Fusing Frontal and Occipital EEG Features to Detect “Brain Switch” by Utilizing Convolutional Neural Network

Xin Zhang,Aravind Ravi,Ning Jiang,Wenqiang Yan,Guanghua Xu

doi:10.1109/access.2019.2924185

Xin Zhang, Aravind Ravi + Show 3 more

Open Access

PDF Available

https://doi.org/10.1109/access.2019.2924185

Copy DOI

Export

Save

Cite

Journal: IEEE Access	Publication Date: Jan 1, 2019
Citations: 6	License type: CC BY 4.0

Affiliation: Xi'an Jiaotong University, University of Waterloo

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Flicker is the most widely used steady-state visual evoked potential (SSVEP) stimulus. In addition, checkerboard can induce steady-state motion visual evoked potential (SSMVEP) in the occipital area. More recently, the action video is proposed to simultaneously elicit SSMVEP and induce sensorimotor area activations via the mirror neuron systems through Action Observation (AO). Integration of AO with brain–computer interface (BCI) is appealing for neural rehabilitation applications. In order to make such a BCI paradigm more feasible in neural rehabilitation, it is essential to discriminate whether a user is actively engaged with the BCI, i.e. intentional control (IC) state, or not engaged, i.e. non-intentional control (NC) state. In this study, the EEG responses to these three types of visual stimuli were compared for the first time and a convolutional neural network (CNN) was proposed to discriminate IC and NC states. A visual gaiting stimulus was designed to realize BCI-based AO. The results showed that the power of alpha rhythms from frontal area decreased more when the participants engaged at the gaiting stimuli than when the participants engaged at the other two types of stimuli. In addition, the correlation coefficient between the EEG from the occipital area and the template signals increased when the participants engaged at the stimuli. The results also clearly demonstrated the proposed CNN method can discriminate the IC and NC states. In addition, the combination of the attention feature from the frontal area and the SSVEP/SSMVEP feature from the occipital area showed significant performance improvement for the gaiting stimulus, but not for the other two types of stimuli.

Highlights

Brain-computer interfaces (BCI) can enable individuals to interact with external environments, such as a computer or other equipment without using regular output pathways of peripheral nerves and muscles [1]
When the participant gazing at the stimulus, the correlation coefficient values increased and the power of alpha rhythms decreased in all types of stimuli
The results showed that the power of alpha rhythms from frontal area decreased and ρ values increased when the participants gazed at the stimuli

Summary

Introduction

Brain-computer interfaces (BCI) can enable individuals to interact with external environments, such as a computer or other equipment without using regular output pathways of peripheral nerves and muscles [1]. Electroencephalographic (EEG) signals are mainly used in non-invasive BCIs, by exploiting neural information in the EEG such as motor imagery, movement-related cortical potential, P300, steadystate visual evoked potential (SSVEP) and so on. SSVEP is evoked by periodic visual stimulation with a stationary distinct spectrum with characteristic SSVEP peaks in EEG recording over occipital cortex [2]. SSVEP-based BCIs have advantages of high information transfer rate (ITR) and no need for subject training [3]. Checkerboard motion stimulus, and recently proposed action video are three different types of visual stimuli. Flicker is the most widely used SSVEP stimulus [3]. The checkerboard motion stimulus, i.e. the periodic motion stimulus, is able to induce steady-state motion visual evoked potential (SSMVEP) in the occipital area in the brain [4]–[6].

Methods

Results

Conclusion