A Comprehensive sLORETA Study on the Contribution of Cortical Somatomotor Regions to Motor Imagery.

Mustafa Yazici,Mukadder Okuyan,Mustafa Ulutas

doi:10.3390/brainsci9120372

Abstract

Brain–computer interface (BCI) is a technology used to convert brain signals to control external devices. Researchers have designed and built many interfaces and applications in the last couple of decades. BCI is used for prevention, detection, diagnosis, rehabilitation, and restoration in healthcare. EEG signals are analyzed in this paper to help paralyzed people in rehabilitation. The electroencephalogram (EEG) signals recorded from five healthy subjects are used in this study. The sensor level EEG signals are converted to source signals using the inverse problem solution. Then, the cortical sources are calculated using sLORETA methods at nine regions marked by a neurophysiologist. The features are extracted from cortical sources by using the common spatial pattern (CSP) method and classified by a support vector machine (SVM). Both the sensor and the computed cortical signals corresponding to motor imagery of the hand and foot are used to train the SVM algorithm. Then, the signals outside the training set are used to test the classification performance of the classifier. The 0.1–30 Hz and mu rhythm band-pass filtered activity is also analyzed for the EEG signals. The classification performance and recognition of the imagery improved up to 100% under some conditions for the cortical level. The cortical source signals at the regions contributing to motor commands are investigated and used to improve the classification of motor imagery.

Highlights

The brain is one of the most complex organs in the body, as it controls our biological functions and mental tasks simultaneously
Classification performance is determined by true/false predictions for each case to determine the success of the predictions, which is calculated by Classification performance =
Future Brain–computer interface (BCI) are expected to have better classification accuracy compared to the BCIs of today and will be used in daily life

Summary

Introduction

The brain is one of the most complex organs in the body, as it controls our biological functions and mental tasks simultaneously. Physiology, engineering, and neuroimaging have helped scientists understand the brain. In the last couple of decades, it has been shown that external devices can be controlled via EEG signals acquired by sensors, by using signal processing and classification algorithms. The brain–machine interface, neural interface, neural prosthetics, and neural engineering terms are used for brain–computer interfaces (BCIs). Researchers have shown that a person can control cursor movement on a screen or control a robotic or prosthetic arm or leg by using brain signals. The design and implementation of BCI is a multidisciplinary field in which physicians, psychologists, and engineers work together to develop better BCIs. Engineers use advanced signal processing techniques to both filter and extract features and machine learning methods for better signal analysis.

Objectives

Methods

Results

Discussion

Conclusion