Abstract
Recently, studies have reported the use of Near Infrared Spectroscopy (NIRS) for developing Brain–Computer Interface (BCI) by applying online pattern classification of brain states from subject-specific fNIRS signals. The purpose of the present study was to develop and test a real-time method for subject-specific and subject-independent classification of multi-channel fNIRS signals using support-vector machines (SVM), so as to determine its feasibility as an online neurofeedback system. Towards this goal, we used left versus right hand movement execution and movement imagery as study paradigms in a series of experiments. In the first two experiments, activations in the motor cortex during movement execution and movement imagery were used to develop subject-dependent models that obtained high classification accuracies thereby indicating the robustness of our classification method. In the third experiment, a generalized classifier-model was developed from the first two experimental data, which was then applied for subject-independent neurofeedback training. Application of this method in new participants showed mean classification accuracy of 63% for movement imagery tasks and 80% for movement execution tasks. These results, and their corresponding offline analysis reported in this study demonstrate that SVM based real-time subject-independent classification of fNIRS signals is feasible. This method has important applications in the field of hemodynamic BCIs, and neuro-rehabilitation where patients can be trained to learn spatio-temporal patterns of healthy brain activity.
Highlights
In contrast to the classical method of presenting stimuli and studying evoked brain responses, Brain–Computer Interface (BCI) and neurofeedback work by altering the neural activity first, and observing the effect of this altered activity on the subjects’ behavior [1,2]
Such a system has been successfully developed for fMRI based BCI using real-time Support Vector Machine (SVM) based classification algorithms [3], and an earlier study has demonstrated the feasibility of implementing machine learning algorithms in classifying single trial activations using multi-channel fNIRS [4]
The evaluation results of the real time fNIRS based neurofeedback system for classifying left versus right hand overt and covert movements are presented
Summary
In contrast to the classical method of presenting stimuli and studying evoked brain responses, BCI and neurofeedback work by altering the neural activity first, and observing the effect of this altered activity on the subjects’ behavior [1,2]. Since most of the evoked responses in the brain are in the form of spatio-temporal patterns of activity (electrical or hemodynamic), a system capable of successfully classifying these patterns is an indispensable tool for rehabilitation [2] Such a system has been successfully developed for fMRI based BCI using real-time Support Vector Machine (SVM) based classification algorithms [3], and an earlier study has demonstrated the feasibility of implementing machine learning algorithms in classifying single trial activations using multi-channel fNIRS [4]. The study showed that true neurofeedback induced significantly greater activation of the contra lateral pre-motor cortex and greater self-assessment scores for kinesthetic motor imagery compared with sham feedback These results illustrate the efficacy of using both fNIRS signals for neurofeedback and machine-learning algorithms for implementing single-trial classifications from such signals. We aimed at combining these two approaches so as to develop a real-time SVM based neurofeedback system based on multi-channel fNIRS signals
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call