Increasing the metrological characteristics of anechoic chambers due to a posteriori analysis based on artificial neural networks
Keywords:
anechoic chamber, neural networks, generative adversarial models, electromagnetic field distribution, metrological characteristicsAbstract
This article considers the possibility of improving the metrological characteristics of an anechoic chamber due to a posteriori processing of measurement results based on a generative adversarial model of an artificial neural network in order to reduce the influence on the distribution of the electromagnetic field in the measuring zone of waves reflected from the outer boundaries of the chamber and the equipment located in it. The training of the neural network was carried out on a data set obtained as part of a computational experiment and including the distribution of the electromagnetic field in the anechoic region for the model of an anechoic chamber and free space for given source layouts. The distributions of the real and imaginary parts of the electric component of the electromagnetic field were encoded with colour images. On the example of two-dimensional models of anechoic chambers, the practical feasibility of the proposed approach to a posteriori processing of measurement results is shown. Methods for estimating the accuracy of a posteriori processing of measurement results based on the metrics used to assess the quality of graphic images and calculating the errors in the amplitudes of the electric component of the electromagnetic field are given. The possibility of implementing the proposed method of a posteriori analysis in the framework of natural microwave measurements in anechoic chambers is assessed.
References
- Mitsmakher MYu, Torgovanov VA. Bezekhovye kamery SVCh [Anechoic chambers UHF]. Moscow: Radio i svyaz’; 1982. 128 p. Russian.
- Fausett L. Fundamentals of neural networks: architectures, algorithms and applications. [S. l.]: Pearson Education Inc.; 1993. XVI, 461 p.
- Sagdeeva YuA, Kopysov SP, Novikov AK. Vvedenie v metod konechnykh elementov [Introduction to the finite element method]. Izhevsk: Udmurtskii universitet; 2011. 44 p. Russian.
- Zhang Yifei. A better autoencoder for image: convolutional autoencoder [Internet]. In: ABCs 2018. 1 st ANU bio-inspired computing conference; 2018 July 20; Canberra, Australia. [S. l.]: [s. n.]; 2018 [cited 2021 November 9]. Available from: http://users.cecs.anu.edu.au/~Tom.Gedeon/conf/ABCs2018/paper/ABCs2018_paper_58.pdf.
- Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. arXiv:1611.07004v3 [Preprint]. 2018 [cited 2021 November 9]: [17 p.]. Available from: https://arxiv.org/abs/1611.07004v3.
- Fardo FA, Conforto VH, de Oliveira FC, Rodrigues PS. A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms. arXiv:1605.07116v1 [Preprint]. 2016 [cited 2021 December 1]: [11 p.]. Available from: https://arxiv.org/abs/1605.07116v1.
Downloads
Additional Files
Published
Issue
Section
License
The authors who are published in this journal agree to the following:
- The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
- The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
- The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)
How to Cite
