Identification of Real and Imaginary Movements in EEG Using Machine Learning Models

The neural activity of the brain may be observed by means of an electroencephalogram (EEG) whose analysis and/or interpretation may lead to the recognition of human activities and behaviors. However, on imagined body movements the brain produces the same EEG patterns as the action performed. This study aims to differentiate real movements from imagined ones, through EEG signals. Three different models; Support Vector Machine, Logistic Regression, and K-Nearest neighbour were implemented to classify these events. The preliminary results, obtained from 15 participants, revealed that the Logistic Regression was the best classifier into the proposed model with accuracy rates varying from 36.8 to 90%. Finally, complementary studies should be addressed to optimize not only the accuracy but also to assure uniform accuracy among the different participants.

[1]  Benjamin Blankertz,et al.  Towards a Cure for BCI Illiteracy , 2009, Brain Topography.

[2]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[3]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  F. Harrell,et al.  Regression modelling strategies for improved prognostic prediction. , 1984, Statistics in medicine.

[5]  Wen Jiang,et al.  Predictive value of EEG-awakening for behavioral awakening from coma , 2015, Annals of Intensive Care.

[6]  L. Deecke,et al.  Magnetic fields of the human brain accompanying voluntary movement: Bereitschaftsmagnetfeld , 2004, Experimental Brain Research.

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  Stefan Debener,et al.  Simultaneous EEG and fMRI: Recording, Analysis, and Application , 2010 .

[9]  Jyh-Yeong Chang,et al.  Gaming control using a wearable and wireless EEG-based brain-computer interface device with novel dry foam-based sensors , 2012, Journal of NeuroEngineering and Rehabilitation.

[10]  Po-Lei Lee,et al.  Recognition of Motor Imagery Electroencephalography Using Independent Component Analysis and Machine Classifiers , 2005, Annals of Biomedical Engineering.

[11]  Sung Chan Jun,et al.  A Review of Brain-Computer Interface Games and an Opinion Survey from Researchers, Developers and Users , 2014, Sensors.

[12]  V. Shotelersuk,et al.  An Economic Evaluation of Neonatal Screening for Inborn Errors of Metabolism Using Tandem Mass Spectrometry in Thailand , 2015, PloS one.

[13]  Carlo Menon,et al.  EEG Classification of Different Imaginary Movements within the Same Limb , 2015, PloS one.

[14]  Nathan Intrator,et al.  Schizophrenia Detection and Classification by Advanced Analysis of EEG Recordings Using a Single Electrode Approach , 2015, PloS one.

[15]  G. Pfurtscheller,et al.  Evidence for distinct beta resonance frequencies in human EEG related to specific sensorimotor cortical areas , 2001, Clinical Neurophysiology.

[16]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[17]  Kyuwan Choi,et al.  Electroencephalography (EEG)-based neurofeedback training for brain–computer interface (BCI) , 2013, Experimental Brain Research.