Počet záznamů: 1
Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis
- 1.
SYSNO ASEP 0577393 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis Tvůrce(i) Pijáčková, Kristýna (UPT-D) ORCID, SAI, RID
Nejedlý, Petr (UPT-D) RID, SAI
Křemen, V. (US)
Plešinger, Filip (UPT-D) RID, ORCID, SAI
Mívalt, F. (US)
Lepková, K. (CZ)
Pail, Martin (UPT-D) RID, SAI, ORCID
Jurák, Pavel (UPT-D) RID, ORCID, SAI
Worrell, G. A. (US)
Brázdil, M. (CZ)
Klimeš, Petr (UPT-D) RID, ORCID, SAICelkový počet autorů 11 Číslo článku 036034 Zdroj.dok. Journal of Neural Engineering. - : Institute of Physics Publishing - ISSN 1741-2560
Roč. 20, č. 3 (2023)Poč.str. 11 s. Forma vydání Tištěná - P Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova intracranial EEG ; genetic algorithms ; optimization ; neural network ; deep learning Vědní obor RIV FH - Neurologie, neurochirurgie, neurovědy Obor OECD Neurosciences (including psychophysiology CEP NU22-08-00278 GA MZd - Ministerstvo zdravotnictví GA22-28784S GA ČR - Grantová agentura ČR LX22NPO5107 GA MŠMT - Ministerstvo školství, mládeže a tělovýchovy Způsob publikování Open access Institucionální podpora UPT-D - RVO:68081731 UT WOS 001085835700001 EID SCOPUS 85163311622 DOI https://doi.org/10.1088/1741-2552/acdc54 Anotace Objective. 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. Pracoviště Ústav přístrojové techniky Kontakt Martina Šillerová, sillerova@ISIBrno.Cz, Tel.: 541 514 178 Rok sběru 2024 Elektronická adresa https://iopscience.iop.org/article/10.1088/1741-2552/acdc54
Počet záznamů: 1