Academic Bibliography
https://biblio.ugent.be/
Ghent University Academic Bibliography2000-01-01T00:00+00:001monthlyParametric modeling and deep learning for enhancing pain assessment in postanesthesia
https://biblio.ugent.be/publication/01HNMPDD1MMD5KW7ES5EF17ATF
Ghita, MihaelaBirs, Isabela RoxanaCopot, DanaMuresan, CristinaNeckebroek, MartineIonescu, Clara-Mihaela2023Objective: The problem of reliable and widely accepted measures of pain is still open. It follows the objective of this work as pain estimation through post-surgical trauma modeling and classification, to increase the needed reliability compared to measurements only.Methods: This article proposes (i) a recursive identification method to obtain the frequency response and parameterization using fractional-order impedance models (FOIM), and (ii) deep learning with convolutional neural networks (CNN) classification algorithms using time-frequency data and spectrograms. The skin impedance measurements were conducted on 12 patients throughout the postanesthesia care in a proof-of-concept clinical trial. Recursive least-squares system identification was performed using a genetic algorithm for initializing the parametric model. The online parameter estimates were compared to the self-reported level by the Numeric Rating Scale (NRS) for analysis and validation of the results. Alternatively, the inputs to CNNs were the spectrograms extracted from the time-frequency dataset, being pre-labeled in four intensities classes of pain during offline and online training with the NRS.Results: The tendency of nociception could be predicted by monitoring the changes in the FOIM parameters' values or by retraining online the network. Moreover, the tissue heterogeneity, assumed during nociception, could follow the NRS trends. The online predictions of retrained CNN have more specific trends to NRS than pain predicted by the offline population-trained CNN.Conclusion: We propose tailored online identification and deep learning for artefact corrupted environment. The results indicate estimations with the potential to avoid over-dosing due to the objectivity of the information.Significance: Models and artificial intelligence (AI) allow objective and personalized nociception-antinociception prediction in the patient safety era for the design and evaluation of closed-loop analgesia controllers.application/pdfhttps://biblio.ugent.be/publication/01HNMPDD1MMD5KW7ES5EF17ATFhttp://hdl.handle.net/1854/LU-01HNMPDD1MMD5KW7ES5EF17ATFhttp://doi.org/10.1109/TBME.2023.3274541https://biblio.ugent.be/publication/01HNMPDD1MMD5KW7ES5EF17ATF/file/01HNMPP4KNJF3WFDMFP0GBBAH0engCreative Commons Attribution 4.0 International Public License (CC-BY 4.0)info:eu-repo/semantics/openAccessIEEE TRANSACTIONS ON BIOMEDICAL ENGINEERINGISSN: 0018-9294ISSN: 1558-2531Technology and EngineeringMedicine and Health SciencesArtificial intelligenceclosed-loop analgesia controlfractional orderimpedance modelfrequency-domain analysisrecursive identificationspectroscopyPOSTOPERATIVE PAINMACHINELOOPParametric modeling and deep learning for enhancing pain assessment in postanesthesiajournalArticleinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionReduced-order approximation of fractional-order controllers by keeping robust stability and robust performance
https://biblio.ugent.be/publication/01HQX2HKWYCVNEVSXWP0A26FX5
Mihaly, VladSusça, MirceaBirs, Isabela RoxanaDobra, Petru2023Recently, the fractional-order element has been integrated into the Robust Control Framework considering the Oustaloup method. As such, the resulting infinite impulse response approximation manages to satisfy the robust stability and the robust performance criteria according to a given uncertainty block. However, the recommended approximation order for each fractional-order element is the number of decades of the frequency range where the approximation is valid, which can lead to a high-order controller. The current paper describes an optimization-based technique to find a low-order approximation of a fractional-order controller such that the resulting controller maintains the robust stability and robust performance as well. A set of numerical experiments have also been performed in order to illustrate the proposed method.application/pdfhttps://biblio.ugent.be/publication/01HQX2HKWYCVNEVSXWP0A26FX5http://hdl.handle.net/1854/LU-01HQX2HKWYCVNEVSXWP0A26FX5http://doi.org/10.23919/ACC55779.2023.10156398https://biblio.ugent.be/publication/01HQX2HKWYCVNEVSXWP0A26FX5/file/01HQX2SMN98SVNQFKXY5R1VPN4engIEEENo license (in copyright)info:eu-repo/semantics/openAccess2023 AMERICAN CONTROL CONFERENCE, ACCISSN: 0743-1619ISSN: 2378-5861ISBN: 9798350328066Technology and EngineeringReduced-order approximation of fractional-order controllers by keeping robust stability and robust performanceconferenceinfo:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersion