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.

Integration of Teaching Processes and Learning Assessment in the Prefrontal Cortex during a Video Game Teaching–learning Task

“…Indeed, if the PFC activity were to facilitate the teaching–learning process, its feedback to the teacher during the teaching–learning task might act similarly as a brain–computer interface (BCI) neuro-feedback training. Recently, several studies had reported NIRS-based BCI focusing on the PFC activity (Naseer et al, 2016a,b). In order to evaluate whether the PFC signals during teaching–learning tasks are suitable for NIRS-based BCI training, it is a prerequisite to calculate the classification accuracies of pattern recognition and discrimination in BCI by cross-validation in future studies (Naseer et al, 2014).…”

Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients

“…These features were calculated across all 12 channels for the MI and MR. All of the feature values were scaled between 0 and 1 using the equation $x^{MathClass-rel\prime }MathClass-rel=\frac{xMathClass-bin-\text{min}\left(x\right)}{\text{max}\left(x\right)MathClass-bin-\text{min}\left(x\right)}$ where x  ∈  R n represents the original feature values, x ′ denotes the rescaled feature values between 0 and 1, max( x ) is the largest value, and min( x ) is the smallest value. After extracting the features from the β values, SVM was used to classify the MI and MR tasks (Naseer et al, 2016b). SVM maximizes the margins between classes by creating hyperplanes that minimize the cost function $\begin{array}{c}leftalign-starleftalign-odd\text{Minimize }\frac{1}{2}{\mathrm{||}w\mathrm{||}}^2+C{\sum }_{i=1}^n{\mathrm{\xi }}_i\\ leftalign-odd\text{Subject to }{z}_i\left(w^T{x}_i+b\right)\ge 1-{\mathrm{\xi }}_i,{\mathrm{\xi }}_i\ge 0\end{array}$ where w T , x i  ∈  R 2 and b ∈  R 1 , || w || 2  =  w T w , C is the trade-off parameter between the error and the margin, ξ i is the measure of the training data, and z i is the class label for the i -th sample.…”

Subject-independent decoding of affective states using functional near-infrared spectroscopy

“…This approach was used in order to test fNIRS based MDB of affective state with the least assumptions possible, to avoid introducing spurious artifact in the signal and to test the feasibility for posterior real-time analysis (Coyle et al, 2007, Sitaram et al, 2007. In comparison, recent studies identified that combining the mean hemoglobin concentration with other temporal and time-frequency features improves the decoding accuracies reaching values close to 90% in within-subject decoding (Tai and Chau, 2009, Naseer et al, 2016a, Naseer et al, 2016b. Therefore, future studies should also evaluate the effect of different feature extraction techniques to the inter-participants MBD of affective states.…”