Classification of Individual Finger Movements from Right Hand Using fNIRS Signals

Abstract

Functional near-infrared spectroscopy (fNIRS) is a comparatively new noninvasive, portable, and easy-to-use brain imaging modality. However, complicated dexterous tasks such as individual finger-tapping, particularly using one hand, have been not investigated using fNIRS technology. Twenty-four healthy volunteers participated in the individual finger-tapping experiment. Data were acquired from the motor cortex using sixteen sources and sixteen detectors. In this preliminary study, we applied standard fNIRS data processing pipeline, i.e., optical densities conversation, signal processing, feature extraction, and classification algorithm implementation. Physiological and non-physiological noise is removed using 4th order band-pass Butter-worth and 3rd order Savitzky-Golay filters. Eight spatial statistical features were selected: signal-mean, peak, minimum, Skewness, Kurtosis, variance, median, and peak-to-peak form data of oxygenated haemoglobin changes. Sophisticated machine learning algorithms were applied, such as support vector machine (SVM), random forests (RF), decision trees (DT), AdaBoost, quadratic discriminant analysis (QDA), Artificial neural networks (ANN), k-nearest neighbors (kNN), and extreme gradient boosting (XGBoost). The average classification accuracies achieved were 0.75±0.04, 0.75±0.05, and 0.77±0.06 using k-nearest neighbors (kNN), Random forest (RF) and XGBoost, respectively. KNN, RF and XGBoost classifiers performed exceptionally well on such a high-class problem. The results need to be further investigated. In the future, a more in-depth analysis of the signal in both temporal and spatial domains will be conducted to investigate the underlying facts. The accuracies achieved are promising results and could open up a new research direction leading to enrichment of control commands generation for fNIRS-based brain-computer interface applications.

Keywords: classification; finger-tapping; functional near-infrared spectroscopy (fNIRS); machine learning; motor cortex.

Figure 1

(A) Experimental setup; (B) optodes arrangement; (C) overcap to reduce external light; (D) optodes holder.

Figure 2

Experimental paradigm visualization. Single experiment consists of three sessions of each finger tapping trail. Single trial consists of 10 s task and 10 s finger tapping.

Figure 3

(A) Source-detector placement over motor cortex. Figure 3A Colour code: Red (source), Blue (detector), Green (channels), and black colour represent channel numbers. (B) Demonstration of total haemoglobin changes over motor cortex during index finger tapping.

Figure 4

Comparison of different classifiers on basis of performance parameters (accuracy, precision, recall F1score).

Figure 5

Confusion metrics for all classifiers for subject one (S01); Classes are labeled as ‘0’, ‘1’, ‘2’, ‘3’, ‘4’ and ‘5’, which stands for ‘Rest’, ‘Thumb’, ‘Index’, ‘Middle’, ‘Ring’, and ‘Little’ finger-tapping classes, respectively. (a) Quadratic discriminant analysis (QDA). (b) AdaBoost. (c) Support vector machine (SVM). (d) Decision tree (DT). (e) Artificial neural networks (ANN). (f) k-nearest neighbors (kNN). (g) Random forest (RF). (h) Extreme Gradient Boosting (XGBoost).

Figure 6

Oxygenated haemoglobin Signal for complete experimental trail.