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

TLDR

The study compares classification accuracies of six classifiers for mental arithmetic versus rest tasks using fNIRS signals. Seven healthy subjects’ prefrontal fNIRS signals were recorded, denoised, and six HbO features were extracted and combined in 2‑ and 3‑dimensional sets, then classified with six algorithms (LDA, QDA, kNN, Naïve Bayes, SVM, ANN). The classifiers achieved average accuracies ranging from 69.7 % to 96.3 %, with ANN attaining the highest 91.4 % (2‑D) and 96.3 % (3‑D) accuracies, and statistical tests confirmed these results were significant (p < 0.005).

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.