Using artificial neural networks for classification of kinesthetic and visual imaginary movements by MEG data

Semen Kurkin; Parth Chholak; Guiomar Niso; Nikita Frolov; Alexander Pisarchik

doi:10.1117/12.2563813

9 April 2020 Using artificial neural networks for classification of kinesthetic and visual imaginary movements by MEG data

Semen Kurkin, Parth Chholak, Guiomar Niso, Nikita Frolov, Alexander Pisarchik

Author Affiliations +

Proceedings Volume 11459, Saratov Fall Meeting 2019: Computations and Data Analysis: from Nanoscale Tools to Brain Functions; 1145905 (2020) https://doi.org/10.1117/12.2563813
Event: Saratov Fall Meeting 2019: VII International Symposium on Optics and Biophotonics, 2019, Saratov, Russian Federation

Abstract

The analysis of neurophysiological mechanisms responsible for motor imagery is essential for the development of brain-computer interfaces. The carried out magnetoencephalographic (MEG) experiments with voluntary participants confirm the existence of two types of motor imagery: kinesthetic imagery (KI) and visual imagery (VI), distinguished by activation and inhibition of different brain areas. For classification of the brain states associated with motor imagery, we used the hierarchical cluster analysis and a popular type of artificial neural networks called multilayer perceptron. The application of machine learning techniques allows us to classify motor imagery in raising right and left arms with an average accuracy of 70% for both KI and VI using appropriate filtration of input signals. The same average accuracy is achieved by optimizing MEG channels and reducing their number to only 13.

Citation Download Citation

Semen Kurkin, Parth Chholak, Guiomar Niso, Nikita Frolov, and Alexander Pisarchik "Using artificial neural networks for classification of kinesthetic and visual imaginary movements by MEG data", Proc. SPIE 11459, Saratov Fall Meeting 2019: Computations and Data Analysis: from Nanoscale Tools to Brain Functions, 1145905 (9 April 2020); https://doi.org/10.1117/12.2563813

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available