Purpose: The principle of microwave characterization of dielectric materials using open-ended coaxial line probe is to link the dielectric properties of the sample under test to the measurements of the probe admittance (Y(f) = G(f)+ jB(f)). The purpose of this paper is to develop an alternative inversion tool able to predict the evolution of the complex permittivity (ε = ε′ – jε″) on a broad band frequency (f from 1 MHz to 1.8 GHz). Design/methodology/approach: The inverse problem is solved using adaptive network based fuzzy inference system (ANFIS) which needs the creation of a database for its learning. Unfortunately, train ANFIS using f, G and B as inputs has given unsatisfying results. Therefore, an inputs selection procedure is used to select the three optimal inputs from new inputs, created mathematically from original ones, using the Jang method. Findings: Inversion results of measurements give, after training, in real time the complex permittivity of solid and liquid samples with a very good accuracy which prove the applicability of ANFIS to solve inverse problems in microwave characterization. Originality/value: The originality of this paper consists on the use of ANFIS with input selection procedure based on the Jang method to solve the inverse problem where the three optimal inputs are selected from 26 new inputs created mathematically from original ones (f, G and B). © 2018, Emerald Publishing Limited.
Eser Adı (dc.title) | An approach based on ANFIS and input selection procedure for microwave characterization of dielectric materials |
Yayın Türü (dc.type) | Makale |
Yazar/lar (dc.contributor.author) | SADOU, Hakim |
Yazar/lar (dc.contributor.author) | HACIB, Tarik |
Yazar/lar (dc.contributor.author) | AÇIKGÖZ, Hulusi |
Yazar/lar (dc.contributor.author) | LE BIHAN, Yan |
Yazar/lar (dc.contributor.author) | MEYER, Olivier |
Yazar/lar (dc.contributor.author) | MEKIDECHE, Mohamed Rachid |
DOI Numarası (dc.identifier.doi) | 10.1108/COMPEL-05-2017-0208 |
Atıf Dizini (dc.source.database) | Scopus |
Konu Başlıkları (dc.subject) | Multiple Criteria Analysis |
Konu Başlıkları (dc.subject) | ANFIS Supplier Selection |
Konu Başlıkları (dc.subject) | Input Selection |
Yayıncı (dc.publisher) | Emerald Group Publishing Ltd. |
Yayın Tarihi (dc.date.issued) | 2018 |
Kayıt Giriş Tarihi (dc.date.accessioned) | 2020-08-07T12:53:19Z |
Açık Erişim tarihi (dc.date.available) | 2020-08-07T12:53:19Z |
Kaynak (dc.source) | COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering |
ISSN (dc.identifier.issn) | 03321649 (ISSN) |
Kaynak Url (dc.source.uri) | https://www.emerald.com/insight/content/doi/10.1108/COMPEL-05-2017-0208/full/html |
Özet (dc.description.abstract) | Purpose: The principle of microwave characterization of dielectric materials using open-ended coaxial line probe is to link the dielectric properties of the sample under test to the measurements of the probe admittance (Y(f) = G(f)+ jB(f)). The purpose of this paper is to develop an alternative inversion tool able to predict the evolution of the complex permittivity (ε = ε′ – jε″) on a broad band frequency (f from 1 MHz to 1.8 GHz). Design/methodology/approach: The inverse problem is solved using adaptive network based fuzzy inference system (ANFIS) which needs the creation of a database for its learning. Unfortunately, train ANFIS using f, G and B as inputs has given unsatisfying results. Therefore, an inputs selection procedure is used to select the three optimal inputs from new inputs, created mathematically from original ones, using the Jang method. Findings: Inversion results of measurements give, after training, in real time the complex permittivity of solid and liquid samples with a very good accuracy which prove the applicability of ANFIS to solve inverse problems in microwave characterization. Originality/value: The originality of this paper consists on the use of ANFIS with input selection procedure based on the Jang method to solve the inverse problem where the three optimal inputs are selected from 26 new inputs created mathematically from original ones (f, G and B). © 2018, Emerald Publishing Limited. |
Yayın Dili (dc.language.iso) | en |
Tek Biçim Adres (dc.identifier.uri) | http://hdl.handle.net/20.500.12498/2889 |