Related Experiment Video
Updated: May 12, 2026
04:44
Inter-Brain Synchrony in Open-Ended Collaborative Learning: An fNIRS-Hyperscanning Study
Published on: July 21, 2021
Towards a multimodal brain-computer interface: combining fNIRS and fTCD measurements to enable higher classification
1Bloorview Research Institute, Holland Bloorview Kids Rehabilitation Hospital, 150 Kilgour Rd., Toronto, Ontario, Canada. a.faress@utoronto.ca
Neuroimage
|April 2, 2013
Summary
Combining near-infrared spectroscopy (NIRS) and transcranial Doppler ultrasonography (TCD) signals in brain-computer interfaces (BCI) significantly improves classification accuracy. Multimodal neuroimaging offers a promising path for enhancing future BCI system performance.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Signal Processing
Background:
- Brain-computer interface (BCI) research traditionally relies on single neuroimaging modalities like near-infrared spectroscopy (NIRS) or transcranial Doppler ultrasonography (TCD).
- Multimodal BCIs, integrating data from diverse brain signal sources, are hypothesized to enhance system accuracy and robustness.
Purpose of the Study:
- To compare the classification accuracies of NIRS alone, TCD alone, and a combined NIRS-TCD system.
- To evaluate the efficacy of multimodal neuroimaging in improving BCI performance.
Main Methods:
- Simultaneous NIRS and TCD data acquisition from nine healthy participants performing a verbal fluency task or resting.
- Classification of task vs. rest states using Linear Discriminant Analysis (LDA).
Main Results:
- The combined NIRS-TCD system achieved a mean classification accuracy of 86.5±6.0%, outperforming NIRS (76.1±9.9%) and TCD (79.4±10.3%) alone.
- Significantly higher accuracies (p<0.05) were observed with the NIRS-TCD system in five out of nine participants compared to single modalities.
Conclusions:
- Multimodal neuroimaging, specifically combining NIRS and TCD, demonstrates potential for significantly improving BCI classification accuracy.
- This approach may pave the way for more effective and reliable brain-computer interfaces in the future.
