Methods for Improving Brain-Computer Interface: Using A Brain-Directed Adjuvant and A Second-Generation Artificial Intelligence System to Enhance Information Streaming and Effectiveness of Stimuli

Background: The brain-computer interface (BCI) is gaining much attention to treat neurological disorders and improve brain-dependent functions. Significant achievements over the last decade have focused on engineering and computation technology to enhance the recording of signals and the generation of output stimuli. Nevertheless, many challenges remain for the translation of BCIs to clinical applications. Methods: We review the relevant data on the four significant gaps in enhancing BCI's clinical implementation and effectiveness. Results: The paper describes three methods to bridge the current gaps in the clinical application of BCI. The first is using a brain-directed adjuvant with a high safety profile, which can improve the accuracy of brain signaling, summing of information, and production of stimuli. The second is implementing a second-generation artificial intelligence system that is outcome-oriented for improving data streaming, recording individualized brain-variability patterns into the algorithm, and improving closed-loop learning at the level of the brain and with the target organ. The system overcomes the compensatory mechanisms that underlie the loss of stimuli' effectiveness for ensuring sustainable effects. Finally, we use inherent brain parameters relevant to consciousness and brain function to bridge some of the described gaps. Conclusions: Combined with the currently developed techniques for enhancing effectiveness and ensuring a sustainable response, these methods can potentially improve the clinical outcome of BCI techniques.

Brain-computer interface coding method based on high-frequency dual-frequency SSVEP / 国际生物医学工程杂志

Objective:To improve the users’ comfort of steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) through high-frequency stimulation and overcome the problem of accuracy decline caused by high frequency by combining dual-frequency encoding.Methods:Two dual-frequency high-frequency 60-instruction paradigms based on left and right visual fields and checkerboard stimuli were designed based on the 25.5 - 39.6 Hz frequency. Thirteen subjects participated in the experiment, and spectrum and spatial characteristics analyses were performed on SSVEP signals. The filter bank parameters were optimized based on the spectrum characteristics. Extended canonical correlation analysis (eCCA), ensemble task-related component analysis (eTRCA), and task-discriminant component analysis (TDCA) were used for SSVEP recognition.Results:Stable SSVEP was successfully induced in both the left and right visual fields and the checkerboard grid paradigm. The left and right visual fields had high signal-to-noise ratios for the fundamental frequency and its harmonics and weak signal-to-noise ratios for intermodulation components, whereas the intermodulation components of the 2 stimulus frequencies of the checkerboard grid, f1 + f2, had significantly higher signal-to-noise ratios than the second harmonic components above 30 Hz, and there was also a f2 ? f1 component and a 2 f1 ? f2 component. Combined with brain topography, it can be seen that the f1 and f2 response components of the left and right visual fields are located on opposite sides of the visual field, while the checkerboard grids are both concentrated in the center of the occipital region. Regarding the lateralization of brain topography amplitude and signal-to-noise ratio, the mean values of the PO3 and PO4 signal-to-noise ratios at the stimulation frequency of the left and right visual fields are consistent with the contralateral response characteristics. The 5 fb ? 1 method is the optimal filter set setting method, and the recognition correctness rate of TDCA for the left and right visual fields is the highest. However, the comparison of the recognition correctness rate of tessellated lattice eTRCA and TDCA is not statistically significant ( P > 0.05). The information transmission rates of the three algorithms all increase and then decrease with the increase in data length. Conclusions:The designed dual-frequency, high-frequency SSVEP-BCI paradigm is able to better balance performance and comfort and provides a basis for practical large instruction set BCI design methods.

Brain-computer interface technology for stroke in the past decade: a visualized analysis / 中国康复理论与实践

ObjectiveTo conduct a visualized analysis of the research related to the use of brain-computer interface technology for stroke rehabilitation in the past ten years, and identify and predict the hot spots and hot trends in order to promote the further development of this field. MethodsThe Web of Science Core Collection database was searched for literature related to brain-computer interface technology for stroke rehabilitation from January, 2011 to October, 2022. CiteSpace 5.8.R3 was used to analyze the number of publications, countries, institutions, authors, keywords, co-citations, and grant support. Results and ConclusionA total of 592 papers were included, and the annual number of publications in this field of research showed a rapid growth trend, and the research enthusiasm continued to increase. The United States was in the leading position in this field, with the highest number of cooperative publications and the highest intermediary centrality; China had certain advantages in this field, but still needed to strengthen the exchange and cooperation with other countries/regions. Foreign institutions and authors had formed a network of close cooperative relationships, and formed a high-impact team represented by Niels Birbaumer, Cuntai Guan, Kai Keng Ang, etc.; there were poor cooperative relationships among domestic authors and institutions, and there were geographical restrictions and lack of high-impact academic groups. The keywords "motor imagery" and "recovery" formed ten major clusters and 15 prominent words with high variation rates, showing a trend of diversification in research directions. The study of the efficacy of upper limb motor rehabilitation and central mechanisms has been the hot topics in this field and will continue for some time in the future; the use of lower limb brain-computer interface systems for improving foot drop, gait and balance in stroke patients and the application of multimodal brain-computer interfaces will probably become a hot topic in the future. Finally, the use of brain-computer interface-guided neurofeedback training for cognitive and language rehabilitation in stroke also needs attention.

Effect of brain-computer interface training based on motor imagery on hand function for subacute stroke patients / 中国康复理论与实践

ObjectiveTo observe the effect of brain-computer interface (BCI) training based on motor imagery on hand function in hemiplegic patients with subacute stroke. MethodsFrom June, 2020 to December, 2021, 40 patients with hemiplegia in subacute stroke from Department of Rehabilitation Medicine, Fifth Affiliated Hospital of Zhengzhou University were divided into control group (n = 20) and experimental group (n = 20) using random number table. Both groups accepted medication and routine comprehensive rehabilitation, while the control group accepted hand rehabilitation robot training, and the experimental group accepted the robot training using motor imagery-based BCI, for four weeks. They were assessed with Fugl-Meyer Assessment-Upper Extremities (FMA-UE), modified Barthel Index, modified Ashworth scale, and measured integrated electromyogram of the superficial finger flexors, finger extensors and short thumb extensors of the affected forearm during maximum isometric voluntary contraction with surface electromyography. ResultsTwo patients in the control group and one in the experimental group dropped off. All the indexes improved in both groups after treatment (t > 2.322, Z > 2.631, P < 0.05), and they were better in the experimental group than in the control group (t > 2.227, Z > 2.078, P < 0.05), except the FMA-UE score of wrist. ConclusionMotor imagery-based BCI training is more effective on hand function and activities of daily living in hemiplegic patients with subacute stroke.

Roadmap of Medical Device for Implanted Brain-computer Interface / 中国医疗器械杂志

Implanted brain-computer interface (iBCI) is a system that establishes a direct communication channel between human brain and computer or an external devices by implanted neural electrode. Because of the good functional extensibility, iBCI devices as a platform technology have the potential to bring benefit to people with nervous system disease and progress rapidly from fundamental neuroscience discoveries to translational applications and market access. In this report, the industrialization process of implanted neural regulation medical devices is reviewed, and the translational pathway of iBCI in clinical application is proposed. However, the Food and Drug Administration (FDA) regulations and guidances for iBCI were expounded as a breakthrough medical device. Furthermore, several iBCI products in the process of applying for medical device registration certificate were briefly introduced and compared recently. Due to the complexity of iBCI in clinical application, the translational applications and industrialization of iBCI as a medical device need the closely cooperation between regulatory departments, companies, universities, institutes and hospitals in the future.

Multi-scale feature extraction and classification of motor imagery electroencephalography based on time series data enhancement / 生物医学工程学杂志

The brain-computer interface (BCI) based on motor imagery electroencephalography (MI-EEG) enables direct information interaction between the human brain and external devices. In this paper, a multi-scale EEG feature extraction convolutional neural network model based on time series data enhancement is proposed for decoding MI-EEG signals. First, an EEG signals augmentation method was proposed that could increase the information content of training samples without changing the length of the time series, while retaining its original features completely. Then, multiple holistic and detailed features of the EEG data were adaptively extracted by multi-scale convolution module, and the features were fused and filtered by parallel residual module and channel attention. Finally, classification results were output by a fully connected network. The application experimental results on the BCI Competition IV 2a and 2b datasets showed that the proposed model achieved an average classification accuracy of 91.87% and 87.85% for the motor imagery task, respectively, which had high accuracy and strong robustness compared with existing baseline models. The proposed model does not require complex signals pre-processing operations and has the advantage of multi-scale feature extraction, which has high practical application value.

Research on phase modulation to enhance the feature of high-frequency steady-state asymmetric visual evoked potentials / 生物医学工程学杂志

High-frequency steady-state asymmetric visual evoked potential (SSaVEP) provides a new paradigm for designing comfortable and practical brain-computer interface (BCI) systems. However, due to the weak amplitude and strong noise of high-frequency signals, it is of great significance to study how to enhance their signal features. In this study, a 30 Hz high-frequency visual stimulus was used, and the peripheral visual field was equally divided into eight annular sectors. Eight kinds of annular sector pairs were selected based on the mapping relationship of visual space onto the primary visual cortex (V1), and three phases (in-phase[0º, 0º], anti-phase [0º, 180º], and anti-phase [180º, 0º]) were designed for each annular sector pair to explore response intensity and signal-to-noise ratio under phase modulation. A total of 8 healthy subjects were recruited in the experiment. The results showed that three annular sector pairs exhibited significant differences in SSaVEP features under phase modulation at 30 Hz high-frequency stimulation. And the spatial feature analysis showed that the two types of features of the annular sector pair in the lower visual field were significantly higher than those in the upper visual field. This study further used the filter bank and ensemble task-related component analysis to calculate the classification accuracy of annular sector pairs under three-phase modulations, and the average accuracy was up to 91.5%, which proved that the phase-modulated SSaVEP features could be used to encode high- frequency SSaVEP. In summary, the results of this study provide new ideas for enhancing the features of high-frequency SSaVEP signals and expanding the instruction set of the traditional steady state visual evoked potential paradigm.

Ethics considerations on brain-computer interface technology / 生物医学工程学杂志

The development and potential application of brain-computer interface (BCI) technology is closely related to the human brain, so that the ethical regulation of BCI has become an important issue attracting the consideration of society. Existing literatures have discussed the ethical norms of BCI technology from the perspectives of non-BCI developers and scientific ethics, while few discussions have been launched from the perspective of BCI developers. Therefore, there is a great need to study and discuss the ethical norms of BCI technology from the perspective of BCI developers. In this paper, we present the user-centered and non-harmful BCI technology ethics, and then discuss and look forward on them. This paper argues that human beings can cope with the ethical issues arising from BCI technology, and as BCI technology develops, its ethical norms will be improved continuously. It is expected that this paper can provide thoughts and references for the formulation of ethical norms related to BCI technology.

Advances in brain-computer interface based on high-frequency steady-state visual evoked potential / 生物医学工程学杂志

Steady-state visual evoked potential (SSVEP) has been widely used in the research of brain-computer interface (BCI) system in recent years. The advantages of SSVEP-BCI system include high classification accuracy, fast information transform rate and strong anti-interference ability. Most of the traditional researches induce SSVEP responses in low and middle frequency bands as control signals. However, SSVEP in this frequency band may cause visual fatigue and even induce epilepsy in subjects. In contrast, high-frequency SSVEP-BCI provides a more comfortable and natural interaction despite its lower amplitude and weaker response. Therefore, it has been widely concerned by researchers in recent years. This paper summarized and analyzed the related research of high-frequency SSVEP-BCI in the past ten years from the aspects of paradigm and algorithm. Finally, the application prospect and development direction of high-frequency SSVEP were discussed and prospected.

Effect of visual motion-induced brain computer interface technology on upper limb motor and cognitive function of patients with stroke / 中国康复理论与实践

ObjectiveTo investigate the effects of visual motion-induced brain-computer interface (BCI) technology on upper limb motor function and cognitive function of patients with stroke. MethodsFrom July, 2021 to March, 2022, 50 stroke patients with upper limb hand dysfunction in Shaanxi Provincial Rehabilitation Hospital were randomly divided into control group (n = 25) and experimental group (n = 25). Both groups received conventional rehabilitation therapy, in addition, the control group received passive rehabilitation training, and the experimental group received visual motion-induced BCI rehabilitation training, for two weeks. They were assessed with Fugl-Meyer Assessment-Upper Extremities (FMA-UE), modified Barthel Index (MBI) and Montreal Cognitive Assessment (MoCA) before and after treatment. Brain participation was evaluated during the whole training process of the experimental group. ResultsBefore treatment, there was no difference in the scores of FMA-UE, MBI and MoCA between two groups (P > 0.05). Two weeks after treatment, the scores of FMA-UE, MBI and MoCA improved in both groups (t > 2.481, P < 0.001), and were better in the exprimental group than in the control group (t > 2.453, P < 0.05); the mean brain participation of the experimental group increased 21% after treatment. ConclusionVisual motion-induced BCI rehabilitation training could promote the recovery of motor function of upper limb, and cognitive function of patients with stroke.

Design and preliminary application of outdoor flying pigeon-robot / 生物医学工程学杂志

Control at beyond-visual ranges is of great significance to animal-robots with wide range motion capability. For pigeon-robots, such control can be done by the way of onboard preprogram, but not constitute a closed-loop yet. This study designed a new control system for pigeon-robots, which integrated the function of trajectory monitoring to that of brain stimulation. It achieved the closed-loop control in turning or circling by estimating pigeons' flight state instantaneously and the corresponding logical regulation. The stimulation targets located at the formation reticularis medialis mesencephali (FRM) in the left and right brain, for the purposes of left- and right-turn control, respectively. The stimulus was characterized by the waveform mimicking the nerve cell membrane potential, and was activated intermittently. The wearable control unit weighted 11.8 g totally. The results showed a 90% success rate by the closed-loop control in pigeon-robots. It was convenient to obtain the wing shape during flight maneuver, by equipping a pigeon-robot with a vivo camera. It was also feasible to regulate the evolution of pigeon flocks by the pigeon-robots at different hierarchical level. All of these lay the groundwork for the application of pigeon-robots in scientific researches.

Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation / 生物医学工程学杂志

Aiming at the problem of low recognition accuracy of motor imagery electroencephalogram signal due to individual differences of subjects, an individual adaptive feature representation method of motor imagery electroencephalogram signal is proposed in this paper. Firstly, based on the individual differences and signal characteristics in different frequency bands, an adaptive channel selection method based on expansive relevant features with label F (ReliefF) was proposed. By extracting five time-frequency domain observation features of each frequency band signal, ReliefF algorithm was employed to evaluate the effectiveness of the frequency band signal in each channel, and then the corresponding signal channel was selected for each frequency band. Secondly, a feature representation method of common space pattern (CSP) based on fast correlation-based filter (FCBF) was proposed (CSP-FCBF). The features of electroencephalogram signal were extracted by CSP, and the best feature sets were obtained by using FCBF to optimize the features, so as to realize the effective state representation of motor imagery electroencephalogram signal. Finally, support vector machine (SVM) was adopted as a classifier to realize identification. Experimental results show that the proposed method in this research can effectively represent the states of motor imagery electroencephalogram signal, with an average identification accuracy of (83.0±5.5)% for four types of states, which is 6.6% higher than the traditional CSP feature representation method. The research results obtained in the feature representation of motor imagery electroencephalogram signal lay the foundation for the realization of adaptive electroencephalogram signal decoding and its application.

Automatic removal algorithm of electrooculographic artifacts in non-invasive brain-computer interface based on independent component analysis / 生物医学工程学杂志

The non-invasive brain-computer interface (BCI) has gradually become a hot spot of current research, and it has been applied in many fields such as mental disorder detection and physiological monitoring. However, the electroencephalography (EEG) signals required by the non-invasive BCI can be easily contaminated by electrooculographic (EOG) artifacts, which seriously affects the analysis of EEG signals. Therefore, this paper proposed an improved independent component analysis method combined with a frequency filter, which automatically recognizes artifact components based on the correlation coefficient and kurtosis dual threshold. In this method, the frequency difference between EOG and EEG was used to remove the EOG information in the artifact component through frequency filter, so as to retain more EEG information. The experimental results on the public datasets and our laboratory data showed that the method in this paper could effectively improve the effect of EOG artifact removal and improve the loss of EEG information, which is helpful for the promotion of non-invasive BCI.

Multi-task motor imagery electroencephalogram classification based on adaptive time-frequency common spatial pattern combined with convolutional neural network / 生物医学工程学杂志

The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.

Motor imagery electroencephalogram classification based on sparse spatiotemporal decomposition and channel attention / 生物医学工程学杂志

Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.

A review of researches on decoding algorithms of steady-state visual evoked potentials / 生物医学工程学杂志

Brain-computer interface (BCI) systems based on steady-state visual evoked potential (SSVEP) have become one of the major paradigms in BCI research due to their high signal-to-noise ratio and short training time required by users. Fast and accurate decoding of SSVEP features is a crucial step in SSVEP-BCI research. However, the current researches lack a systematic overview of SSVEP decoding algorithms and analyses of the connections and differences between them, so it is difficult for researchers to choose the optimum algorithm under different situations. To address this problem, this paper focuses on the progress of SSVEP decoding algorithms in recent years and divides them into two categories-trained and non-trained-based on whether training data are needed. This paper also explains the fundamental theories and application scopes of decoding algorithms such as canonical correlation analysis (CCA), task-related component analysis (TRCA) and the extended algorithms, concludes the commonly used strategies for processing decoding algorithms, and discusses the challenges and opportunities in this field in the end.

Applications, industrial transformation and commercial value of brain-computer interface technology / 生物医学工程学杂志

Brain-computer interface (BCI) is a revolutionary human-computer interaction technology, which includes both BCI that can output instructions directly from the brain to external devices or machines without relying on the peripheral nerve and muscle system, and BCI that bypasses the peripheral nerve and muscle system and inputs electrical, magnetic, acoustic and optical stimuli or neural feedback directly to the brain from external devices or machines. With the development of BCI technology, it has potential application not only in medical field, but also in non-medical fields, such as education, military, finance, entertainment, smart home and so on. At present, there is little literature on the relevant application of BCI technology, the current situation of BCI industrialization at home and abroad and its commercial value. Therefore, this paper expounds and discusses the above contents, which are expected to provide valuable information for the public and organizations, BCI researchers, BCI industry translators and salespeople, and improve the cognitive level of BCI technology, further promote the application and industrial transformation of BCI technology and enhance the commercial value of BCI, so as to serve mankind better.

Key technologies for intelligent brain-computer interaction based on magnetoencephalography / 生物医学工程学杂志

Brain-computer interaction (BCI) is a transformative human-computer interaction, which aims to bypass the peripheral nerve and muscle system and directly convert the perception, imagery or thinking activities of cranial nerves into actions for further improving the quality of human life. Magnetoencephalogram (MEG) measures the magnetic field generated by the electrical activity of neurons. It has the unique advantages of non-contact measurement, high temporal and spatial resolution, and convenient preparation. It is a new BCI driving signal. MEG-BCI research has important brain science significance and potential application value. So far, few documents have elaborated the key technical issues involved in MEG-BCI. Therefore, this paper focuses on the key technologies of MEG-BCI, and details the signal acquisition technology involved in the practical MEG-BCI system, the design of the MEG-BCI experimental paradigm, the MEG signal analysis and decoding key technology, MEG-BCI neurofeedback technology and its intelligent method. Finally, this paper also discusses the existing problems and future development trends of MEG-BCI. It is hoped that this paper will provide more useful ideas for MEG-BCI innovation research.

A spatial-temporal hybrid feature extraction method for rapid serial visual presentation of electroencephalogram signals / 生物医学工程学杂志

Rapid serial visual presentation-brain computer interface (RSVP-BCI) is the most popular technology in the early discover task based on human brain. This algorithm can obtain the rapid perception of the environment by human brain. Decoding brain state based on single-trial of multichannel electroencephalogram (EEG) recording remains a challenge due to the low signal-to-noise ratio (SNR) and nonstationary. To solve the problem of low classification accuracy of single-trial in RSVP-BCI, this paper presents a new feature extraction algorithm which uses principal component analysis (PCA) and common spatial pattern (CSP) algorithm separately in spatial domain and time domain, creating a spatial-temporal hybrid CSP-PCA (STHCP) algorithm. By maximizing the discrimination distance between target and non-target, the feature dimensionality was reduced effectively. The area under the curve (AUC) of STHCP algorithm is higher than that of the three benchmark algorithms (SWFP, CSP and PCA) by 17.9%, 22.2% and 29.2%, respectively. STHCP algorithm provides a new method for target detection.

A comparative study of microwire electrode array with built-in and external reference electrodes / 中国应用生理学杂志

Objective: To compare the difference between the built-in and external reference electrode of microwire electrode array in the process of recording rat brain neuron firings, optimizing the production and embedding of the microwire electrode array, and providing a more affordable and excellent media tool for multi-channel electrophysiological real-time recording system. Methods: A 16 channel microwire electrode array was made by using nickel chromium alloy wires, circuit board, electrode pin and ground wires (silver wires). The reference electrode of the microwire electrode array was built-in (the reference electrode and electrode array were arranged in parallel) or external (the reference electrode and ground wire were welded at both ends of one side of the electrode), and the difference between the two electrodes was observed and compared in recording neuronal discharges in ACC brain area of rats. Experimental rats were divided into built-in group and external group, n=8-9. The test indicators included signal-to-noise ratio (n=8), discharge amplitude (n=380) and discharge frequency (n=54). Results: The microwire electrode array with both built-in and external reference electrodes successfully recorded the electrical signals of neurons in the ACC brain region of rats. Compared with the external group, the electrical signals of neurons in built-in group had the advantages of a higher signal-to-noise ratio (P＜0.05), a smaller amplitude of background signals and less noise interference, and a larger discharge amplitude(P＜0.05); there was no significant difference in spike discharge frequency recorded by these two types of electrodes (P＞0.05). Conclusion: When recording the electrical activity of neurons in the ACC brain region of rats, the microwire electrode array with built-in reference electrode recorded electrical signals with higher signal-to-noise ratio and larger discharge amplitude, providing a more reliable tool for multi-channel electrophysiology technology.