE Antennas and Wireless Propagation Letters 15, 1483–1486.CrossRefGoogle Scholar
Xiao, LY, Shao, W, Jin, FL and Wang, BZ (2018) Multiparameter modeling with ANN for antenna design. IEEE Transactions on Antennas and Propagation 66, 3718–3723.CrossRefGoogle Scholar
Kapetanakis, TN, Vardiambasis, IO, Ioannidou, MP and Maras, A (2018) Neural network modeling for the solution of the inverse loop antenna radiation problem. IEEE Transactions on Antennas and Propagation 66, 6283–6290.CrossRefGoogle Scholar
Ustun, D, Toktas, A and Akdagli, A (2019) Deep neural network-based soft computing the resonant frequency of E–shaped patch antennas. International Journal of Electronics Communications 102, 54–61.CrossRefGoogle Scholar
Sarkar, D, Khan, T and Laskar, RH (2020) Multi-parametric ANN modelling for interference rejection in UWB antennas. International Journal of Electronics 107, 2068–2083.Google Scholar
Bergstra, J, Bardenet, R, Bengio, Y and Kegl, B (2011) Algorithms for hyperparameter optimization. Advances in Neural Information Processing Systems 24, 2546–2554.Google Scholar
Bergstra, J and Bengio, Y (2012) Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, 281–305.Google Scholar
Assuncao, F, Lourenco, N, Machado, P and Ribeiro, B. Automatic generation of neural networks with structured grammatical evolution. 2017 IEEE Congress on Evolutionary Computation, San Sebastian, 1557–1564.Google Scholar
Zhang, S, Wang, H, Liu, L, Du, C and Lu, J. Optimization of neural network based on genetic algorithm and BP. 2014 International Conference on Cloud Computing and Internet of Things, Changchun, 203–207.Google Scholar
Itano, F, Sousa, MADAD and Hernandez, EDM. Extending MLP ANN hyper-parameters optimization by using genetic algorithm. 2018 International Joint Conf on Neural Networks, 1–8.Google Scholar
Wang, S, Roger, M, Sarrazin, J and Perrault, CL (2019) Hyperparameter optimization of two-hidden-layer neural networks for power amplifiers behavioral modeling using genetic algorithms. IEEE Microwave and Wireless Components Letters 29, 802–805.CrossRefGoogle Scholar
Johnson, F, Valderrama, A, Valle, C, Crawford, B, Soto, R and Nanculef, R (2020) Automating configuration of convolutional neural network hyperparameters using genetic algorithm. IEEE Access 8, 156139–156152.CrossRefGoogle Scholar
Kim, TY and Cho, SB. Particle swarm optimization-based CNN-LSTM networks for forecasting energy consumption. 2019 IEEE Congress on Evolutionary Computation, 1510–1516.Google Scholar
Ye, F (2017) Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data. PLoS One 12, 1–36.CrossRefGoogle ScholarPubMed
Lorenzo, PR, Nalepa, J, Kawulok, M, Ramos, LS and Pastor, JR (2017) Particle swarm optimization for hyper-parameter selection in deep neural networks. Genetic and Evolutionary Computation Conference, Berlin, Germany 2017.CrossRefGoogle Scholar
Sun, C, Li, C, Liu, Y, Liu, Z, Wang, X and Tan, J (2019) Prediction method of concentricity and perpendicularity of aero-engine multistage rotors based on PSO-BP neural network. IEEE Access 7, 132271–132278.CrossRefGoogle Scholar
Zaharis, ZD, Gravas, IP, Yioultsis, TV, Laziridis, PI, Glover, IA, Skeberis, C and Xenos, TD (2017) Exponential log-periodic antenna design using improved particle swarm optimization with velocity mutation. IEEE Transactions on Magnetics 53, 1–4.CrossRefGoogle Scholar
Gravas, IP, Zaharis, ZD, Lazaridis, PI, Yioultsis, TV, Kantartzis, NV, Antonopoulos, CS, Chochliouros, IP and Xenos, TD (2020) Optimal design of aperiodic reconfigurable antenna array suitable for broadcasting applications. Electronics 9, 818.Google Scholar
Reddaf, A, Djerfaf, F, Ferroudji, K, Boudjerda, M, Hamdi-Chérif, K and Bouchachi, I (2019) Design of dual-band antenna using an optimized complementary split-ring resonator. Applied Physics A: Solids and Surfaces 125, 1–9.CrossRefGoogle Scholar
Gravas, IP, Sifakis, NF, Zaharis, ZD, Lazaridis, PI and Xenos, TD (2020) Optimal fractal antenna for in-vehicle entertainment application. Wireless Telecommunications Symposium, 1–5.Google Scholar
Zaharis, ZD, Gravas, IP, Lazaridis, PI, Glover, IA, Antonopoulos, CS and Xenos, TD (2018) Optimal LTE-protected LPDA design for DVB-T reception using particle swarm optimization with velocity mutation. IEEE Transactions on Antennas and Propagation 66, 3926–3935.CrossRefGoogle Scholar
Karystinos, GN and Pados, DA (2000) On overfitting, generalization, and randomly expanded training sets. IEEE Transactions on Neural Networks and Learning Systems 11, 1050–1057.CrossRefGoogle ScholarPubMed
Kwok, TY and Yeung, DY (1995) Efficient cross-validation for feedforward neural networks. International Conference on Neural Networks, Australia 1995.Google Scholar
Rahman, M, Jahromi, MN, Mirjavadi, SS and Hamouda, AM (2019) Compact UWB band-notched antenna with integrated bluetooth for personal wireless communication and UWB applications. Electronics 8, 1–13.CrossRefGoogle Scholar
Li, WT, Hei, YQ, Feng, W and Shi, XW (2012) Planar antenna for 3G/Bluetooth/WiMAX and UWB applications with dual band-notched characteristics. IEEE Antennas and Wireless Propagation Letters 11, 61–64.Google Scholar
Srivastava, K, Ashwani, K, Kanaujia, BK, Dwari, S, Verma, AK, Esselle, KP and Mittra, R (2018) Integrated GSM-UWB Fibonacci-type antennas with single, dual, and triple notched bands. IET Microwaves, Antennas & Propagation 12, 1004–1012.CrossRefGoogle Scholar
Iqbal, A, Smida, A, Mallat, NK, Islam, MT and Kim, S (2019) A compact UWB antenna with independently controllable notch bands. Sensors 19, 1–12.CrossRefGoogle ScholarPubMed
Jin, N and Samii, YR (2010) Hybrid real-binary particle swarm optimization (HPSO) in engineering electromagnetics. IEEE Transactions on Antennas and Propagation 58, 3786–3794.CrossRefGoogle Scholar
Sengupta, S, Basak, S and Peters, RA (2018) Particle swarm optimization: a survey of historical and recent developments with hybridization perspectives. Machine Learning and Knowledge Extraction 1, 157–191.CrossRefGoogle Scholar
Mirjalili, S, Song Dong, J, Sadiq, AS and Faris, H (2020) Genetic algorithm: theory, literature review, and application in image reconstruction. In Mirjalili, S, Song Dong, J and Lewis, A (eds), Nature-Inspired Optimizers, Studies in Computational Intelligence, vol. 811. Cham: Springer, pp. 69–85.Google Scholar