Enhanced Image Reconstruction in Electrical Impedance Tomography using Radial Basis Function Neural Networks

Simple item page
dc.contributor.authorKouakouo Nomvussi, Serge Aymecs
dc.contributor.authorMikulka, Jancs
dc.coverage.issue6cs
dc.coverage.volume24cs
dc.date.accessioned2025-06-10T11:56:00Z
dc.date.available2025-06-10T11:56:00Z
dc.date.issued2024-12-16cs
dc.description.abstractThis paper presents a novel cascade algorithm for image reconstruction in electrical impedance tomography (EIT) using radial basis function neural networks. The first subnetwork applies a density-based algorithm and k-nearest neighbors (KNN) to determine the center and width of the radial basis function neural networks, with the aim of preventing ill-conditioned connection weights between the hidden and output layers. The second subnetwork is a generalized regression neural network dedicated to functional approximation. The combined subnetworks result in a reduced mean square error and achieve an accuracy of 89.54 % without noise and an accuracy between 82.90 % and 89.53 % with noise levels ranging from 30 to 60 dB. In comparison, the original radial basis function neural networks (RBFNN) method achieves an accuracy of 85.44 % without noise and between 80.90 % and 85.31 % under similar noise conditions. The total variation (TV) method achieves 83.13 % without noise, with noise-influenced accuracy ranging from 34.28 % to 45.15 %. The Gauss-Newton method achieves 82.35 % accuracy without noise, with accuracy ranging from 33.21 % to 46.15 % in the presence of noise. The proposed method proves to be resilient to various types of noise, including white Gaussian noise, impulsive noise, and contact noise, and consistently delivers superior performance. It also outperforms the other methods in noise-free conditions. The reliability of the method in noisy environments supports its potential application in the development of new modular systems for electrical impedance tomography.en
dc.formattextcs
dc.format.extent200-210cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationMeasurement Science Review. 2024, vol. 24, issue 6, p. 200-210.en
dc.identifier.doi10.2478/msr-2024-0027cs
dc.identifier.issn1335-8871cs
dc.identifier.orcid0000-0002-0740-4994cs
dc.identifier.orcid0000-0003-3270-1795cs
dc.identifier.other193528cs
dc.identifier.researcheridABF-1823-2021cs
dc.identifier.researcheridK-1324-2012cs
dc.identifier.scopus11140405800cs
dc.identifier.urihttps://hdl.handle.net/11012/251601
dc.language.isoencs
dc.publisherSciendocs
dc.relation.ispartofMeasurement Science Reviewcs
dc.relation.urihttps://sciendo.com/article/10.2478/msr-2024-0027cs
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1335-8871/cs
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/cs
dc.subjectArtificial neural networken
dc.subjectdensity-based algorithmen
dc.subjectelectrical impedance tomographyen
dc.subjectk-nearest neighborsen
dc.subjectradial basis function neural networksen
dc.subjectEIDORS frameworken
dc.titleEnhanced Image Reconstruction in Electrical Impedance Tomography using Radial Basis Function Neural Networksen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-193528en
sync.item.dbtypeVAVen
sync.item.insts2025.06.10 13:56:00en
sync.item.modts2025.06.10 13:33:09en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav teoretické a experimentální elektrotechnikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
EnhancedImageReconstructioninElectricalImpedanceTomographyusingRadialBasisFunctionNeuralNetworks.pdf
Size:
2.05 MB
Format:
Adobe Portable Document Format
Description:
file EnhancedImageReconstructioninElectricalImpedanceTomographyusingRadialBasisFunctionNeuralNetworks.pdf
Download
Collections
Ústav teoretické a experimentální elektrotechniky