Machine learning approach to transform scattering parameters to complex permittivities

References

• Agostinelli F, Hoffman M, Sadowski P, Baldi P. 2015. Learning activation functions to improve deep neural networks. In: 3rd Int Conf Learn Represent ICLR 2015 - Work Track Proc. San Diego: ICLR 2015; p. 1–9.
   Google Scholar
• Baker-Jarvis J, Janezic MD, Grosvenor JH, Jr., Geyer RG. 1992. Transmission/reflection and short-circuit line methods for measuring permittivity and permeability. Washington, DC: NIST.
   Google Scholar
• Bartley PG, Begley SB. 2010. A new technique for the determination of the complex permittivity and permeability of materials. In: IEEE Instrum Meas Technol Conference; Austin, TX, USA.
   Google Scholar
• Blakney TL, Weir WB. 1975. Automatic measurement of complex dielectric constant and permeability at microwave frequencies. Proc IEEE. 63(1):203–205.
   Google Scholar
• Blakney TL, Weir WB, Constant D. 1975. Comments on “automatic measurement of complex dielectric constant and permeability at microwave frequencies”. Proc IEEE. 63(1):203–205.
   Google Scholar
• Bois KJ, Handjojo LF, Benally AD, Mubarak K, Zoughi R. 1999. Analysis of an open-ended coaxial probe with lift-off for nondestructive testing. IEEE Trans Instrum Meas. 48(6):1141–1148.
   Google Scholar
• Bussey HE. 1967. Measurement of RF properties of materials a survey. Proc IEEE. 55(6):1046–1053.
   Web of Science ®Google Scholar
• Chen Q, Huang K-M, Yang X, Luo M, Zhu H. 2011. An artificial nerve network realization in the measurement of material permittivity. PIER. 116(April):347–361.
   Google Scholar
• COMSOL AB. EM Module [Internet]. www.comsol.com.
   Google Scholar
• Gajda G, Stuchly SS. 1983. An equivalent circuit of an open-ended coaxial line. IEEE Trans Instrum Meas. 32(4):367–368.
   Google Scholar
• Geyer RG, Grosvenor CA, Holloway CL, Janezic MD, Johk RT, Kabos P, Baker-Jarvis J. 2005. Measuring the permittivity and permeability of lossy materials. Boulder, CO:  NIST.
   Google Scholar
• Guo D, Wang Y, Xia J, Nan C, Li L. 2002. Investigation of BaTiO3 formulation: An artificial neural network (ANN) method. J Eur Ceram Soc. 22(11):1867–1872.
   Google Scholar
• Li Y, Yuan Y. 2017. Convergence analysis of two-layer neural networks with ReLU activation. In: Long Beach: NeurIPS Proceedings; Adv Neural Inf Process Syst. 30; pp. 1–11.
   Google Scholar
• Li Z, Ma X, Xin H. 2017. Feature engineering of machine-learning chemisorption models for catalyst design. Catal Today. 280:232–238. [Internet]. https://doi.org/http://dx.doi.org/10.1016/j.cattod.2016.04.013.
   Web of Science ®Google Scholar
• Maas AL, Hannun AY, Ng AY. 2013. Rectifier nonlinearities improve neural network acoustic models. Proc 30th Int Conf Mach Learn. 30(1):3.
   Google Scholar
• Mittlböck M, Schemper M. 1996. Explained variation for logistic regression. Statist Med. 15(19):1987–1997.
   PubMed Web of Science ®Google Scholar
• Mueller T, Kusne AG, Ramprasad R. 2016. Machine learning in materials science: Recent progress and emerging applications. Rev Comput Chem. 29:186–273.
   Web of Science ®Google Scholar
• Narang S, Elsen E, Diamos G, Sengupta S. 2017. Exploring sparsity in recurrent neural networks. Int Conf Learn Represent. 1(1):1–10.
   Google Scholar
• Nicolson AM, Ross GF. 1970. Measurement of the intrinsic properties of materials by time domain techniques. IEEE Trans Instrum Meas. 19(4):377–382.
   Web of Science ®Google Scholar
• Nigrin A. 1993. Neural networks for pattern recognition. 1st ed. Cambridge (MA): MIT Press.
   Google Scholar
• Raff L, Komanduri R, Hagan M, Bukkapatnam S. 2012. Applications of neural network fitting of potential-energy surfaces. In: Neural Networks Chem React Dyn. Oxford: Oxford University Press; p. 283.
   Google Scholar
• Ramachandran P, Zoph B, Le QV. 2017. Searching for activation functions. arXiv. 1(1):1–13.
   Google Scholar
• Sahoo S, Lampert C, Martius G. 2018. Learning equations for extrapolation and control. Proc 35th Int Conf Mach Learn. 80:4442–4450.
   Google Scholar
• Schwab J, Antholzer S, Haltmeier M. 2019. Deep null space learning for inverse problems: Convergence analysis and rates. Inverse Probl. 35(2):025008.
   Google Scholar
• Scott DJ, Coveney PV, Kilner JA, Rossiny JCH, Alford NMN. 2007. Prediction of the functional properties of ceramic materials from composition using artificial neural networks. J Eur Ceram Soc. 27(16):4425–4435.
   Google Scholar
• Tempke R, Wildfire C, Shekhawat D, Musho T. 2020. Dielectric measurement of powdery materials using a coaxial transmission line. IET Sci Meas Technol. 14(10):972–978.
   Google Scholar
• Tuck D, Coad S. 1995. Neurocomputed model of open-circuited coaxial probes. Ind Res. 5(4):5–7.
   Google Scholar
• Yasin AS, Musho TD. 2020. A machine learning approach for increased throughput of density functional theory substitutional alloy studies. Comput Mater Sci. 181:109726.
   Google Scholar
• Yaw KC. 2006. Measurement of dielectric material properties application note, Rohde & Schwarz. Meas Tech. 1–35.
   Google Scholar
• Zangwill A. 2013. Modern electrodynamics. Cambridge: Cambridge University Press.
   Google Scholar
• Zeiler MD. 2012. ADADELTA: An adaptive learning rate method. arXiv. 1(1):1–6.
   Google Scholar
• Zhao Z, Qu Y, Zhang Y, Shen X. 2013. Overview of microwave device modeling techniques based on machine learning. Int J Adv Comput Technol. 5(9):299–306.
   Google Scholar