Improving inter-session performance via relevant session-transfer for multi-session motor imagery classification.

Motor imagery (MI)-based brain-computer interfaces (BCIs) using electroencephalography (EEG) have found practical applications in external device control. However, the non-stationary nature of EEG signals remains to obstruct BCI performance across multiple sessions, even for the same user. In this study, we aim to address the impact of non-stationarity, also known as inter-session variability, on multi-session MI classification performance by introducing a novel approach, the relevant session-transfer (RST) method. Leveraging the cosine similarity as a benchmark, the RST method transfers relevant EEG data from the previous session to the current one. The effectiveness of the proposed RST method was investigated through performance comparisons with the self-calibrating method, which uses only the data from the current session, and the whole-session transfer method, which utilizes data from all prior sessions. We validated the effectiveness of these methods using two datasets: a large MI public dataset (Shu Dataset) and our own dataset of gait-related MI, which includes both healthy participants and individuals with spinal cord injuries. Our experimental results revealed that the proposed RST method leads to a 2.29 % improvement (p < 0.001) in the Shu Dataset and up to a 6.37 % improvement in our dataset when compared to the self-calibrating method. Moreover, our method surpassed the performance of the recent highest-performing method that utilized the Shu Dataset, providing further support for the efficacy of the RST method in improving multi-session MI classification performance. Consequently, our findings confirm that the proposed RST method can improve classification performance across multiple sessions in practical MI-BCIs.

Differentiating changes in movement-related EEG response induced by transcranial direct current stimulation using convolutional neural network.

Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique that can modulate neuronal excitability and induce brain plasticity. Although tDCS has been studied with various methods, more research is needed on the movement-related electroencephalography (EEG) changes induced by tDCS. Moreover, it is necessary to investigate whether these changes can be distinguished through a convolutional neural network (CNN)-based classifier. In this study, we measured the EEG during the voluntary foot-tapping task of participants who received tDCS or sham stimulation and evaluated the classification performance. As a result, significantly higher classification accuracy was shown using the ß band (88.7±9.4%), which is more related to motor function, than in the other bands (71.4±10.6% for δ band, 64.1±13.4% for θ band, and 65.7±10.9% for α band). Consequently, EEG changes during the voluntary foot-tapping task induced by tDCS appeared large in the ß band, implying that it is effective in classifying whether tDCS was given or not, and plays an important role in identifying the effect of tDCS.

Application of subject-specific helmets for the study of human visuomotor behavior using transcranial focused ultrasound: a pilot study.

BACKGROUND AND OBJECTIVE: As a novel non-invasive human brain stimulation method, transcranial focused ultrasound (tFUS) is receiving growing attention due to its superior spatial specificity and depth penetrability. Since the focal point of tFUS needs to be fixated precisely to the target brain region during stimulation, a critical issue is to identify and maintain the accurate position and orientation of the tFUS transducer relative to the subject's head. This study aims to propose the entire framework of tFUS stimulation integrating the methods previously proposed by the authors for tFUS transducer configuration optimization and a subject-specific 3D-printed helmet, and to validate this complete setup in a human behavioral neuromodulation study. METHODS: To find the optimal configuration of the tFUS transducer, a numerical method based on subject-specific tFUS beamlines simulation was used. Then, the subject-specific 3D-printed helmet has been applied to effectively secure the transducer at the estimated optimal configuration. To validate this tFUS framework, a common behavioral neuromodulation paradigm was chosen; the effect of the dorsolateral prefrontal cortex (DLPFC) stimulation on anti-saccade (AS) behavior. While human participants (n=2) were performing AS tasks, tFUS stimulations were randomly applied to the left DLPFC right after the fixation target disappeared. RESULTS: The neuromodulation result strongly suggests that the cortical stimulation using the proposed tFUS setup is effective in significantly reducing the error rates of anti-saccades (about -10 %p for S1 and -16 %p for S2), whereas no significant effect was observed on their latencies. These observed behavioral effects are consistent with the previous results based on conventional brain stimulation or lesion studies. CONCLUSIONS: The proposed subject-specific tFUS framework has been effectively used in human neuromodulation study. The result suggests that the tFUS stimulation targeted to the DLPFC can generate a neuromodulatory effect on AS behavior.

High-Frequency Vibrating Stimuli Using the Low-Cost Coin-Type Motors for SSSEP-Based BCI.

Steady-state somatosensory-evoked potential- (SSSEP-) based brain-computer interfaces (BCIs) have been applied for assisting people with physical disabilities since it does not require gaze fixation or long-time training. Despite the advancement of various noninvasive electroencephalogram- (EEG-) based BCI paradigms, researches on SSSEP with the various frequency range and related classification algorithms are relatively unsettled. In this study, we investigated the feasibility of classifying the SSSEP within high-frequency vibration stimuli induced by a versatile coin-type eccentric rotating mass (ERM) motor. Seven healthy subjects performed selective attention (SA) tasks with vibration stimuli attached to the left and right index fingers. Three EEG feature extraction methods, followed by a support vector machine (SVM) classifier, have been tested: common spatial pattern (CSP), filter-bank CSP (FBCSP), and mutual information-based best individual feature (MIBIF) selection after the FBCSP. Consequently, the FBCSP showed the highest performance at 71.5 ± 2.5% for classifying the left and right-hand SA tasks than the other two methods (i.e., CSP and FBCSP-MIBIF). Based on our findings and approach, the high-frequency vibration stimuli using low-cost coin motors with the FBCSP-based feature selection can be potentially applied to developing practical SSSEP-based BCI systems.

Subject-Transfer Decoding using the Convolutional Neural Network for Motor Imagery-based Brain-Computer Interface.

Various pattern-recognition or machine learning-based methods have recently been developed to improve the accuracy of the motor imagery (MI)-based brain-computer interface (BCI). However, more research is needed to reduce the training time to apply it to the real-world environment. In this study, we propose a subject-transfer decoding method based on a convolutional neural network (CNN) which is robust even with a small number of training trials. The proposed CNN was pre-trained with other subjects' MI data and then fine-tuned to the target subject's training MI data. We evaluated the proposed method using the BCI competition IV data2a, which had the 4-class MIs. Consequently, on the same test dataset, with changing the number of training trials, the proposed method showed better accuracy than the self-training method, which used only the target subject's data for training, as averaged 86.54±7.78% (288 trials), 85.76 ±8.00% (240 trials), 84.65±8.11% (192 trials), and 83.29 ±8.25% (144 trials), respectively, which was 4.94% (288 trials), 6.10% (240 trials), 9.03% (192 trials), and 12.31% (144 trials)-point higher than the self-training method. Consequently, the proposed method was shown to be effective in maintaining classification accuracy even with the reduced training trials.

Multi-Domain Convolutional Neural Networks for Lower-Limb Motor Imagery Using Dry vs. Wet Electrodes.

Motor imagery (MI) brain-computer interfaces (BCIs) have been used for a wide variety of applications due to their intuitive matching between the user's intentions and the performance of tasks. Applying dry electroencephalography (EEG) electrodes to MI BCI applications can resolve many constraints and achieve practicality. In this study, we propose a multi-domain convolutional neural networks (MD-CNN) model that learns subject-specific and electrode-dependent EEG features using a multi-domain structure to improve the classification accuracy of dry electrode MI BCIs. The proposed MD-CNN model is composed of learning layers for three domain representations (time, spatial, and phase). We first evaluated the proposed MD-CNN model using a public dataset to confirm 78.96% classification accuracy for multi-class classification (chance level accuracy: 30%). After that, 10 healthy subjects participated and performed three classes of MI tasks related to lower-limb movement (gait, sitting down, and resting) over two sessions (dry and wet electrodes). Consequently, the proposed MD-CNN model achieved the highest classification accuracy (dry: 58.44%; wet: 58.66%; chance level accuracy: 43.33%) with a three-class classifier and the lowest difference in accuracy between the two electrode types (0.22%, d = 0.0292) compared with the conventional classifiers (FBCSP, EEGNet, ShallowConvNet, and DeepConvNet) that used only a single domain. We expect that the proposed MD-CNN model could be applied for developing robust MI BCI systems with dry electrodes.

Developing a Motor Imagery-Based Real-Time Asynchronous Hybrid BCI Controller for a Lower-Limb Exoskeleton.

This study aimed to develop an intuitive gait-related motor imagery (MI)-based hybrid brain-computer interface (BCI) controller for a lower-limb exoskeleton and investigate the feasibility of the controller under a practical scenario including stand-up, gait-forward, and sit-down. A filter bank common spatial pattern (FBCSP) and mutual information-based best individual feature (MIBIF) selection were used in the study to decode MI electroencephalogram (EEG) signals and extract a feature matrix as an input to the support vector machine (SVM) classifier. A successive eye-blink switch was sequentially combined with the EEG decoder in operating the lower-limb exoskeleton. Ten subjects demonstrated more than 80% accuracy in both offline (training) and online. All subjects successfully completed a gait task by wearing the lower-limb exoskeleton through the developed real-time BCI controller. The BCI controller achieved a time ratio of 1.45 compared with a manual smartwatch controller. The developed system can potentially be benefit people with neurological disorders who may have difficulties operating manual control.

A Multimodal Analysis Combining Behavioral Experiments and Survey-Based Methods to Assess the Cognitive Effect of Video Game Playing: Good or Evil?

This study aims to bridge the gap between the discrepant views of existing studies in different modalities on the cognitive effect of video game play. To this end, we conducted a set of tests with different modalities within each participant: (1) Self-Reports Analyses (SRA) consisting of five popular self-report surveys, and (2) a standard Behavioral Experiment (BE) using pro- and antisaccade paradigms, and analyzed how their results vary between Video Game Player (VGP) and Non-Video Game Player (NVGP) participant groups. Our result showed that (1) VGP scored significantly lower in Behavioral Inhibition System (BIS) than NVGP (p = 0.023), and (2) VGP showed significantly higher antisaccade error rate than NVGP (p = 0.005), suggesting that results of both SRA and BE support the existing view that video game play has a maleficent impact on the cognition by increasing impulsivity. However, the following correlation analysis on the results across individual participants found no significant correlation between SRA and BE, indicating a complex nature of the cognitive effect of video game play.