fNIRS-based Brain-computer Interface Research Articles

Enhancing Classification Accuracy with Integrated Contextual Gate Network: Deep Learning Approach for Functional Near-Infrared Spectroscopy Brain-Computer Interface Application.

Brain-computer interface (BCI) systems include signal acquisition, preprocessing, feature extraction, classification, and an application phase. In fNIRS-BCI systems, deep learning (DL) algorithms play a crucial role in enhancing accuracy. Unlike traditional machine learning (ML) classifiers, DL algorithms eliminate the need for manual feature extraction. DL neural networks automatically extract hidden patterns/features within a dataset to classify the data. In this study, a hand-gripping (closing and opening) two-class motor activity dataset from twenty healthy participants is acquired, and an integrated contextual gate network (ICGN) algorithm (proposed) is applied to that dataset to enhance the classification accuracy. The proposed algorithm extracts the features from the filtered data and generates the patterns based on the information from the previous cells within the network. Accordingly, classification is performed based on the similar generated patterns within the dataset. The accuracy of the proposed algorithm is compared with the long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM). The proposed ICGN algorithm yielded a classification accuracy of 91.23 ± 1.60%, which is significantly (p < 0.025) higher than the 84.89 ± 3.91 and 88.82 ± 1.96 achieved by LSTM and Bi-LSTM, respectively. An open access, three-class (right- and left-hand finger tapping and dominant foot tapping) dataset of 30 subjects is used to validate the proposed algorithm. The results show that ICGN can be efficiently used for the classification of two- and three-class problems in fNIRS-based BCI applications.

Unleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface.

In this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements to increase the number of control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, a well-known task in fNIRS and fMRI studies, but limited to left/right or few fingers. Twenty-four right-handed participants performed the individual finger-tapping task. Data were recorded by using sixteen sources and detectors placed over the motor cortex according to the 10-10 international system. The event's average oxygenated Δ HbO and deoxygenated Δ HbR hemoglobin data were utilized as features to assess the performance of diverse machine learning (ML) models in a challenging multi-class classification setting. These methods include LDA, QDA, MNLR, XGBoost, and RF. A new DL-based model named "Hemo-Net" has been proposed which consists of multiple parallel convolution layers with different filters to extract the features. This paper aims to explore the efficacy of using fNRIS along with ML/DL methods in a multi-class classification task. Complex models like RF, XGBoost, and Hemo-Net produce relatively higher test set accuracy when compared to LDA, MNLR, and QDA. Hemo-Net has depicted a superior performance achieving the highest test set accuracy of 76%, however, in this work, we do not aim at improving the accuracies of models rather we are interested in exploring if fNIRS has the neural signatures to help modern ML/DL methods in multi-class classification which can lead to applications like brain-computer interfaces. Multi-class classification of fine anatomical movements, such as individual finger movements, is difficult to classify with fNIRS data. Traditional ML models like MNLR and LDA show inferior performance compared to the ensemble-based methods of RF and XGBoost. DL-based method Hemo-Net outperforms all methods evaluated in this study and demonstrates a promising future for fNIRS-based BCI applications.

Hierarchical Classification Strategy for Mitigating the Impact of The Presence of Pain in fNIRS-based BCIs.

Brain computer interfaces (BCIs) can find applications in assistive systems for patients who experience conditions that impede their motor abilities. A BCI uses signals acquired from the brain to control external devices. As physical pain influences cortical signals, the presence of pain can negatively impact the performance of the BCI. In this work, we propose a strategy to mitigate this negative impact. Cortical signals are acquired from test subjects while they performed two mental arithmetic tasks, in the presence and the absence of painful stimuli. The task of the BCI is to reliably classify the two mental arithmetic tasks from the cortical recordings, irrespective of the presence or the absence of pain. We propose to do this classification, hierarchically, in two levels. In the first level, the data is classified into those captured in the presence and the absence of pain. Depending on the results of the classification from the first level, in the second level, the BCI performs the classification of tasks using a classifier trained either in the presence or the absence of pain. A 1-dimensional convolutional neural network (1D-CNN) is used for classification at both levels. It is observed that using this hierarchical strategy, the BCI is able to classify the tasks with an accuracy greater than 90%, irrespective of the presence or the absence of pain. Given that the presence of physical pain has shown previously to reduce the classification accuracy of a BCI to almost chance levels, this mitigation strategy will be a significant step towards enhancing the performance of BCIs when they are used in assistive systems for patients.

Synchronizing Motor Imagery Cue in fNIRS Brain-Computer Interface to reduce confounding effects of respiration.

Functional near-infrared spectroscopy (fNIRS) is a neuroimaging method that measures oxygenated hemoglobin (HbO) levels in the brain to infer neural activity using near-infrared light. Measured HbO levels are directly affected by a person's respiration. Hence, respiration cycles tend to confound fNIRS readings in motor imagery-based fNIRS Brain-Computer Interfaces (BCI). To reduce this confounding effect, we propose a method of synchronizing the motor imagery cue timing with the subject's respiration cycle using a breathing sensor. We conducted an experiment to collect 160 single trials from 10 subjects performing motor imagery using an fNIRS-based BCI and the breathing sensor. We then compared the HbO levels in trials with and without respiration synchronization. The results showed that respiration synchronization yielded HbO levels that were less dispersed across trials, and a negative correlation between the dispersion index of HbO levels with MI decoding accuracies was found across the 10 subjects. This showed that synchronizing motor imagery cues to respiration can yield increased HbO level consistency leading to better MI performance. Hence, the proposed method holds promise to improve the decoding performance of fNIRS-BCI by reducing the confounding effects of respiration.

CGAN-rIRN: a data-augmented deep learning approach to accurate classification of mental tasks for a fNIRS-based brain-computer interface.

Functional near-infrared spectroscopy (fNIRS) is increasingly used to investigate different mental tasks for brain-computer interface (BCI) control due to its excellent environmental and motion robustness. Feature extraction and classification strategy for fNIRS signal are essential to enhance the classification accuracy of voluntarily controlled BCI systems. The limitation of traditional machine learning classifiers (MLCs) lies in manual feature engineering, which is considered as one of the drawbacks that reduce accuracy. Since the fNIRS signal is a typical multivariate time series with multi-dimensionality and complexity, it makes the deep learning classifier (DLC) ideal for classifying neural activation patterns. However, the inherent bottleneck of DLCs is the requirement of substantial-scale, high-quality labeled training data and expensive computational resources to train deep networks. The existing DLCs for classifying mental tasks do not fully consider the temporal and spatial properties of fNIRS signals. Therefore, a specifically-designed DLC is desired to classify multi-tasks with high accuracy in fNIRS-BCI. To this end, we herein propose a novel data-augmented DLC to accurately classify mental tasks, which employs a convolution-based conditional generative adversarial network (CGAN) for data augmentation and a revised Inception-ResNet (rIRN) based DLC. The CGAN is utilized to generate class-specific synthetic fNIRS signals to augment the training dataset. The network architecture of rIRN is elaborately designed in accordance with the characteristics of the fNIRS signal, with serial multiple spatial and temporal feature extraction modules (FEMs), where each FEM performs deep and multi-scale feature extraction and fusion. The results of the paradigm experiments show that the proposed CGAN-rIRN approach improves the single-trial accuracy for mental arithmetic and mental singing tasks in both the data augmentation and classifier, as compared to the traditional MLCs and the commonly used DLCs. The proposed fully data-driven hybrid deep learning approach paves a promising way to improve the classification performance of volitional control fNIRS-BCI.

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

In recent decades, the brain-computer interface (BCI) has emerged as a leading area of research. The feature selection is vital to reduce the dataset's dimensionality, increase the computing effectiveness, and enhance the BCI's performance. Using activity-related features leads to a high classification rate among the desired tasks. This study presents a wrapper-based metaheuristic feature selection framework for BCI applications using functional near-infrared spectroscopy (fNIRS). Here, the temporal statistical features (i.e., the mean, slope, maximum, skewness, and kurtosis) were computed from all the available channels to form a training vector. Seven metaheuristic optimization algorithms were tested for their classification performance using a k-nearest neighbor-based cost function: particle swarm optimization, cuckoo search optimization, the firefly algorithm, the bat algorithm, flower pollination optimization, whale optimization, and grey wolf optimization (GWO). The presented approach was validated based on an available online dataset of motor imagery (MI) and mental arithmetic (MA) tasks from 29 healthy subjects. The results showed that the classification accuracy was significantly improved by utilizing the features selected from the metaheuristic optimization algorithms relative to those obtained from the full set of features. All of the abovementioned metaheuristic algorithms improved the classification accuracy and reduced the feature vector size. The GWO yielded the highest average classification rates (p < 0.01) of 94.83 ± 5.5%, 92.57 ± 6.9%, and 85.66 ± 7.3% for the MA, MI, and four-class (left- and right-hand MI, MA, and baseline) tasks, respectively. The presented framework may be helpful in the training phase for selecting the appropriate features for robust fNIRS-based BCI applications.

Transformer Model for Functional Near-Infrared Spectroscopy Classification.

Functional near-infrared spectroscopy (fNIRS) is a promising neuroimaging technology. The fNIRS classification problem has always been the focus of the brain-computer interface (BCI). Inspired by the success of Transformer based on self-attention mechanism in the fields of natural language processing and computer vision, we propose an fNIRS classification network based on Transformer, named fNIRS-T. We explore the spatial-level and channel-level representation of fNIRS signals to improve data utilization and network representation capacity. Besides, a preprocessing module, which consists of one-dimensional average pooling and layer normalization, is designed to replace filtering and baseline correction of data preprocessing. It makes fNIRS-T an end-to-end network, called fNIRS-PreT. Compared with traditional machine learning classifiers, convolutional neural network (CNN), and long short-term memory (LSTM), the proposed models obtain the best accuracy on three open-access datasets. Specifically, in the most extensive ternary classification task (30 subjects) that includes three types of overt movements, fNIRS-T, CNN, and LSTM obtain 75.49%, 72.89%, and 61.94% on test sets, respectively. Compared to traditional classifiers, fNIRS-T is at least 27.41% higher than statistical features and 6.79% higher than well-designed features. In the individual subject experiment of the ternary classification task, fNIRS-T achieves an average subject accuracy of 78.22% and surpasses CNN and LSTM by a large margin of +4.75% and +11.33%. fNIRS-PreT using raw data also achieves competitive performance to fNIRS-T. Therefore, the proposed models improve the performance of fNIRS-based BCI significantly.

Cross-Modal Transfer Learning From EEG to Functional Near-Infrared Spectroscopy for Classification Task in Brain-Computer Interface System.

The brain-computer interface (BCI) based on functional near-infrared spectroscopy (fNIRS) has received more and more attention due to its vast application potential in emotion recognition. However, the relatively insufficient investigation of the feature extraction algorithms limits its use in practice. In this article, to improve the performance of fNIRS-based BCI, we proposed a method named R-CSP-E, which introduces EEG signals when computing fNIRS signals’ features based on transfer learning and ensemble learning theory. In detail, we used the Independent Component Analysis (ICA) algorithm for the correspondence between the sources of the two signals. We then introduced the EEG signals when computing the spatial filter based on a modified Common Spatial Pattern (CSP) algorithm. Experimental results on public datasets show that the proposed method in this paper outperforms traditional methods without transfer. In general, the mean classification accuracy can be increased by up to 5%. To our knowledge, it is an innovation that we tried to apply transfer learning between EEG and fNIRS. Our study’s findings not only prove the potential of the transfer learning algorithm in cross-model brain-computer interface, but also offer a new and innovative perspective to research the hybrid brain-computer interface.

LASSO Homotopy-Based Sparse Representation Classification for fNIRS-BCI.

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.

Classification of Individual Finger Movements from Right Hand Using fNIRS Signals.

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 , , and 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.

See, Hear, or Feel - to Speak: A Versatile Multiple-Choice Functional Near-Infrared Spectroscopy-Brain-Computer Interface Feasible With Visual, Auditory, or Tactile Instructions.

Severely motor-disabled patients, such as those suffering from the so-called “locked-in” syndrome, cannot communicate naturally. They may benefit from brain-computer interfaces (BCIs) exploiting brain signals for communication and therewith circumventing the muscular system. One BCI technique that has gained attention recently is functional near-infrared spectroscopy (fNIRS). Typically, fNIRS-based BCIs allow for brain-based communication via voluntarily modulation of brain activity through mental task performance guided by visual or auditory instructions. While the development of fNIRS-BCIs has made great progress, the reliability of fNIRS-BCIs across time and environments has rarely been assessed. In the present fNIRS-BCI study, we tested six healthy participants across three consecutive days using a straightforward four-choice fNIRS-BCI communication paradigm that allows answer encoding based on instructions using various sensory modalities. To encode an answer, participants performed a motor imagery task (mental drawing) in one out of four time periods. Answer encoding was guided by either the visual, auditory, or tactile sensory modality. Two participants were tested outside the laboratory in a cafeteria. Answers were decoded from the time course of the most-informative fNIRS channel-by-chromophore combination. Across the three testing days, we obtained mean single- and multi-trial (joint analysis of four consecutive trials) accuracies of 62.5 and 85.19%, respectively. Obtained multi-trial accuracies were 86.11% for visual, 80.56% for auditory, and 88.89% for tactile sensory encoding. The two participants that used the fNIRS-BCI in a cafeteria obtained the best single- (72.22 and 77.78%) and multi-trial accuracies (100 and 94.44%). Communication was reliable over the three recording sessions with multi-trial accuracies of 86.11% on day 1, 86.11% on day 2, and 83.33% on day 3. To gauge the trade-off between number of optodes and decoding accuracy, averaging across two and three promising fNIRS channels was compared to the one-channel approach. Multi-trial accuracy increased from 85.19% (one-channel approach) to 91.67% (two-/three-channel approach). In sum, the presented fNIRS-BCI yielded robust decoding results using three alternative sensory encoding modalities. Further, fNIRS-BCI communication was stable over the course of three consecutive days, even in a natural (social) environment. Therewith, the developed fNIRS-BCI demonstrated high flexibility, reliability and robustness, crucial requirements for future clinical applicability.

Most favorable stimulation duration in the sensorimotor cortex for fNIRS-based BCI.

One of the primary objectives of the brain-computer interface (BCI) is to obtain a command with higher classification accuracy within the shortest possible time duration. Therefore, this study evaluates several stimulation durations to propose a duration that can yield the highest classification accuracy. Furthermore, this study aims to address the inherent delay in the hemodynamic responses (HRs) for the command generation time. To this end, HRs in the sensorimotor cortex were evaluated for the functional near-infrared spectroscopy (fNIRS)-based BCI. To evoke brain activity, right-hand-index finger poking and tapping tasks were used. In this study, six different stimulation durations (i.e., 1, 3, 5, 7, 10, and 15 s) were tested on 10 healthy male subjects. Upon stimulation, different temporal features and multiple time windows were utilized to extract temporal features. The extracted features were then classified using linear discriminant analysis. The classification results using the main HR showed that a 5 s stimulation duration could yield the highest classification accuracy, i.e., 74%, with a combination of the mean and maximum value features. However, the results were not significantly different from the classification accuracy obtained using the 15 s stimulation. To further validate the results, a classification using the initial dip was performed. The results obtained endorsed the finding with an average classification accuracy of 73.5% using the features of minimum peak and skewness in the 5 s window. The results based on classification using the initial dip for 5 s were significantly different from all other tested stimulation durations (p < 0.05) for all feature combinations. Moreover, from the visual inspection of the HRs, it is observed that the initial dip occurred as soon as the task started, but the main HR had a delay of more than 2 s. Another interesting finding is that impulsive stimulation in the sensorimotor cortex can result in the generation of a clearer initial dip phenomenon. The results reveal that the command for the fNIRS-based BCI can be generated using the 5 s stimulation duration. In conclusion, the use of the initial dip can reduce the time taken for the generation of commands and can be used to achieve a higher classification accuracy for the fNIRS-BCI within a 5 s task duration rather than relying on longer durations.

Subject-Independent Functional Near-Infrared Spectroscopy-Based Brain-Computer Interfaces Based on Convolutional Neural Networks.

Functional near-infrared spectroscopy (fNIRS) has attracted increasing attention in the field of brain–computer interfaces (BCIs) owing to their advantages such as non-invasiveness, user safety, affordability, and portability. However, fNIRS signals are highly subject-specific and have low test-retest reliability. Therefore, individual calibration sessions need to be employed before each use of fNIRS-based BCI to achieve a sufficiently high performance for practical BCI applications. In this study, we propose a novel deep convolutional neural network (CNN)-based approach for implementing a subject-independent fNIRS-based BCI. A total of 18 participants performed the fNIRS-based BCI experiments, where the main goal of the experiments was to distinguish a mental arithmetic task from an idle state task. Leave-one-subject-out cross-validation was employed to evaluate the average classification accuracy of the proposed subject-independent fNIRS-based BCI. As a result, the average classification accuracy of the proposed method was reported to be 71.20 ± 8.74%, which was higher than the threshold accuracy for effective BCI communication (70%) as well as that obtained using conventional shrinkage linear discriminant analysis (65.74 ± 7.68%). To achieve a classification accuracy comparable to that of the proposed subject-independent fNIRS-based BCI, 24 training trials (of approximately 12 min) were necessary for the traditional subject-dependent fNIRS-based BCI. It is expected that our CNN-based approach would reduce the necessity of long-term individual calibration sessions, thereby enhancing the practicality of fNIRS-based BCIs significantly.

A Unified Analytical Framework With Multiple fNIRS Features for Mental Workload Assessment in the Prefrontal Cortex.

Knowing the actual level of mental workload is important to ensure the efficacy of brain-computer interface (BCI) based cognitive training. Extracting signals from limited area of a brain region might not reveal the actual information. In this study, a functional near-infrared spectroscopy (fNIRS) device equipped with multi-channel and multi-distance measurement capability was employed for the development of an analytical framework to assess mental workload in the prefrontal cortex (PFC). In addition to the conventional features, e.g. hemodynamic slope, we introduced a new feature - deep contribution ratio which is the proportion of cerebral hemodynamics to the fNIRS signals. Multiple sets of features were examined by a simple logical operator to suppress the false detection rate in identifying the activated channels. Using the number of activated channels as input to a linear support vector machine (SVM), the performance of the proposed analytical framework was assessed in classifying three levels of mental workload. The best set of features involves the combination of hemodynamic slope and deep contribution ratio, where the identified number of activated channels returned an average accuracy of 80.6% in predicting mental workload, compared to a single conventional feature (accuracy: 59.8%). This suggests the feasibility of the proposed analytical framework with multiple features as a means towards a more accurate assessment of mental workload in fNIRS-based BCI applications.

Discrimination of Two-Class Motor Imagery in a fNIRS Based Brain Computer Interface.

The purpose of this study was to discriminate between left- and right-hand motor imagery tasks. We recorded the brain signals from two participants using a fNIRS system and compared different feature extraction (mean, peak, minimum, skewness and kurtosis) and classification techniques (linear (LDA) and quadratic discriminant analysis (QDA), support vector machine (SVM), logistic regression, K-nearest-neighbor (KNN), and neural networks with Levenberg-Marquardt (LMA), Bayesian Regularization (BRANN) and Scaled Conjugate Gradient (SCGA) training algorithms). The results showed poor classification accuracies (<; 58%) when skewness and kurtosis were used. When mean, peak, and minimum were used as features, QDA, SVM and KNN produced higher classification accuracies relative to LDA and logistic regression. Overall, BRANN led to the highest accuracies (>98%) when mean, peak and minimum were used as features.

Effect of stimulation duration to the existence of initial dip.

In this paper, we investigate the effect of stimulation durations on the hemodynamic responses (HRs) in the somatosensory cortex. In doing so, the relationship between stimulation duration and the initial dip is also investigated. The HRs are measured using functional near-infrared spectroscopy (fNIRS). The HR signals related to finger poking are acquired from the left somatosensory cortex. Two different stimulation durations (i.e., 1 and 5 sec) were tested in this study. From the results of the study, it is concluded that the stimulation duration of 1 sec (short stimulus) evokes initial dip in the somatosensory cortex, but it disappears as the stimulation duration gets longer. Therefore, the 1-sec stimulation duration can serve the purpose of the fNIRS-based brain-computer interface.

Enhancing Communication for People in Late-Stage ALS Using an fNIRS-Based BCI System.

Brain-computer interface (BCI) based communication remains a challenge for people with later-stage amyotrophic lateral sclerosis (ALS) who lose all voluntary muscle control. Although recent studies have demonstrated the feasibility of functional near-infrared spectroscopy (fNIRS) to successfully control BCIs primarily for healthy cohorts, these systems are yet inefficient for people with severe motor disabilities like ALS. In this study, we developed a new fNIRS-based BCI system in concert with a single-trial Visuo-Mental (VM) paradigm to investigate the feasibility of enhanced communication for ALS patients, particularly those in the later stages of the disease. In the first part of the study, we recorded data from six ALS patients using our proposed protocol (fNIRS-VM) and compared the results with the conventional electroencephalography (EEG)-based multi-trial P3Speller (P3S). In the second part, we recorded longitudinal data from one patient in the late locked-in state (LIS) who had fully lost eye-gaze control. Using statistical parametric mapping (SPM) and correlation analysis, the optimal channels and hemodynamic features were selected and used in linear discriminant analysis (LDA). Over all the subjects, we obtained an average accuracy of 81.3%±5.7% within comparatively short times (< 4 sec) in the fNIRS-VM protocol relative to an average accuracy of 74.0%±8.9% in the P3S, though not competitive in patients with no substantial visual problems. Our longitudinal analysis showed substantially superior accuracy using the proposed fNIRS-VM protocol (73.2%±2.0%) over the P3S (61.8%±1.5%). Our findings indicate the potential efficacy of our proposed system for communication and control for late-stage ALS patients.

Detecting self-paced walking intention based on fNIRS technology for the development of BCI.

Since more and more elderly people suffer from lower extremity movement problems, it is of great social significance to assist persons with motor dysfunction to walk independently again and reduce the burden on caregivers. The self-paced walking intention, which could increase the ability of self-control on the start and stop of motion, was studied by applying brain-computer interface (BCI) technology, a novel research field. The cerebral hemoglobin signal, which was obtained from 30 subjects by applying functional near-infrared spectroscopy (fNIRS) technology, was processed to detect self-paced walking intention in this paper. Teager-Kaiser energy was extracted at each sampling point for five sub-bands (0.0095~0.021Hz, 0.021~0.052Hz, 0.052~0.145Hz, 0.145~0.6Hz, and 0.6~2.0Hz). Gradient boosting decision tree (GBDT) was then utilized to establish the detecting model in real-time. The proposed method had a good performance to detect the walking intention and passed the pseudo-online test with a true positive rate of 100% (80/80), a false positive rate of 2.91% (4822/165171), and a detection latency of 0.39 ± 1.06s. GBDT method had an area under the curve value of 0.944 and was 0.125 (p < 0.001) higher than linear discriminant analysis (LDA). The results reflected that it is feasible to decode self-paced walking intention by applying fNIRS technology. This study lays a foundation for applying fNIRS-based BCI technology to control walking assistive devices practically. Graphical abstract Graphical representation of the detecting process for pseudo-online test. The lower figure is a partial enlargement of the upper figure. In the lower figure, the blue line represents the probability of walking predicted by GBDT without smoothing and the orange-red line represents the smoothed probability. The dark-red ellipse shows the effect of the smoothing-threshold method.

A Between-Subject fNIRS-BCI Study on Detecting Self-Regulated Intention During Walking.

Most BCI (brain-computer interface) studies have focused on detecting motion intention from a resting state. However, the dynamic regulation of two motion states, which usually happens in real life, is rarely studied. Besides, popular within-subject methods also require an extensive and time-consuming learning stage when testing on a new subject. This paper proposed a method to discriminate dynamic gait- adjustment intention with strong adaptability for different subjects. Cerebral hemoglobin signals obtained from 30 subjects were studied to decode gait-adjustment intention. Cerebral hemoglobin information was recorded by using fNIRS (functional near infrared spectroscopy) technology. Mathematical morphology filtering was applied to remove zero drift and EWM (Entropy Weight Method) was used to calculate the average hemoglobin values over Regions of Interest (ROIs). The gradient boosting decision tree (GBDT) was utilized to detect the onset of self-regulated intention. A 2-layer-GA-SVM (Genetic Algorithm-Support Vector Machine) model based on stacking algorithm was further proposed to identify the four types of self-regulated intention (speed increase, speed reduction, step increase, and step reduction). It was found that GBDT had a good performance to detect the onset intention with an average AUC (Area Under Curve) of 0.894. The 2-layer-GA-SVM model boosted the average ACC (accuracy) of four types of intention from 70.6% to 84.4% ( p = 0.005 ) from the single GA-SVM model. Furthermore, the proposed method passed pseudo-online test with the average results as following: AUC = 0.883, TPR (True Positive Rate) = 97.5%, FPR (False Positive Rate) = 0.11%, and LAY (Detection Latency) = -0.52 ± 2.57 seconds for the recognition of gait-adjustment intention; ACC = 80% for the recognition of adjusted gait. The results indicate that it is feasible to decode dynamic gait-adjustment intentions from a motion state for different subjects based on fNIRS technology. It has a potential to realize the practical application of fNIRS-based brain-computer interface technology in controlling walking-assistive devices.

Resting-State-Based Spatial Filtering for an fNIRS-Based Motor Imagery Brain-Computer Interface

Functional near-infrared spectroscopy (fNIRS) has attracted much attention in brain-computer interface (BCI) area due to its advantages of portability, robustness to electrical artifacts, etc. However, in practical applications, fNIRS-based BCI usually needs a labor-intensive and time-consuming training session (calibration procedure) to optimize the user-specific neural spatial and temporal patterns for further classification. Recently, studies revealed that neural spatial and temporal patterns extracted from user-specific resting-state brain signals were closely related to those of his/her task data. In this study, we proposed a resting-state independent component analysis (RSICA) based spatial filtering algorithm aiming at extracting individual task-related spatial and temporal brain patterns from the resting-state data. Specifically, independent component analysis (ICA) was applied to extract different independent components (ICs) from resting-state fNIRS data. The ICs with their spatial filter weights maximally lateralized over the sensorimotor regions were regarded as most relevant to motor imagery. These spatial filters were used to spatially filter the multi-channel motor imagery task data for feature extraction. Based on 8-minute resting-state data and a small training dataset (20 trials) from 10 participants, the proposed RSICA algorithm achieved an approximately 7% increase in left vs. right hand motor imagery classification accuracy, as compared to the conventional common spatial pattern (CSP)-based and shrinkage algorithms (69.8±12.1%, 63.3±10.3% and 63.4±11.8%, respectively). For acquiring a similar level of classification accuracy (i.e. 70%), the number of training data required could be reduced from 36 trials (CSP) to 22 trials (RSICA). As a relatively small training set is required to obtain a satisfactory performance, training burden is significantly reduced by RSICA, which might be useful for developing practical fNIRS-based motor imagery BCIs.