Search

Objective . Electroencephalography (EEG) is an important kind of bioelectric signal for measuring physiological activities of the brain, and motor imagery (MI) EEG has significant clinical application prospects. Convolutional neural network has become a mainstream algorithm for MI EEG classification, however lack of subject-specific data considerably restricts its decoding accuracy and generalization performance. To address this challenge, a novel transfer learning (TL) framework using auxiliary dataset to improve the MI EEG classification performance of target subject is proposed in this paper. Approach . We developed a multi-source deep domain adaptation ensemble framework (MSDDAEF) for cross-dataset MI EEG decoding. The proposed MSDDAEF comprises three main components: model pre-training, deep domain adaptation, and multi-source ensemble. Moreover, for each component, different designs were examined to verify the robustness of MSDDAEF. Main results . Bidirectional validation experiments were performed on two large public MI EEG datasets (openBMI and GIST). The highest average classification accuracy of MSDDAEF reaches 74.28% when openBMI serves as target dataset and GIST serves as source dataset. While the highest average classification accuracy of MSDDAEF is 69.85% when GIST serves as target dataset and openBMI serves as source dataset. In addition, the classification performance of MSDDAEF surpasses several well-established studies and state-of-the-art algorithms. Significance . The results of this study show that cross-dataset TL is feasible for left/right-hand MI EEG decoding, and further indicate that MSDDAEF is a promising solution for addressing MI EEG cross-dataset variability., (© 2024 Institute of Physics and Engineering in Medicine.)

Vibration stimulation has been shown to have the potential to improve the activation pattern of unilateral motor imagery (MI) and to promote motor recovery. However, in the widely used left and right hand MI brain-computer interface (BCI) paradigm, the vibration stimuli cannot be directly applied to the imaginary side due to the spontaneity of imagery. In this study, we proposed a method of phase-dependent closed-loop vibration stimulation to be applied on both hands, and explored the effects of different vibration stimuli on the left and right hand MI-BCI. Eighteen healthy subjects were recruited and asked to perform, in sequence, MI tasks under three different conditions of vibratory feedback, which were no vibration stimulus (MI), phase-dependent closed-loop vibration stimulus (PDS), and continuous vibration stimulus (CS). Then the performance of the left and right hand MI-BCI and the patterns of brain oscillation were compared and analyzed under these different stimulation conditions. The results showed that vibration stimulation effectively boosted the activation of the sensorimotor cortex and enhanced the functional connectivity among sensorimotor-related brain regions during MI. The closed-loop stimulation evoked stronger event-related desynchronization patterns on the contralateral side of the imagined hand compared to continuous stimulation. There was a more obvious distinction between left hand task and right hand task. In addition, phase-dependent closed-loop vibration stimulation increased classification accuracy by approximately 7% (paired t-test, p=0.004, n=18) compared to MI alone, while continuous vibration stimulation only increased it by 4% (paired t-test, p=0.067, n=18). This result further demonstrated the effectiveness of the phase-dependent closed-loop vibration stimulation method in improving the overall performance of the MI paradigm and is expected to be further applied in areas such as stroke rehabilitation in the future. [ABSTRACT FROM AUTHOR]

The controlling of robotic arms based on brain–computer interface (BCI) can revolutionize the quality of life and living conditions for individuals with physical disabilities. Invasive electroencephalography (EEG)-based BCI has been able to control multiple degrees of freedom (DOFs) robotic arms in three dimensions. However, it is still hard to control a multi-DOF robotic arm to reach and grasp the desired target accurately in complex three-dimensional (3D) space by a noninvasive system mainly due to the limitation of EEG decoding performance. In this study, we propose a noninvasive EEG-based BCI for a robotic arm control system that enables users to complete multitarget reach and grasp tasks and avoid obstacles by hybrid control. The results obtained from seven subjects demonstrated that motor imagery (MI) training could modulate brain rhythms, and six of them completed the online tasks using the hybrid-control-based robotic arm system. The proposed system shows effective performance due to the combination of MI-based EEG, computer vision, gaze detection, and partially autonomous guidance, which drastically improve the accuracy of online tasks and reduce the brain burden caused by long-term mental activities. [ABSTRACT FROM AUTHOR]