Enhancing classification accuracy of fNIRS-BCI using features acquired from vector-based phase analysis

Abstract

Objective. In this paper, a novel methodology for feature extraction to enhance classification accuracy of functional near-infrared spectroscopy (fNIRS)-based two-class and three-class brain–computer interface (BCI) is presented. Approach. Novel features are extracted using vector-based phase analysis method. Changes in oxygenated Δ H b O and de-oxygenated ( Δ H b R ) haemoglobin are used to calculate four novel features: change in cerebral blood volume ( Δ C B V ), change in cerebral oxygen exchange ( Δ C O E ), vector magnitude (|L|) and angle (k). Δ C B V is the sum and Δ C O E is difference of Δ H b O and Δ H b R , whereas |L| is magnitude and k is angle of vector. fNIRS signals of seven healthy subjects, corresponding to left-hand index finger tapping (LFT), right-hand index finger tapping (RFT) and rest are acquired from motor cortex using multi-channel continuous-wave imaging system. After removing physiological and instrumental noises from the acquired signals, the four novel features are calculated. For validation, conventional temporal, spatial and spatiotemporal features; mean, peak, slope, variance, kurtosis and skewness are also calculated using Δ H b O and Δ H b R . All possible two-feature and three-feature combinations of the novel and conventional features are then used to classify two-class (LFT vs RFT) and three-class (LFT vs RFT vs rest) fNIRS-BCI using linear discriminant analysis. Main results. Results demonstrate that combination of four novel features yields significantly higher average classification accuracies of 98.7 ± 1.0% and 85.4 ± 1.4% as compared to 68.7 ± 6.9% and 53.6 ± 10.6% using conventional features for two-class and three-class problem, respectively. Validation of proposed method on an open access database containing RFT, LFT and dominant side foot tapping tasks for 30 subjects also shows improvement in average classification accuracies for two-class and three-class fNIRS-BCIs. Significance. This study provides a step forward in improving the classification accuracies of state-of-the-art fNIRS-BCIs by showing significant improvement in classification accuracies of two-class and three-class fNIRS-BCIs using novel features extracted by vector-based phase analysis.

Enhancing Classification Performance of fNIRS-BCI by Identifying Cortically Active Channels Using the z-Score Method

“…In the present study, the authors proposed a new method of selecting cortical-activation-based channels to increase fNIRS-BCI performance, especially in terms of classification accuracy and COI/ROI. In the literature, recent studies have also focussed on enhancing classification accuracies of fNIRS-BCI systems by optimal classification technique [60], optimal feature selection [24,54], optimal feature-combination [57], general linear model [25], vector-based phase analysis [26,61,62], t-value method [22,37,41,63], cross-correlation [33], and dominant channel selection [64]. Accurate and reliable fNIRS-BCI performance may lead to producing applications in neurorobotics, rehabilitation, clinical BCI for monitoring and analysis, and neuroergonomics [10,[65][66][67].…”

Vector Phase Analysis Approach for Sleep Stage Classification: A Functional Near-Infrared Spectroscopy-Based Passive Brain–Computer Interface

“…If the hemodynamic indicators of fNIRS signals ( HbO and HbR) are mapped as orthogonal axes in an orthogonal vector coordinate plane, then they give rise to a very promising scheme regarded as VPA method as shown in Figure 3. When this orthogonal coordinate plane is rotated by an angle of π /4 rad counterclockwise, then it adds up new useful components in this vector plane: HbT and COE (due to neurovascular coupling) (Yoshino and Kato, 2012;Hong and Naseer, 2016;Hong et al, 2018;Zafar and Hong, 2018;Nazeer et al, 2020a). These indices are defined as,…”

“…Any point on this vector coordinate plane holds a value-based upon four indices HbO, HbR, HbT , and COE; and its distance from the origin specifies a vector R that reveals information about CORE (Yoshino and Kato, 2012;Hong and Naseer, 2016;Nazeer et al, 2020a). The magnitude |R| and angle R of vector R are stated below.…”

“…As drowsiness detection is intended from VPA, six features were selected by keeping in view the promising information of vector phase diagram, which are trajectory slopes of VPA indices and parameters; m( HbO), m( HbR), m( HbT), m( COE), m( R), and m(|R|). Other three statistical features were extracted from HbO time signal, namely, signal mean (M), signal peak (P), and the sum of peaks (SoP), which were reported to be the best suitable features of fNIRS signal for binary class classification of drowsiness activity (Khan and Hong, 2015;Tanveer et al, 2019;Nazeer et al, 2020a). All features were computed for the 0-5 s time window for all subjects according to the following relations.…”

Summary of over Fifty Years with Brain-Computer Interfaces—A Review

“…Another interesting brain's activity measurement method is functional near-infrared spectroscopy (fNIRS), which is a low-cost, non-invasive and portable technique [91,[142][143][144]. Despite its lower spatial resolution to the one obtained from the fMRI and the lower temporal resolution to the one obtained from the EEG, it can be a good alternative to those two.…”