Upcoming CMBES Webinar

Advancements in the Brain-Computer Interface

Assessing a Combined EEG and fNIRS Brain Computer Interface to Improve Accuracies During a Motor Imagery Task   

Join us on January 12th at 2:00pm EST

The world of wearable technologies has been exploding over the past few years, with concepts originally thought of as science fiction making their way from the research lab into our hospitals and on the street.  This talk will be the first in, hopefully, a series that will delve into the science and engineering behind what will soon be a commonplace technology.  Consider the short but meteoric development arc of the smart-watch with its capabilities and you can appreciate the potential here.  And there are so many other devices and systems that also will be incorporating this technology.  So, whether you will be using the technologies or simply wanting to do your due diligence homework before these devices hit your hospital or rehabilitation centre, this is a talk for you.  It is more than an academic talk, but rather a very important backgrounder that will be of interest to a very broad array of biomedical engineers and technologists.    

Abstract: Brain computer interfaces (BCIs) are promising technologies that enable persons with severe disabilities to interact with their surroundings using control signals generated from their brain rather than their muscles. Electroencephalography (EEG) and functional near infrared spectroscopy (fNIRS) are two commonly used non-invasive brain imaging modalities in BCI systems. EEG records the electrical activity produced by neuronal activations whereas fNIRS measures the concentration changes of oxy- and deoxy-hemoglobin molecules in the brain cortex. The purpose of this study was to investigate the impact of combining EEG and fNIRS in a BCI compared to a single-modality system. The brain signals were recorded during a bilateral right- and left-hand motor imagery task. Motor imagery is the mental rehearsal of a motor action without overt movement. The results showed significant improvements in classification accuracies in a combined EEG and fNIRS BCI system compared to EEG or fNIRS alone       

Amir Moslehi, PhD.
Biomedical Engineering
Department of Mechanical & Materials Engineering 
Queen's University, Kingston, ON, Canada

Click here to Register

Return to the news page