Abstract

A brain-computer interface (BCI) is a communication tool that analyzes neural activity and relays the translated commands to carry out actions. In recent years, semi-supervised learning (SSL) has attracted attention for visual event-related potential (ERP)-based BCIs and motor-imagery BCIs as an effective technique that can adapt to the variations in patterns among subjects and trials. The applications of the SSL techniques are expected to improve the performance of auditory ERP-based BCIs as well. However, there is no conclusive evidence supporting the positive effect of SSL techniques on auditory ERP-based BCIs. If the positive effect could be verified, it will be helpful for the BCI community. In this study, we assessed the effects of SSL techniques on two public auditory BCI datasets-AMUSE and PASS2D-using the following machine learning algorithms: step-wise linear discriminant analysis, shrinkage linear discriminant analysis, spatial temporal discriminant analysis, and least-squares support vector machine. These backbone classifiers were firstly trained by labeled data and incrementally updated by unlabeled data in every trial of testing data based on SSL approach. Although a few data of the datasets were negatively affected, most data were apparently improved by SSL in all cases. The overall accuracy was logarithmically increased with every additional unlabeled data. This study supports the positive effect of SSL techniques and encourages future researchers to apply them to auditory ERP-based BCIs.

Highlights

  • As a brain-computer interface (BCI) performs communication based on neural activity measurement

  • The improvements in averaged BCI accuracy owing to supervised learning (SSL) were 2.25, 4.27, 3.70, and 2.80% for step-wise LDA (SWLDA), shrinkage regularized based LDA (SKLDA), spatial-temporal discriminant analysis (STDA), and LS-support vector machine (SVM) respectively

  • Four classifiers (SWLDA, SKLDA, STDA, and least squares SVM (LS-SVM)) and their SSL expansion versions were applied to two public datasets (AMUSE and PASS2D)

Read more

Summary

Introduction

As a brain-computer interface (BCI) performs communication based on neural activity measurement. It is a useful tool for patients with paralysis who find it difficult to express their feelings and thoughts via body movements [1], [2]. Among devices such as functional near-infrared spectroscopy (fNIRS), functional magnetic resonance imaging (fMRI), and electroencephalogram (EEG) used to measure neuronal activities, EEGs have attracted considerable research attention due to their noninvasive monitoring potential with a high. A P300 speller, which mainly uses the temporal features of positive amplitude peaks appearing approximately 300 ms after the aforementioned stimuli is presented, is regarded as the most well-known paradigm in BCI community [8], [9]. In order to use such ERP-based BCI regardless of the

Methods
Results
Conclusion
Full Text
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