Key result
The proposed hybrid EEG-fNIRS method using a modified vector phase diagram achieved an improved classification accuracy of 86.0% compared to 63.8% using linear discriminant analysis in a 1.5 s window.
Why the study?
Enhanced classification accuracy and a sufficient number of commands are highly demanding in brain-computer interfaces, requiring early detection of brain commands.
Comparison
Novel classifier using a modified vector phase diagram and EEG power vs linear discriminant analysis
Authors
Loading...
Hypothesis-generating for hybrid EEG-fNIRS BCI; prospective validation required before clinical translation.
Absolute Event Rate: 86% vs 63.8%
A novel hybrid EEG-fNIRS classifier using a modified vector phase diagram improves the early detection accuracy of hemodynamic responses for brain-computer interfaces.
Khan et al. (2018) studied Healthy subjects (BCI motor task) (n=3). Modified vector phase diagram using EEG and fNIRS vs. Linear discriminant analysis (LDA) was evaluated on Classification accuracy. The proposed hybrid EEG-fNIRS method using a modified vector phase diagram achieved an improved classification accuracy of 86.0% compared to 63.8% using linear discriminant analysis in a 1.5 s window.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: