Single-trial classification of fNIRS signals in four directions motor imagery tasks measured from prefrontal cortex

As a promising non-invasive technique, functional near-infrared spectroscopy (fNIRS) can easily detect the hemodynamic responses of cortical brain activities. This paper investigated the multiclass classification of motor imagery (MI) based on fNIRS; ten healthy individuals were recruited to move an object using their imagination. A multi-channel continuous-wave fNIRS equipment was applied to obtain the signals from the prefrontal cortex. A combination of ensemble empirical mode decomposition and independent component analysis method was used to solve the signal-noise frequency spectrum aliasing issues caused by the Mayer wave (0.1 Hz), then the signal means features were extracted as an input of linear discriminant analysis and support vector machine (SVM) classifier. The SVM classifier shows better classification results, and the average accuracies of four directions, up-down and left-right were 40.55%, 73.05%, and 70.7%, respectively, using oxygenated hemoglobin (8-21 s). This paper demonstrated that Brodmann area 4 was activated, which is consistent with previous conclusions. Furthermore, we found that the orbitofrontal cortex is also involved in MI and O2sat can also serve as a classified index.