Abstract
Gaussian process (GP) is a multi-layer perceptron neural network (NN) with infinite units in its hidden layer that could learn effectively, so as a machine learning (ML) method, it has been a sought-after surrogate model in electromagnetics (EM) field. GP can implement complex covariance functions or insert itself into a more complicated probability structure to improve predictive function. When handling the high-dimensional data, however, GP still causes some problems, e.g., precise and efficiency degradation. Hence, we propose a dimension reduction network structure based on GP to strengthen its ability of feature extraction and apply the approach into the inverse surrogate models of microwave devices. In this model, the compressed representation process of input features is dependent on a multi-layer extreme learning machine (ML-ELM), which stacks multiple ELMs-based autoencoders (AEs) by nonorthogonal random parameters including weights and biases of hidden layers. The novelties of this paper are as follows: (1) enormous unlabeled data satisfied with designed requirements are generated randomly, and they are then used to train the parameters of ML-ELM except the last layer to improve its performance, instead of random determination of its weights and biases; (2) parameters of the last layer of the ML-ELM and hyperparameters of GP are fine-tuned by particle swarm optimization (PSO) algorithm based on some labeled data; and (3) we also study on the ML-ELM architecture deeply and draw some rewarding conclusions based on different experimental results of some typical testing functions. Empirical study on the triple-band microwave antenna demonstrates that compared with GP, predictive accuracy of the proposed method is high, considering about compressing for dimensionality of the same data.
Similar content being viewed by others
References
Ding WT, Tian YB, Li PF et al (2022) Antenna optimization based on master-apprentice broad learning system. Int J Mach Learn Cybern 13(2):461–470
Khatab ZE, Gazestani AH, Ghorashi SA et al (2021) A fingerprint technique for indoor localization using autoencoder based semi-supervised deep extreme learning machine. Signal Process 181:107915
Xiao LY, Shao W, Ding X et al (2019) Multigrade artificial neural network for the design of finite periodic arrays. IEEE Trans Antennas Propag 67(5):3109–3116
Fourati H, Maaloul R, Chaari L (2021) A survey of 5G network systems: challenges and machine learning approaches. Int J Mach Learn Cybern 12(2):385–431
Pitra Z, Bajer L, Holena M (2015) Comparing SVM, gaussian process and random forest surrogate models for the CMA-ES. In: ITAT (pp 186–193), Slovensky Raj, Slovakia
Sun FY, Tian YB, Ren ZL (2016) Modeling the resonant frequency of compact microstrip antenna by the PSO-based SVM with the hybrid kernel function. Int J Numer Model Electron Networks Devices Fields 29(6):1129–1139
Fu H, Vong CM, Wong PK et al (2016) Fast detection of impact location using kernel extreme learning machine. Neural Comput Appl 27(1):121–130
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Zhu J, Fox JJ, Yi N et al (2019) Structural design for stretchable microstrip antennas. ACS Appl Mater Interfaces 11(9):8867–8877
Zhang G, Cui D, Mao S et al (2020) Unsupervised feature learning with sparse Bayesian auto-encoding based extreme learning machine. Int J Mach Learn Cybern 11(7):1557–1569
Wilson A, Nickisch H (2015) Kernel interpolation for scalable structured Gaussian processes (KISS-GP). In: International In: Conference on Machine Learning (pp 1775–1784), Lille, France
Bajer L, Pitra Z, Repický J et al (2019) Gaussian process surrogate models for the CMA evolution strategy. Evol Comput 27(4):665–697
Burt D, Rasmussen CE, Van Der Wilk M (2019) Rates of convergence for sparse variational Gaussian process regression. In: International Conference on Machine Learning (pp 862–871), Taiwan, China
Rasmussen CE (2003) Gaussian processes in machine learning. In: Summer school on machine learning (pp 63–71). Springer, Berlin, Heidelberg
Jacobs JP (2015) Efficient resonant frequency modeling for dual-band microstrip antennas by gaussian process regression. IEEE Trans Antennas Propag 14(3):337–341
Cardona HDV, Orozco ÁA, Álvarez MA (2016) Multi-output Gaussian processes for enhancing resolution of diffusion tensor fields. In: The 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp 1111–1114), Florida, USA
Fan X, Tian YB, Zhao Y (2018) Optimal design of microwave devices by fitness-estimation-based particle swarm optimization algorithm. Appl Comput Electromagn Soc J 33(11):1259–1267
Wilson AG, Hu Z, Salakhutdinov R, et al (2016) Deep kernel learning Artificial intelligence and statistics. In: PMLR (pp 370–378), New York, USA
Huang G, Song S, Gupta JND et al (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 44(12):2405–2417
Kasun LLC, Zhou H, Huang GB et al (2013) Representational learning with ELMs for big data. Intell Syst 28(6):31–34
Vincent P, Larochelle H, Lajoie I, et al (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11(12).
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786): 504–507
Kasun LLC, Yang Y, Huang GB et al (2016) Dimension reduction with extreme learning machine. IEEE Trans Image Process 25(8):3906–3918
Abu AO, Abo-Hammour Z, Momani S et al (2012) Solving singular two-point boundary value problems using continuous genetic algorithm. Abstr Appl Anal 2012:25
Abo-Hammour Z, Abu AO, Momani S et al (2014) Optimization solution of Troesch’s and Bratu’s problems of ordinary type using novel continuous genetic algorithm. Discret Dyn Nat Soc 2014:15
Arqub AO, Abo-Hammour Z (2014) Numerical solution of systems of second-order boundary valueproblems using continuous genetic algorithm. Inf Sci 279:396–415
Abo-Hammour Z, Arqub AO, Alsmadi O et al (2014) An optimization algorithm for solving systems of singular boundary value problems. Appl Math Inform Sci 8(6):2809–2821
Chen XZ, Tian YB, Zhang TL et al (2020) Differential evolution based manifold Gaussian process machine learning for microwave Filter’s parameter extraction. IEEE Access 8:146450–146462
Fan J, Zhang Q, Zhu J et al (2020) Robust deep auto-encoding Gaussian process regression for unsupervised anomaly detection. Neurocomputing 376:180–190
Eberhart R, Kennedy J (1995) Particle swarm optimization. In: IEEE international conference on neural networks (pp 1942–1948), Perth, Western Australia
Marini F, Walczak B (2015) Particle swarm optimization (PSO). A tutorial-ScienceDirect. Chemom Intell Lab Syst 149:153–165
Williams CK, Rasmussen CE (2006) Gaussian processes for machine learning. MIT press, Cambridge
Chakraborty S, Chowdhury R (2019) Graph-theoretic-approach-assisted Gaussian process for nonlinear stochastic dynamic analysis under generalized loading. J Eng Mech 145(12):04019105
Kuipers L, Niederreiter H (2012) Uniform distribution of sequences. Courier Corporation
Jorgensen B (2012) Statistical properties of the generalized inverse Gaussian distribution. Springer
Kiche J, Ngesa O, Orwa G (2019) On generalized gamma distribution and its application to survival data. Int J Stat Prob 8(5):85–102
Floudas CA, Pardalos PM, Adjiman C, et al (2013) Handbook of test problems in local and global optimization. Springer
Molga M, Smutnicki C (2005) Test functions for optimization needs. Test Funct Optim Needs 101:48
Back T (1996) Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms. Oxford University Press
Dixon LCW (1978) The global optimization problem. An introduction. Toward Global Optim 2:1–15
PichenyV WT, Ginsbourger D (2013) A benchmark of kriging-based infill criteria for noisy optimization. Struct Multidiscip Optim 48(3):607–626
Kumar A, Jhanwar D, Sharma MM (2017) A compact printed multistubs loaded resonator rectangular monopole antenna design for multiband wireless systems. Int J RF Microwave Comput Aided Eng 27(9):e21147
Acknowledgements
This work was supported by the scientific research capacity improvement project of key developing disciplines in Guangdong Province of China under No. 2021ZDJS057, the special projects in key fields of Guangdong Universities of China under No. 2022ZDZX1020, and the Tertiary Education Scientific research project of Guangzhou Municipal Education Bureau of China under No. 202234598.
Author information
Authors and Affiliations
Corresponding author
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Han, S., Tian, Y. Structure parameter estimation method for microwave device using dimension reduction network. Int. J. Mach. Learn. & Cyber. 14, 1285–1301 (2023). https://doi.org/10.1007/s13042-022-01698-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01698-1