Motor imagery BCI classification based on novel two-dimensional modelling in empirical wavelet transform

Brain complexity and non-stationary nature of electroencephalography (EEG) signal make considerable challenges for the accurate identification of different motor-imagery (MI) tasks in brain–computer interface (BCI). In the proposed Letter, a novel framework is proposed for the automated accurate cla...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Electronics letters Ročník 56; číslo 25; s. 1367 - 1369
Hlavní autori:	Sadiq, Muhammad Tariq, Yu, Xiaojun, Yuan, Zhaohui, Aziz, Muhammad Zulkifal
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	The Institution of Engineering and Technology 10.12.2020
Predmet:	automated accurate classification brain complexity brain‐computer interfaces brain–computer interface cascade forward neural networks classification check considerable challenges denoised signals different motor‐imagery tasks electroencephalography electroencephalography signal empirical wavelet extracted feature vectors feature extraction feedforward neural nets feedforward neural network medical signal processing MI tasks motor imagery BCI classification multiscale principal component analysis neural nets nonstationary nature principal component analysis raw EEG signals signal classification signal denoising single geometrical feature name Special Issue: Current Trends in Cognitive Science and Brain Computing Research and Applications total classification accuracy wavelet transforms cascade forward neural networks brain-computer interfaces wavelet transforms MI tasks automated accurate classification signal denoising nonstationary nature feature extraction brain complexity empirical wavelet multiscale principal component analysis extracted feature vectors electroencephalography total classification accuracy denoised signals single geometrical feature name different motor-imagery tasks brain–computer interface electroencephalography signal signal classification medical signal processing feedforward neural network motor imagery BCI classification raw EEG signals considerable challenges principal component analysis neural nets classification check feedforward neural nets
ISSN:	0013-5194, 1350-911X, 1350-911X
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Brain complexity and non-stationary nature of electroencephalography (EEG) signal make considerable challenges for the accurate identification of different motor-imagery (MI) tasks in brain–computer interface (BCI). In the proposed Letter, a novel framework is proposed for the automated accurate classification of MI tasks. First, raw EEG signals are denoised with multiscale principal component analysis. Secondly, denoised signals are decomposed by empirical wavelet transform into different modes. Thirdly, the two-dimensional (2D) modelling of modes is introduced to identify the variations of different signals. Fourthly, a single geometrical feature name as, a summation of distance from each point relative to a coordinate centre is extracted from 2D modelling of modes. Finally, the extracted feature vectors are provided to the feedforward neural network and cascade forward neural networks for classification check. The proposed study achieved 95.3% of total classification accuracy with 100% outcome for subject with very small training samples, which is outperforming existing methods on the same database.
ISSN:	0013-5194 1350-911X 1350-911X
DOI:	10.1049/el.2020.2509