LASSO Homotopy-Based Sparse Representation Classification for fNIRS-BCI

Abstract

Brain-computer interface (BCI) systems based on functional near-infrared spectroscopy (fNIRS) have been used as a way of facilitating communication between the brain and peripheral devices. The BCI provides an option to improve the walking pattern of people with poor walking dysfunction, by applying a rehabilitation process. A state-of-the-art step-wise BCI system includes data acquisition, pre-processing, channel selection, feature extraction, and classification. In fNIRS-based BCI (fNIRS-BCI), channel selection plays a vital role in enhancing the classification accuracy of the BCI problem. In this study, the concentration of blood oxygenation (HbO) in a resting state and in a walking state was used to decode the walking activity and the resting state of the subject, using channel selection by Least Absolute Shrinkage and Selection Operator (LASSO) homotopy-based sparse representation classification. The fNIRS signals of nine subjects were collected from the left hemisphere of the primary motor cortex. The subjects performed the task of walking on a treadmill for 10 s, followed by a 20 s rest. Appropriate filters were applied to the collected signals to remove motion artifacts and physiological noises. LASSO homotopy-based sparse representation was used to select the most significant channels, and then classification was performed to identify walking and resting states. For comparison, the statistical spatial features of mean, peak, variance, and skewness, and their combination, were used for classification. The classification results after channel selection were then compared with the classification based on the extracted features. The classifiers used for both methods were linear discrimination analysis (LDA), support vector machine (SVM), and logistic regression (LR). The study found that LASSO homotopy-based sparse representation classification successfully discriminated between the walking and resting states, with a better average classification accuracy (p < 0.016) of 91.32%. This research provides a step forward in improving the classification accuracy of fNIRS-BCI systems. The proposed methodology may also be used for rehabilitation purposes, such as controlling wheelchairs and prostheses, as well as an active rehabilitation training technique for patients with motor dysfunction.

Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks

“…for channel selection can improve the accuracy of walking and resting states (Gulraiz et al, 2022). This method has aroused our great interest and may improve the accuracy of our proposed KF/a-GMM.…”

“…Future studies will increase the sample size to corroborate again. Ninth, channel selection plays a critical role in classifying mental tasks for fNIRS-BCI by reducing data dimensionality, saving model training time, and improving model classification performance (Gulraiz et al, 2022 ). Besides the commonly used Fisher score method for channel selection (Hwang et al, 2016 ), the least absolute shrinkage and selection operator homotopy-based sparse representation method proposed by Gulraiz et al for channel selection can improve the accuracy of walking and resting states (Gulraiz et al, 2022 ).…”

“…Ninth, channel selection plays a critical role in classifying mental tasks for fNIRS-BCI by reducing data dimensionality, saving model training time, and improving model classification performance (Gulraiz et al, 2022 ). Besides the commonly used Fisher score method for channel selection (Hwang et al, 2016 ), the least absolute shrinkage and selection operator homotopy-based sparse representation method proposed by Gulraiz et al for channel selection can improve the accuracy of walking and resting states (Gulraiz et al, 2022 ). This method has aroused our great interest and may improve the accuracy of our proposed KF/a-GMM.…”

A Hybrid GCN and Filter-Based Framework for Channel and Feature Selection: An fNIRS-BCI Study

“…In the case of classifcation accuracy, the selection of appropriate channels and features plays a vital role [22][23][24]. For active channel selection, averaging over all channels [25][26][27], averaging over a region of interest [28,29], t-and z-statistics [29][30][31][32], baseline correction [33], vector-phase analysis [31,[34][35][36], Pearson correlation coefcient [37], the contrast-to-noise ratio [38], LASSO homotopy-based sparse representation [39], and jointchannel-connectivity [40] methods are employed in fNIRSbased BCI studies. Temporal statistical characteristics of fNIRS signals time series (i.e., mean, slope, peak, minimum value, skewness, kurtosis, variance, and standard deviation) are the most commonly used features [6].…”

Metaheuristic Optimization-Based Feature Selection for Imagery and Arithmetic Tasks: An fNIRS Study

“…The selection of the channels and features is a key component for enhancing the BCI classification accuracy. In fNIRS-based BCI research, active channel selection has been performed using various methods, such as averaging on a particular region of interest [ 26 , 27 ], computing the Pearson correlation coefficient [ 28 ], performing vector phase analyses [ 21 , 29 , 30 , 31 ], averaging across all the channels [ 32 , 33 , 34 ], applying baseline corrections [ 24 ], calculating the contrast-to-noise ratios [ 35 ], using t-statistics and z-statistics [ 23 , 30 , 36 ], using a least absolute shrinkage and selection operator homotopy-based sparse representation [ 37 ], and utilizing joint-channel-connectivity methods [ 38 ].…”