Publication detail

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

PIJÁČKOVÁ, K. NEJEDLÝ, P. KŘEMEN, V. PLEŠINGER, F. MÍVALT, F. LEPKOVÁ, K. PAIL, M. JURÁK, P. WORRELL, G. BRÁZDIL, M. KLIMEŠ, P.

Original Title

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

Type

journal article in Web of Science

Language

English

Original Abstract

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.

Keywords

intracranial EEG; genetic algorithms; optimization; neural network; deep learning

Authors

PIJÁČKOVÁ, K.; NEJEDLÝ, P.; KŘEMEN, V.; PLEŠINGER, F.; MÍVALT, F.; LEPKOVÁ, K.; PAIL, M.; JURÁK, P.; WORRELL, G.; BRÁZDIL, M.; KLIMEŠ, P.

Released

16. 6. 2023

Publisher

IOP Publishing

Location

BRISTOL

ISBN

1741-2560

Periodical

J NEURAL ENG

Year of study

20

Number

3

State

United Kingdom of Great Britain and Northern Ireland

Pages from

1

Pages to

11

Pages count

11

URL

https://iopscience.iop.org/article/10.1088/1741-2552/acdc54

Full text in the Digital Library

http://hdl.handle.net/11012/244967

BibTex

@article{BUT185287,
  author="Kristýna {Pijáčková} and Petr {Nejedlý} and Václav {Křemen} and Filip {Plešinger} and Filip {Mívalt} and Kamila {Lepková} and Martin {Pail} and Pavel {Jurák} and Gregory {Worrell} and Milan {Brázdil} and Petr {Klimeš}",
  title="Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis",
  journal="J NEURAL ENG",
  year="2023",
  volume="20",
  number="3",
  pages="1--11",
  doi="10.1088/1741-2552/acdc54",
  issn="1741-2560",
  url="https://iopscience.iop.org/article/10.1088/1741-2552/acdc54"
}