Biomedical Signal Processing and Control, Год журнала: 2024, Номер 102, С. 107369 - 107369
Опубликована: Дек. 21, 2024
Язык: Английский
Biomedical Signal Processing and Control, Год журнала: 2024, Номер 102, С. 107369 - 107369
Опубликована: Дек. 21, 2024
Язык: Английский
Diagnostics, Год журнала: 2025, Номер 15(3), С. 363 - 363
Опубликована: Фев. 4, 2025
Background\Objectives: Solving the secrets of brain is a significant challenge for researchers. This work aims to contribute this area by presenting new explainable feature engineering (XFE) architecture designed obtain results related stress and mental performance using electroencephalography (EEG) signals. Materials Methods: Two EEG datasets were collected detect stress. To achieve classification results, XFE model was developed, incorporating novel extraction function called Cubic Pattern (CubicPat), which generates three-dimensional vector coding channels. Classification obtained cumulative weighted iterative neighborhood component analysis (CWINCA) selector t-algorithm-based k-nearest neighbors (tkNN) classifier. Additionally, generated CWINCA Directed Lobish (DLob). Results: The CubicPat-based demonstrated both interpretability. Using 10-fold cross-validation (CV) leave-one-subject-out (LOSO) CV, introduced CubicPat-driven achieved over 95% 75% accuracies, respectively, datasets. Conclusions: interpretable deploying DLob statistical analysis.
Язык: Английский
Процитировано
2Journal of Hydrology, Год журнала: 2024, Номер 642, С. 131867 - 131867
Опубликована: Авг. 23, 2024
Язык: Английский
Процитировано
4Displays, Год журнала: 2024, Номер 84, С. 102754 - 102754
Опубликована: Май 29, 2024
Язык: Английский
Процитировано
3Expert Systems with Applications, Год журнала: 2024, Номер unknown, С. 125420 - 125420
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
3Biomedical Signal Processing and Control, Год журнала: 2025, Номер 103, С. 107429 - 107429
Опубликована: Янв. 29, 2025
Язык: Английский
Процитировано
0Biomedical Signal Processing and Control, Год журнала: 2025, Номер 105, С. 107554 - 107554
Опубликована: Фев. 8, 2025
Язык: Английский
Процитировано
0Expert Systems with Applications, Год журнала: 2025, Номер 280, С. 127563 - 127563
Опубликована: Апрель 8, 2025
Язык: Английский
Процитировано
0Neural Networks, Год журнала: 2025, Номер unknown, С. 107457 - 107457
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
0Sleep Medicine Reviews, Год журнала: 2025, Номер 81, С. 102097 - 102097
Опубликована: Май 7, 2025
Язык: Английский
Процитировано
0Connection Science, Год журнала: 2023, Номер 35(1)
Опубликована: Дек. 9, 2023
Studying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, substantial advances have been made EEG-based classification of emotions. However, using different EEG features complementarity to discriminate other emotions is still challenging. Most existing models extract a single temporal feature from signal while ignoring crucial dynamic information, which, certain extent, constrains capability model. To address this issue, we propose Attention-Based Depthwise Parameterized Convolutional Gated Recurrent Unit (AB-DPCGRU) model validate it with mixed experiment on SEED SEED-IV datasets. The experimental outcomes revealed that accuracy outperforms state-of-the-art methods, which confirmed superiority our approach over currently popular emotion recognition models.
Язык: Английский
Процитировано
7