84998

Автор(ы): 

Автор(ов): 

5

Параметры публикации

Тип публикации: 

Статья в журнале/сборнике

Название: 

Deep Learning for Analysis of Neurophysiological Fatigue Using EEG: Comparison of Architectures and Identification of Sensorimotor Activity Markers

ISBN/ISSN: 

1064-2269

DOI: 

10.1134/S1064226926600887

Наименование источника: 

  • Journal of Communications Technology and Electronics

Обозначение и номер тома: 

Vol. 71, No. 2

Город: 

  • Moscow

Издательство: 

  • Pleiades Publishing, Inc.

Год издания: 

2026

Страницы: 

103-114
Аннотация
This paper presents an approach for identifying neurophysiological markers of fatigue based on the analysis of EEG sensorimotor rhythms using deep learning methods. A methodology is proposed for generating spectrograms from multichannel EEG signals, including normalization, preprocessing, and data segmentation. Three adapted convolutional neural network architectures (EEGSpecResNet2D, EEGSpecMobileNetV3, EEGSpecAlexNet) are compared in both multiclass and binary classification tasks related to fatigue phases. EEGSpecResNet2D demonstrated the highest accuracy and robustness against overfitting. Additionally, training dynamics were analyzed, and pattern recognition features during intermediate task phases were visualized. The results confirm the effectiveness of residual architectures and anisotropic signal processing for monitoring cognitive load. The study highlights the potential of neural network models for developing BCI interfaces aimed at assessing and predicting operator functional states.

Библиографическая ссылка: 

Вольф Д.А., Туровский Я.А., Галин Р.Р., Венец В.И., Галина С.Б. Deep Learning for Analysis of Neurophysiological Fatigue Using EEG: Comparison of Architectures and Identification of Sensorimotor Activity Markers // Journal of Communications Technology and Electronics. 2026. Vol. 71, No. 2. С. 103-114.