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
Review
. 2018 Jun 28:12:246.
doi: 10.3389/fnhum.2018.00246. eCollection 2018.

Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces

Keum-Shik Hong  1   2 , M Jawad Khan  2 , Melissa J Hong  3
Affiliations
Review

Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces

Keum-Shik Hong et al. Front Hum Neurosci. .

Abstract

In this study, a brain-computer interface (BCI) framework for hybrid functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) for locked-in syndrome (LIS) patients is investigated. Brain tasks, channel selection methods, and feature extraction and classification algorithms available in the literature are reviewed. First, we categorize various types of patients with cognitive and motor impairments to assess the suitability of BCI for each of them. The prefrontal cortex is identified as a suitable brain region for imaging. Second, the brain activity that contributes to the generation of hemodynamic signals is reviewed. Mental arithmetic and word formation tasks are found to be suitable for use with LIS patients. Third, since a specific targeted brain region is needed for BCI, methods for determining the region of interest are reviewed. The combination of a bundled-optode configuration and threshold-integrated vector phase analysis turns out to be a promising solution. Fourth, the usable fNIRS features and EEG features are reviewed. For hybrid BCI, a combination of the signal peak and mean fNIRS signals and the highest band powers of EEG signals is promising. For classification, linear discriminant analysis has been most widely used. However, further research on vector phase analysis as a classifier for multiple commands is desirable. Overall, proper brain region identification and proper selection of features will improve classification accuracy. In conclusion, five future research issues are identified, and a new BCI scheme, including brain therapy for LIS patients and using the framework of hybrid fNIRS-EEG BCI, is provided.

Keywords: brain-computer interface; classification; electroencephalography; feature extraction; functional near-infrared spectroscopy; locked-in syndrome patient.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Typical brain-computer interface scheme for control applications with brain function recovery.
Figure 2
Figure 2
An illustration for BCI domain: BCI is required if there is no detectable muscular movement (BCI, brain-computer interface; LIS, locked-in syndrome; UWS, unresponsive wakeful state; MCD, minimal conscious disorder; MI, motor impairment; CI, cognitive impairment).
Figure 3
Figure 3
Distribution of the prefrontal tasks used for brain-computer interfaces: This chart was constructed using 102 papers (2002–2017) from the Web of Science (www.isiknowledge.com).
Figure 4
Figure 4
Partitioning the prefrontal cortex: Only a subregion showing the highest accuracy can be used for brain-computer interface purposes (for example, Region A was used by Khan and Hong, 2015).
Figure 5
Figure 5
Vector-phase diagram proposed by Kato (2003).
Figure 6
Figure 6
Bundled optode scheme: A schematic of densely configured fNIRS probes for deep brain imaging.
Figure 7
Figure 7
Illustration of vector-phase analysis for two choice decoding.
Figure 8
Figure 8
Features and classifiers used in fNIRS and hybrid EEG-fNIRS studies (64 fNIRS-BCI papers and 14 hybrid EEG-fNIRS papers from 2010 to 2017).
Figure 9
Figure 9
Proposed brain-computer interface (BCI) scheme to improve the BCI performance for device control for locked-in syndrome patients.
See this image and copyright information in PMC

References

    1. Abibullaev B., An J., Moon J. I. (2011). Neural network classification of brain hemodynamic responses from four mental tasks. Int. J. Optomechatr. 5, 340–359. 10.1080/15599612.2011.633209 - DOI
    1. Abibullaev B., An J. (2012). Classification of frontal cortex hemodynamic responses during cognitive tasks using wavelet transforms and machine learning algorithms. Med. Eng. Phys. 34, 1394–1410. 10.1016/j.medengphy.2012.01.002 - DOI - PubMed
    1. Aghajani H., Garbey M., Omurtag A. (2017). Measuring mental workload with EEG plus fNIRS. Front. Hum. Neurosci. 11:359 10.3389/fnhum.2017.00359 - DOI - PMC - PubMed
    1. Ahn M., Jun S. C. (2015). Performance variation in motor imagery brain-computer interface: a brief review. J. Neurosci. Methods 243, 103–110. 10.1016/j.jneumeth.2015.01.033 - DOI - PubMed
    1. Ahn S., Nguyen T., Jang H., Kim J. G., Jun S. C. (2016). Exploring neuro-physiological correlates of drivers' mental fatigue caused by sleep deprivation using simultaneous EEG, ECG, and fNIRS data. Front. Hum. Neurosci. 10:219 10.3389/fnhum.2016.00219 - DOI - PMC - PubMed