1 February 2022 in Journal of Neural Engineering
Objective. Brain–computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Approach. Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting. Main results. The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy. Significance. Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.
1 June 2024 in Journal of Neural Engineering
Objective. Multi-channel electroencephalogram (EEG) technology in brain–computer interface (BCI) research offers the advantage of enhanced spatial resolution and system performance. However, this also implies that more time is needed in the data processing stage, which is not conducive to the rapid response of BCI. Hence, it is a necessary and challenging task to reduce the number of EEG channels while maintaining decoding effectiveness. Approach. In this paper, we propose a local optimization method based on the Fisher score for within-subject EEG channel selection. Initially, we extract the common spatial pattern characteristics of EEG signals in different bands, calculate Fisher scores for each channel based on these characteristics, and rank them accordingly. Subsequently, we employ a local optimization method to finalize the channel selection. Main results. On the BCI Competition IV Dataset IIa, our method selects an average of 11 channels across four bands, achieving an average accuracy of 79.37%. This represents a 6.52% improvement compared to using the full set of 22 channels. On our self-collected dataset, our method similarly achieves a significant improvement of 24.20% with less than half of the channels, resulting in an average accuracy of 76.95%. Significance. This research explores the importance of channel combinations in channel selection tasks and reveals that appropriately combining channels can further enhance the quality of channel selection. The results indicate that the model selected a small number of channels with higher accuracy in two-class motor imagery EEG classification tasks. Additionally, it improves the portability of BCI systems through channel selection and combinations, offering the potential for the development of portable BCI systems.
7 June 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Wrist exoskeletons are increasingly being used in the rehabilitation of stroke and hand dysfunction because of its ability to assist patients in high intensity, repetitive, targeted and interactive rehabilitation training. However, the existing wrist exoskeletons cannot effectively replace the work of therapist and improve hand function, mainly because the existing exoskeletons cannot assist patients to perform natural hand movement covering the entire physiological motor space (PMS). Here, we present a bioelectronic controlled hybrid serial-parallel wrist exoskeleton HrWr-ExoSkeleton (HrWE) which is based on the PMS design guidance, the gear set can carry out forearm pronation/supination (P/S) and the 2-DoF parallel configuration fixed on the gear set can carry out wrist flexion/extension (F/E) and radial/ulnar deviation (R/U). This special configuration not only provides enough range of motion (RoM) for rehabilitation training (85F/85E, 55R/55U, and 90P/90S), but also makes it easier to provide the interface for finger exoskeletons and be adapted to upper limb exoskeletons. In addition, to further improve the rehabilitation effect, we propose a HrWE-assisted active rehabilitation training platform based on surface electromyography signals.
1 December 2022 in Journal of Neural Engineering
Objective. The brain-computer interface (BCI) system based on sensorimotor rhythm can convert the human spirit into instructions for machine control, and it is a new human-computer interaction system with broad applications. However, the spatial resolution of scalp electroencephalogram (EEG) is limited due to the presence of volume conduction effects. Therefore, it is very meaningful to explore intracranial activities in a noninvasive way and improve the spatial resolution of EEG. Meanwhile, low-delay decoding is an essential factor for the development of a real-time BCI system. Approach. In this paper, EEG conduction is modeled by using public head anatomical templates, and cortical EEG is obtained using dynamic parameter statistical mapping. To solve the problem of a large amount of computation caused by the increase in the number of channels, the filter bank common spatial pattern method is used to obtain a spatial filter kernel, which reduces the computational cost of feature extraction to a linear level. And the feature classification and selection of important features are completed using a neural network containing band-spatial-time domain self-attention mechanisms. Main results. The results show that the method proposed in this paper achieves high accuracy for the four types of motor imagery EEG classification tasks, with fairly low latency and high physiological interpretability. Significance. The proposed decoding framework facilitates the realization of low-latency human-computer interaction systems.