No abstract

Near-Infrared Spectroscopy (NIRS)-based BrainComputer Interface (BCI) was recently studied for numerical cognition. This study presents a study using high density 348 channels NIRS-based BCI from 8 healthy subjects while solving mental arithmetic problems with two difficulty levels and the rest condition. The existing feature extraction and selection methods on the existing study were presented only for low density 16 channels NIRS-based BCI, and required the specification on the number of features to select to yield desirable performance. This paper presents a method of extracting discriminative features from high density single-trial NIRS data using common average reference spatial filtering and single-trial baseline reference, and a method of automatically selecting a set of discriminative and non-redundant features using the Mutual Information-based Rough Set Reduction (MIRSR) and Supervised Pseudo SelfEvolving Cerebellar (SPSEC) algorithms. The performance of the proposed method is evaluated using 5×5-fold crossvalidations on the single-trial NIRS data collected using the support vector machine classifier. The results yielded an overall average accuracy of 71.4% and 91.0% in classifying hard versus easy tasks and hard versus rest tasks respectively using the proposed method, compared to 46.1% and 62.2% respectively using existing methods. The results demonstrated the effectiveness of using the proposed feature extraction and selection method in high density NIRS-based BCI for assessing numerical cognition.

Recent studies have shown that pleasant and unpleasant emotions could be detected through functional Near-Infrared Spectroscopy (fNIRS). This study investigates the prefrontal cortical activation in human subjects while they were viewing urban and garden scenes. A multi-channel continuous wave fNIRS system was used to record the prefrontal cortical activations from seven subjects. During the data collection, the subjects viewed 40 trials of video clips. In each trial, the subjects viewed a video of randomized urban or garden scenes for 30s followed by 30s of idle scene which showed a dark blue progress bar on black background on the screen. NIRS-SPM is employed to work out the changes of hemoglobin response and the prefrontal cortical activations were generated using group analysis based on the contrasts of urban versus idle, garden versus idle and urban versus garden. The activation for the contrast of urban versus garden showed an increase of oxy-hemoglobin on the right area of the prefrontal cortex with p <; 0.05. This preliminary result showed that the garden scene might provide a pleasant and less stressful experience as compared to the urban scene for subjects. This suggests the possibility of using a NIRS-based Brain-Computer Interface to detect subject preferences of different scenes.