Single trial eeg classification of tasks with dominance of mental and sensory attention with deep learning approach

Standard

Single trial eeg classification of tasks with dominance of mental and sensory attention with deep learning approach. / Knyazeva, Irina; Efitorov, Alexander; Boytsova, Yulia; Danko, Sergey; Shiroky, Vladimir; Makarenko, Nikolay.

Studies in Computational Intelligence. Vol. 799 2019. p. 190-195 (Studies in Computational Intelligence).

Research output: Chapter in Book/Report/Conference proceeding › Article in an anthology › peer-review

Author

Knyazeva, Irina ; Efitorov, Alexander ; Boytsova, Yulia ; Danko, Sergey ; Shiroky, Vladimir ; Makarenko, Nikolay. / Single trial eeg classification of tasks with dominance of mental and sensory attention with deep learning approach. Studies in Computational Intelligence. Vol. 799 2019. pp. 190-195 (Studies in Computational Intelligence).

BibTeX

@inbook{7de06a1726eb4487884dadf4d7ae2c5b,

title = "Single trial eeg classification of tasks with dominance of mental and sensory attention with deep learning approach",

abstract = "{\textcopyright} Springer Nature Switzerland AG 2019. In this paper, we present classification algorithms based on single-trial ElectroEncephaloGraphy (EEG) during the performance of tasks with the dominance of mental and sensory attention. Statistical data analysis showed numerous significant differences of EEG wavelet spectra density during this task at the group level. We decided to use wavelet power spectral density (PSD) computed in each channel for single trial as the source of feature extraction for the classification task. To obtain a low-dimensional representation of PSD image convolutional autoencoder (CNN) was trained. With this encoded representation binary classification for each subject with multilayer perceptron (MLP) were performed. The classification error varies depending on the subject with the average true classification rate is 83.4%, and the standard deviation is 6.6%. So this approach potentially could be used in the tasks where pattern classification is used, such as a clinical decision or in Brain-Computer Interface (BCI) system.",

keywords = "Deep learning, EEG single trial classification, Mental and sensory attention, Neural networks",

author = "Irina Knyazeva and Alexander Efitorov and Yulia Boytsova and Sergey Danko and Vladimir Shiroky and Nikolay Makarenko",

year = "2019",

month = jan,

day = "1",

doi = "10.1007/978-3-030-01328-8_21",

language = "English",

volume = "799",

series = "Studies in Computational Intelligence",

publisher = "Springer",

pages = "190--195",

booktitle = "Studies in Computational Intelligence",

}

RIS

TY - CHAP

T1 - Single trial eeg classification of tasks with dominance of mental and sensory attention with deep learning approach

AU - Knyazeva, Irina

AU - Efitorov, Alexander

AU - Boytsova, Yulia

AU - Danko, Sergey

AU - Shiroky, Vladimir

AU - Makarenko, Nikolay

PY - 2019/1/1

Y1 - 2019/1/1

N2 - © Springer Nature Switzerland AG 2019. In this paper, we present classification algorithms based on single-trial ElectroEncephaloGraphy (EEG) during the performance of tasks with the dominance of mental and sensory attention. Statistical data analysis showed numerous significant differences of EEG wavelet spectra density during this task at the group level. We decided to use wavelet power spectral density (PSD) computed in each channel for single trial as the source of feature extraction for the classification task. To obtain a low-dimensional representation of PSD image convolutional autoencoder (CNN) was trained. With this encoded representation binary classification for each subject with multilayer perceptron (MLP) were performed. The classification error varies depending on the subject with the average true classification rate is 83.4%, and the standard deviation is 6.6%. So this approach potentially could be used in the tasks where pattern classification is used, such as a clinical decision or in Brain-Computer Interface (BCI) system.

AB - © Springer Nature Switzerland AG 2019. In this paper, we present classification algorithms based on single-trial ElectroEncephaloGraphy (EEG) during the performance of tasks with the dominance of mental and sensory attention. Statistical data analysis showed numerous significant differences of EEG wavelet spectra density during this task at the group level. We decided to use wavelet power spectral density (PSD) computed in each channel for single trial as the source of feature extraction for the classification task. To obtain a low-dimensional representation of PSD image convolutional autoencoder (CNN) was trained. With this encoded representation binary classification for each subject with multilayer perceptron (MLP) were performed. The classification error varies depending on the subject with the average true classification rate is 83.4%, and the standard deviation is 6.6%. So this approach potentially could be used in the tasks where pattern classification is used, such as a clinical decision or in Brain-Computer Interface (BCI) system.

KW - Deep learning

KW - EEG single trial classification

KW - Mental and sensory attention

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85054695933&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/single-trial-eeg-classification-tasks-dominance-mental-sensory-attention-deep-learning-approach

U2 - 10.1007/978-3-030-01328-8_21

DO - 10.1007/978-3-030-01328-8_21

M3 - Article in an anthology

AN - SCOPUS:85054695933

VL - 799

T3 - Studies in Computational Intelligence

SP - 190

EP - 195

BT - Studies in Computational Intelligence

ER -

ID: 35578540