Analysis of Different Classification Techniques for Two-Class Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface

Abstract

We analyse and compare the classification accuracies of six different classifiers for a two-class mental task (mental arithmetic and rest) using functional near-infrared spectroscopy (fNIRS) signals. The signals of the mental arithmetic and rest tasks from the prefrontal cortex region of the brain for seven healthy subjects were acquired using a multichannel continuous-wave imaging system. After removal of the physiological noises, six features were extracted from the oxygenated hemoglobin (HbO) signals. Two- and three-dimensional combinations of those features were used for classification of mental tasks. In the classification, six different modalities, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), k-nearest neighbour (kNN), the Naïve Bayes approach, support vector machine (SVM), and artificial neural networks (ANN), were utilized. With these classifiers, the average classification accuracies among the seven subjects for the 2- and 3-dimensional combinations of features were 71.6, 90.0, 69.7, 89.8, 89.5, and 91.4% and 79.6, 95.2, 64.5, 94.8, 95.2, and 96.3%, respectively. ANN showed the maximum classification accuracies: 91.4 and 96.3%. In order to validate the results, a statistical significance test was performed, which confirmed that the p values were statistically significant relative to all of the other classifiers (p < 0.005) using HbO signals.

Figure 1

(a) Schematic of the experimental paradigm: the blue blocks represent the 44 s rest periods at the beginning and at the end; the second, green block represents the 44 s mental arithmetic task; (b) optode placement and channel location on the prefrontal cortex. Fp1 and Fp2 are the reference points of the international 10-20 system.

Figure 2

3D scatter plot of the signal mean, signal peak, and signal skewness values of HbO (subject 2).

Figure 3

The averaged HbO and standard deviation (subject 2) for mental arithmetic and rest.

Figure 4

Classification accuracies using different types of classifiers from 2- and 3-dimensional combinations of features of Δc _HbO(t) signals across all subjects.