Abstract
Brain Computer Interfaces (BCIs) are capable of processing neural stimuli using electroencephalogram (EEG) measurements to aid communication capabilities. Yet, BCIs often require extensive calibration steps in order to be tuned to specific users. In this work, we develop a subject independent P300 classification framework, which eliminates the need for user-specific calibration. We begin by employing a series of pre-processing steps, where, among other steps, we consider different trial averaging methodologies and various EEG electrode configurations. We then consider three distinct deep learning architectures and two linear machine learning models as P300 signal classifiers. Through evaluation on three datasets, and in comparison to three benchmark P300 classification frameworks, we find that averaging up to seven trials while using eight specific electrode channels on a two-layered convolutional neural network (CNN) leads to robust subject independent P300 classification. In this capacity, our method achieves greater than a 0.20 gain in AUC in comparison to prior P300 classification methods. In addition, our proposed framework is computationally efficient with training time gains of greater than 3×, compared to linear machine learning models, and online evaluation time speedups of up to 2× compared to benchmark methods.
Highlights
P ATIENTS who have suffered lower brain trauma, such as a stroke or a traumatic brain injury (TBI), are often subjects of locked-in syndrome (LIS)
We use the outstanding subject for evaluation, where we first determine the number of true positives (TP), false positives (FP), True Negatives (TN), and False Negatives (FN)
We found that the 4-channel and 32-channel configurations follow the same trend in which the convolutional neural network (CNN) and Recurrent Neural Networks (RNNs) are among the best performing classifiers followed by the convolutional LSTM recurrent neural network (CRNN) and the Linear Discriminant Analysis (LDA) and Support Vector Machines (SVMs) models
Summary
P ATIENTS who have suffered lower brain trauma, such as a stroke or a traumatic brain injury (TBI), are often subjects of locked-in syndrome (LIS). LIS prevents patients from moving their extremities resulting in, among a myriad of other challenges, extremely limited communication capabilities. Neural stimuli from LIS patients can be analyzed to aid communication abilities. Various neural signal processing algorithms [1]–[4] have been proposed for Brain Computer Interfaces (BCIs) [5], which are controlled using neural inputs from the subject’s upper brain activity. Such neural inputs are non-invasively collected with electrodes placed at various positions on a subject’s scalp using electroencephalogram (EEG) measurements [6]–[8]. The collected signals are processed in real time on board the BCI
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
