Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Jan 5;11(1):e0146610.
doi: 10.1371/journal.pone.0146610. eCollection 2016.

Hybrid EEG-fNIRS Asynchronous Brain-Computer Interface for Multiple Motor Tasks

Alessio Paolo Buccino  1   2 , Hasan Onur Keles  1 , Ahmet Omurtag  1
Affiliations

Hybrid EEG-fNIRS Asynchronous Brain-Computer Interface for Multiple Motor Tasks

Alessio Paolo Buccino et al. PLoS One. .

Abstract

Non-invasive Brain-Computer Interfaces (BCI) have demonstrated great promise for neuroprosthetics and assistive devices. Here we aim to investigate methods to combine Electroencephalography (EEG) and functional Near-Infrared Spectroscopy (fNIRS) in an asynchronous Sensory Motor rhythm (SMR)-based BCI. We attempted to classify 4 different executed movements, namely, Right-Arm-Left-Arm-Right-Hand-Left-Hand tasks. Previous studies demonstrated the benefit of EEG-fNIRS combination. However, since normally fNIRS hemodynamic response shows a long delay, we investigated new features, involving slope indicators, in order to immediately detect changes in the signals. Moreover, Common Spatial Patterns (CSPs) have been applied to both EEG and fNIRS signals. 15 healthy subjects took part in the experiments and since 25 trials per class were available, CSPs have been regularized with information from the entire population of participants and optimized using genetic algorithms. The different features have been compared in terms of performance and the dynamic accuracy over trials shows that the introduced methods diminish the fNIRS delay in the detection of changes.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: Ahmet Omurtag has a financial interest in Bio-Signal Group Inc., which makes the device microEEG that was used in this study. This does not alter the authors’ adherence to PLOS ONE policies on sharing data and materials.

Figures

Fig 1
Fig 1
Left: EEG electrodes and fNIRS optodes configuration on the cap. Right: Real picture of a subject wearing the cap completely mounted (with EEG electrodes, fNIRS sources and detectors).
Fig 2
Fig 2. EEG, fNIRS, and HYB Rest-Task classification accuracy [%] for a 1 s moving window with 50% overlap (top: EEG, middle: fNIRS, bottom: HYB).
The colored lines represent the different subjects and the black thick line is the average accuracy. The first black vertical line (at time 0 s) is the beginning of the task, while the second one (at time 6 s) is the end of it.
Fig 3
Fig 3. μ power, HbO averages, and HbO slopes (top: EEG, middle: HbO-average, bottom: HbO-slope) scalp plots along the trial (values are averaged over all subjects).
The values are computed every 1 s with 50% overlap and averaged over the time interval shown on top (e.g. [−3, −1]: values averaged between −3 s and −1 s). The task, as shown by the light blue rectangle at the bottom, starts at 0 s and ends at 6 s.
Fig 4
Fig 4. EEG, fNIRS, and HYB Right-Left classification accuracy [%] for a 1 s moving window with 50% overlap (top: EEG, middle: fNIRS, bottom: HYB).
The colored lines represent the different subjects and the black thick line is the average accuracy. The first black vertical line (at time 0 s) is the beginning of the task, while the second one (at time 6 s) is the end of it.
Fig 5
Fig 5. EEG, fNIRS, and HYB Arm-Hand classification accuracy [%] for a 1 s moving window with 50% overlap (top: EEG, middle: fNIRS, bottom: HYB).
The colored lines represent the different subjects and the black thick line is the average accuracy. The first black vertical line (at time 0 s) is the beginning of the task, while the second one (at time 6 s) is the end of it.
See this image and copyright information in PMC

References

    1. Wolpaw J, Wolpaw EW. Brain-Computer Interfaces: Principles and Practice. Oxford University Press, New York, NY; 2011.
    1. Penny WD, Roberts SJ, Curran EA, Stokes MJ. EEG-based communication: a pattern recognition approach. IEEE Transactions on Rehabilitation Engineering. 2000. June;8(2):214–215. 10.1109/86.847820 - DOI - PubMed
    1. Pfurtscheller G, Neuper C, Schlogl A, Lugger K. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Transactions on Rehabilitation Engineering. 1998. September;6(3):316–325. 10.1109/86.712230 - DOI - PubMed
    1. Pfurtscheller G, Brunner C, Schlogl A, Lopes da Silva FH. Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks. NeuroImage. 2006. May;31(1):153–159. 10.1016/j.neuroimage.2005.12.003 - DOI - PubMed
    1. Wang T, He B. An efficient rhythmic component expression and weighting synthesis strategy for classifying motor imagery EEG in a brain-computer interface. Journal of Neural Engineering. 2004. March;1(1):1 10.1088/1741-2560/1/1/001 - DOI - PubMed

Publication types

LinkOut - more resources