Standard

Detection of the intention to perform a two-staged movement from EEG signals. / Sagatdinov, A.; Knyazeva, V.; Lipkovich, M.; Aleksandrov, A.

2024. 183-186 Работа представлена на 2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN).

Результаты исследований: Материалы конференций › материалы › Рецензирование

Harvard

Sagatdinov, A, Knyazeva, V, Lipkovich, M & Aleksandrov, A 2024, 'Detection of the intention to perform a two-staged movement from EEG signals', Работа представлена на 2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN), 19/09/24 - 21/09/24 стр. 183-186. https://doi.org/10.1109/cnn63506.2024.10705815

APA

Sagatdinov, A., Knyazeva, V., Lipkovich, M., & Aleksandrov, A. (2024). Detection of the intention to perform a two-staged movement from EEG signals. 183-186. Работа представлена на 2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN). https://doi.org/10.1109/cnn63506.2024.10705815

Vancouver

Sagatdinov A, Knyazeva V, Lipkovich M, Aleksandrov A. Detection of the intention to perform a two-staged movement from EEG signals. 2024. Работа представлена на 2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN). https://doi.org/10.1109/cnn63506.2024.10705815

Author

Sagatdinov, A. ; Knyazeva, V. ; Lipkovich, M. ; Aleksandrov, A. / Detection of the intention to perform a two-staged movement from EEG signals. Работа представлена на 2024 Sixth International Conference Neurotechnologies and Neurointerfaces (CNN).4 стр.

BibTeX

@conference{cfa348443b084b92a58841a8e7b483b5,
title = "Detection of the intention to perform a two-staged movement from EEG signals",
abstract = "The article explores methods for recognizing neurophysiological signals related to the preparation and execution of voluntary movements in the human brain. The experiment involved participants performing a complex self-initiated movement, comprising pressing a button and touching a marker around a transparent partition. Various machine learning models were utilized, including linear models with regularization, random forests, and support vector machines. The introduction of a”stacking” model facilitated the incorporation of new feature types without complete retraining of base models. Hyperparameter optimization was conducted using cross-validation. To address class imbalance, upsampling methods and penalties in the loss functions were applied. Balanced accuracy was chosen as the target metric, considering the disparity between the number of positive and negative epochs. The SHAP method was employed for results interpretation. The best-performing model demonstrated a balanced accuracy of 72% for right-hand presses and 77% for left-hand presses. {\textcopyright}2024 IEEE.",
keywords = "EEG, evoked potentials detection, machine learning, self-initiated movements, Adaptive boosting, Electrocardiography, Self-supervised learning, EEG signals, Evoked potential detection, Human brain, Linear modeling, Machine learning models, Machine-learning, Pressung, Regularisation, Self-initiated movement, Voluntary movement, Support vector machines",
author = "A. Sagatdinov and V. Knyazeva and M. Lipkovich and A. Aleksandrov",
note = "Код конференции: 203271 Export Date: 10 November 2024; null ; Conference date: 19-09-2024 Through 21-09-2024",
year = "2024",
month = sep,
day = "19",
doi = "10.1109/cnn63506.2024.10705815",
language = "Английский",
pages = "183--186",

}

RIS

TY - CONF

T1 - Detection of the intention to perform a two-staged movement from EEG signals

AU - Sagatdinov, A.

AU - Knyazeva, V.

AU - Lipkovich, M.

AU - Aleksandrov, A.

N1 - Код конференции: 203271 Export Date: 10 November 2024

PY - 2024/9/19

Y1 - 2024/9/19

N2 - The article explores methods for recognizing neurophysiological signals related to the preparation and execution of voluntary movements in the human brain. The experiment involved participants performing a complex self-initiated movement, comprising pressing a button and touching a marker around a transparent partition. Various machine learning models were utilized, including linear models with regularization, random forests, and support vector machines. The introduction of a”stacking” model facilitated the incorporation of new feature types without complete retraining of base models. Hyperparameter optimization was conducted using cross-validation. To address class imbalance, upsampling methods and penalties in the loss functions were applied. Balanced accuracy was chosen as the target metric, considering the disparity between the number of positive and negative epochs. The SHAP method was employed for results interpretation. The best-performing model demonstrated a balanced accuracy of 72% for right-hand presses and 77% for left-hand presses. ©2024 IEEE.

AB - The article explores methods for recognizing neurophysiological signals related to the preparation and execution of voluntary movements in the human brain. The experiment involved participants performing a complex self-initiated movement, comprising pressing a button and touching a marker around a transparent partition. Various machine learning models were utilized, including linear models with regularization, random forests, and support vector machines. The introduction of a”stacking” model facilitated the incorporation of new feature types without complete retraining of base models. Hyperparameter optimization was conducted using cross-validation. To address class imbalance, upsampling methods and penalties in the loss functions were applied. Balanced accuracy was chosen as the target metric, considering the disparity between the number of positive and negative epochs. The SHAP method was employed for results interpretation. The best-performing model demonstrated a balanced accuracy of 72% for right-hand presses and 77% for left-hand presses. ©2024 IEEE.

KW - EEG

KW - evoked potentials detection

KW - machine learning

KW - self-initiated movements

KW - Adaptive boosting

KW - Electrocardiography

KW - Self-supervised learning

KW - EEG signals

KW - Evoked potential detection

KW - Human brain

KW - Linear modeling

KW - Machine learning models

KW - Machine-learning

KW - Pressung

KW - Regularisation

KW - Self-initiated movement

KW - Voluntary movement

KW - Support vector machines

UR - https://www.mendeley.com/catalogue/f1e6e30b-6416-3d2a-8bfa-484209cce212/

U2 - 10.1109/cnn63506.2024.10705815

DO - 10.1109/cnn63506.2024.10705815

M3 - материалы

SP - 183

EP - 186

Y2 - 19 September 2024 through 21 September 2024

ER -

ID: 127215490