Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis

Simple item page
dc.contributor.authorPijáčková, Kristýnacs
dc.contributor.authorNejedlý, Petrcs
dc.contributor.authorKřemen, Václavcs
dc.contributor.authorPlešinger, Filipcs
dc.contributor.authorMívalt, Filipcs
dc.contributor.authorLepková, Kamilacs
dc.contributor.authorPail, Martincs
dc.contributor.authorJurák, Pavelcs
dc.contributor.authorWorrell, Gregorycs
dc.contributor.authorBrázdil, Milancs
dc.contributor.authorKlimeš, Petrcs
dc.coverage.issue3cs
dc.coverage.volume20cs
dc.date.issued2023-06-16cs
dc.description.abstractObjective. The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data. Approach. We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification. Main results. Our method improved the macro F1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively. Significance. By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test, p MUCH LESS-THAN 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.en
dc.formattextcs
dc.format.extent1-11cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationJ NEURAL ENG. 2023, vol. 20, issue 3, p. 1-11.en
dc.identifier.doi10.1088/1741-2552/acdc54cs
dc.identifier.issn1741-2560cs
dc.identifier.orcid0000-0002-0693-9495cs
dc.identifier.other185287cs
dc.identifier.researcheridAAX-1872-2021cs
dc.identifier.scopus57205062706cs
dc.identifier.urihttp://hdl.handle.net/11012/244967
dc.language.isoencs
dc.publisherIOP Publishingcs
dc.relation.ispartofJ NEURAL ENGcs
dc.relation.urihttps://iopscience.iop.org/article/10.1088/1741-2552/acdc54cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1741-2560/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectintracranial EEGen
dc.subjectgenetic algorithmsen
dc.subjectoptimizationen
dc.subjectneural networken
dc.subjectdeep learningen
dc.titleGenetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysisen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-185287en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:41:49en
sync.item.modts2025.01.17 15:29:22en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav radioelektronikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Pijackova_2023_J._Neural_Eng._20_036034.pdf
Size:
1.65 MB
Format:
Adobe Portable Document Format
Description:
file Pijackova_2023_J._Neural_Eng._20_036034.pdf
Download
Collections
Ústav radioelektroniky