Tetramethylpyrazine-loaded electroconductive hydrogels promote tissue repair after spinal cord injury by protecting the blood-spinal cord barrier and neurons.

Spinal cord injury (SCI) usually induces profound microvascular dysfunction. It disrupts the integrity of the blood-spinal cord barrier (BSCB), which could trigger a cascade of secondary pathological events that manifest as neuronal apoptosis and axonal demyelination. These events can further lead to irreversible neurological impairments. Thus, reducing the permeability of the BSCB and maintaining its substructural integrity are essential to promote neuronal survival following SCI. Tetramethylpyrazine (TMP) has emerged as a potential protective agent for treating the BSCB after SCI. However, its therapeutic potential is hindered by challenges in the administration route and suboptimal bioavailability, leading to attenuated clinical outcomes. To address this challenge, traditional Chinese medicine, TMP, was used in this study to construct a drug-loaded electroconductive hydrogel for synergistic treatment of SCI. A conductive hydrogel combined with TMP demonstrates good electrical and mechanical properties as well as superior biocompatibility. Furthermore, it also facilitates sustained local release of TMP at the implantation site. Furthermore, the TMP-loaded electroconductive hydrogel could suppress oxidative stress responses, thereby diminishing endothelial cell apoptosis and the breakdown of tight junction proteins. This concerted action repairs BSCB integrity. Concurrently, myelin-associated axons and neurons are protected against death, which meaningfully restore neurological functions post spinal cord injury. Hence, these findings indicate that combining the electroconductive hydrogel with TMP presents a promising avenue for potentiating drug efficacy and synergistic repair following SCI.

Explainable Deep-Learning Prediction for Brain-Computer Interfaces Supported Lower Extremity Motor Gains Based on Multistate Fusion.

Predicting the potential for recovery of motor function in stroke patients who undergo specific rehabilitation treatments is an important and major challenge. Recently, electroencephalography (EEG) has shown potential in helping to determine the relationship between cortical neural activity and motor recovery. EEG recorded in different states could more accurately predict motor recovery than single-state recordings. Here, we design a multi-state (combining eyes closed, EC, and eyes open, EO) fusion neural network for predicting the motor recovery of patients with stroke after EEG-brain-computer-interface (BCI) rehabilitation training and use an explainable deep learning method to identify the most important features of EEG power spectral density and functional connectivity contributing to prediction. The prediction accuracy of the multi-states fusion network was 82%, significantly improved compared with a single-state model. The neural network explanation result demonstrated the important region and frequency oscillation bands. Specifically, in those two states, power spectral density and functional connectivity were shown as the regions and bands related to motor recovery in frontal, central, and occipital. Moreover, the motor recovery relation in bands, the power spectrum density shows the bands at delta and alpha bands. The functional connectivity shows the delta, theta, and alpha bands in the EC state; delta, theta, and beta mid at the EO state are related to motor recovery. Multi-state fusion neural networks, which combine multiple states of EEG signals into a single network, can increase the accuracy of predicting motor recovery after BCI training, and reveal the underlying mechanisms of motor recovery in brain activity.

Influence of Amputation on Kinetic Chain Musculature Activity During Basic and Modified Core Exercises.

PURPOSE: Core strength is vital for athletic performance, and many more exercises that involve the kinetic chain have been designed for able-bodied athletes. Disabilities that impair the kinetic chain can reduce the effectiveness of strength training. However, the impact of amputation on core strength training of people with disabilities and its underlying mechanism remains unclear. This study aimed to evaluate the muscle activation patterns and levels in athletes with amputation during 4 basic and modified weight-bearing core strength-training exercises. METHODS: Fifteen elite athletes with unilateral amputation (170.6 [7.3] cm; 63.9 [11.9] kg; 25.9 [5.3] y) volunteered for this study. Surface electromyography was used to measure the muscle activity mainly in the lumbopelvic-hip complex-stabilizing muscles during 4 kinetic chain trunk exercises with and without modifications. RESULTS: The significance level was set at α = .05. The results showed a significant difference in muscle activation between different body sides (P < .05). Specifically, amputation on the support position resulted in a diagonal pattern of muscle activation, and amputation on the free distal segments resulted in a unilateral dominant pattern with higher activation in muscles on the nonamputated side (P < .05). Modifications led to significant decreases in muscle activation asymmetry index (P < .05). CONCLUSIONS: Amputation caused muscle activation asymmetry and 2 activation patterns. Modifications by enhancing proximal stability and adjusting distal loading effectively reduced the asymmetry of muscle activation. Coaches and clinicians can use these results to tailor exercises for athletes with disabilities in training and rehabilitation.

Adverse effects of unilateral transfemoral amputation on para-alpine sit skiers and mitigation methods.

OBJECTIVES: This study aimed to evaluate the adverse effects of unilateral transfemoral amputation on neuromuscular and kinematic parameters in alpine sit skiers, and to determine if additional restraints on the human-bucket interface could help mitigate the effects. DESIGN: Cross-sectional, repeated measures study. METHODS: Simulated skiing tests were conducted indoors involving 10 skiers with unilateral transfemoral amputation and 10 able-bodied participants. A Paralympic silver medalist performed slalom skiing tests on snow. These tests were conducted with and without additional strapping on the residual limb. Surface electromyography of trunk muscles and athletic performance was measured, and the asymmetry index was calculated. RESULTS: Athletes were significantly dependent on muscle activation on the dominant side (asymmetry index = 7.8 %-28.3 %, p < 0.05). Worse athletic performance to the dominant side was found based on inclination angles of the indoor board (asymmetry index = -9.8 %, p = 0.014) and outdoor sit ski (-11.1 %, p = 0.006), and distance to the gate poles during skiing turns (18.6 %, p < 0.001). After using additional restraints, the above asymmetry index declined significantly (asymmetry index < 4.5 %, p < 0.05). Furthermore, athletic performance was significantly improved on both body sides by 11.1 %-30.7 % (p < 0.05). CONCLUSIONS: Unilateral transfemoral amputation caused the dependence on the trunk muscles of the dominant side and the corresponding unilateral poor performance in athletes. Adjusting restraints in the human-equipment interface by additional strapping could mitigate the asymmetry issues and improve athletic performance.

Motor-Respiratory Coupling Improves Endurance Performance during Rhythmic Isometric Handgrip Exercise.

PURPOSE: This study aimed to evaluate whether motor-respiratory coupling exists in rhythmic isometric handgrip exercises and its effect on endurance performance. In addition, the mechanism underlying observed effects was to be investigated if higher motor-respiratory coupling rate could enhance endurance performance. METHODS: Eleven subjects completed three rhythmic isometric handgrip trials to task failure in a randomized manner. After one pretraining session to determine personal grip frequency, one trial was performed without respiration requirement (CON), and two trials were performed with inspiration-motor coupling (IMC) or expiration-motor coupling. Changes in maximal voluntary contraction (MVC) and EMG were used to measure neuromuscular fatigue. Force data during test were used to assess exercise intensity. Another 10 subjects completed electrical stimulation-induced finger flexion and extension during normal inspiration, normal expiration, fast inspiration, fast expiration, and breath holding. Force changes of different breathing conditions were compared. RESULTS: Normalized exercise time to exhaustion was significantly longer in IMC (1.27 ± 0.23) compared with expiration-motor coupling (0.82 ± 0.18) and CON (0.91 ± 0.18, P < 0.001). ΔMVC, grip frequency, force, and EMG indices were not different among conditions (all P > 0.05). Electrical stimulation-induced finger extensor force was significant higher during fast inspiration (1.11 ± 0.09) than normal respiration (1.00 ± 0.05) and fast expiration (0.94 ± 0.08, P < 0.05). CONCLUSIONS: IMC is an effective way to improve endurance performance of rhythmic handgrip exercise. This is likely due to a reduction in the energy consumption of motion control, as evidenced by similar peripheral fatigue in different conditions and modulation of corticospinal excitability by respiration.

Multiscale Canonical Coherence for Functional Corticomuscular Coupling Analysis.

Functional corticomuscular coupling (FCMC) probes multi-level information communication in the sensorimotor system. The canonical Coherence (caCOH) method has been leveraged to measure the FCMC between two multivariate signals within the single scale. In this paper, we propose the concept of multiscale canonical Coherence (MS-caCOH) to disentangle complex multi-layer information and extract coupling features in multivariate spaces from multiple scales. Then, we verified the reliability and effectiveness of MS-caCOH on two types of data sets, i.e., a synthetic multivariate data set and a real-world multivariate data set. Our simulation results showed that compared with caCOH, MS-caCOH enhanced coupling detection and achieved lower pattern recovery errors at multiple frequency scales. Further analysis on experimental data demonstrated that the proposed MS-caCOH method could also capture detailed multiscale spatial-frequency characteristics. This study leverages the multiscale analysis framework and multivariate method to give a new insight into corticomuscular coupling analysis.

Slackline training for Paralympic alpine sit skiers: Development of human-device multi-joint coordination.

PURPOSE: Para-alpine sit skiers face unique challenges in balance control due to their disabilities and the use of sit skis. This study assessed their multi-joint coordination before and after slackline training. METHODS: Nine alpine sit skiers (6 M/3 F; 27 ± 8 years; height: 168.3 ± 6.0 cm; body mass: 55.4 ± 6.9 kg) with different disabilities (LW10-LW12) volunteered for the experiment. All subjects performed slackline training for 5 weeks (20 sessions). Joint kinematics were captured by vision-based markerless motion analysis. Root mean square (RMS) amplitude, mean velocity and mean power frequency (MPF) were evaluated. RESULTS: After training, performance improved significantly with an increase in balance time (1041%, p = 0.002), and a decrease in joint angular velocities and RMS amplitude of the sit ski foot (p < 0.05). Joint synergies were developed through in- or anti-phase movements between joint pairs, particularly involving the hip joints (continuous relative phase angles ~0° or 180°, p < 0.001). Multi-joint coordination shifted from large-RMS amplitude of elbows to low-MPF large-RMS amplitude of the hip and shoulders (p < 0.05), with a significant increase of hip weighting (77.61%, p = 0.031) in the principal component analysis. The coordination was maintained with the change of slackline tension (p < 0.05). Athletes with severe trunk disabilities (LW10) had shorter balance time and poorer coordination than athletes with full trunk functions (LW12). CONCLUSIONS: Our findings showed the development of joint coordination involving better control of the hip and sit skis during the challenging slackline training task.

Cluster analysis of multiple impairment measures in evidence-based classification for para-alpine sit skiers.

The International Paralympic Committee has been promoting the development of evidence-based classification to reduce the subjectivity in current decision-making systems. The current study aimed to evaluate the validity of the impairment and performance tests for para-alpine sit skiing classification, and whether cluster analysis of the measures would produce a valid classification structure. Thirty-eight para-alpine sit skiers with different disabilities completed seven tests. During these tests, isometric trunk strength, trunk muscle excitation, trunk range of movement (ROM), and simulated skiing performance (board tilt angle) were assessed. Correlations between the measures and the board tilt angle were calculated. To group athletes, K-means cluster analysis was performed according to how much the impairment measures affected the board tilting. There were significant correlations between all measures and the maximal board tilt angle (r = 0.35-0.81, p < 0.05). The cluster analysis revealed that the introduction of ROM and muscle excitation was an effective supplement to strength measures in improving the classification accuracy (53%-79%). It produced four clusters with strong structures (mean silhouette coefficient = 0.81) and large and significant inter-cluster differences in most measures and performance between clusters (p < 0.05). The cluster analysis produced classes comprising athletes with similar degrees of activity limitation. All tests reported can help establish a more transparent classification system for para-alpine sit skiers. This study also provides a reference for evidence-based classification systems in other Para sports.

Lesion-specific cortical activation following sensory stimulation in patients with subacute stroke.

BACKGROUND: Sensory stimulation can play a fundamental role in the activation of the primary sensorimotor cortex (S1-M1), which can promote motor learning and M1 plasticity in stroke patients. However, studies have focused mainly on investigating the influence of brain lesion profiles on the activation patterns of S1-M1 during motor tasks instead of sensory tasks. Therefore, the objective of this study is to explore the lesion-specific activation patterns due to different brain lesion profiles and types during focal vibration (FV). METHODS: In total 52 subacute stroke patients were recruited in this clinical experiment, including patients with basal ganglia hemorrhage/ischemia, brainstem ischemia, other subcortical ischemia, cortical ischemia, and mixed cortical-subcortical ischemia. Electroencephalograms (EEG) were recorded following a resting state lasting for 4 min and three sessions of FV. FV was applied over the muscle belly of the affected limb's biceps for 3 min each session. Beta motor-related EEG power desynchronization overlying S1-M1 was used to indicate the activation of S1-M1, while the laterality coefficient (LC) of the activation of S1-M1 was used to assess the interhemispheric asymmetry of brain activation. RESULTS: (1) Regarding brain lesion profiles, FV could lead to the significant activation of bilateral S1-M1 in patients with basal ganglia ischemia and other subcortical ischemia. The activation of ipsilesional S1-M1 in patients with brainstem ischemia was higher than that in patients with cortical ischemia. No activation of S1-M1 was observed in patients with lesions involving cortical regions. (2) Regarding brain lesion types, FV could induce the activation of bilateral S1-M1 in patients with basal ganglia hemorrhage, which was significantly higher than that in patients with basal ganglia ischemia. Additionally, LC showed no significant correlation with the modified Barthel index (MBI) in all patients, but a positive correlation with MBI in patients with basal ganglia lesions. CONCLUSIONS: These results reveal that sensory stimulation can induce lesion-specific activation patterns of S1-M1. This indicates FV could be applied in a personalized manner based on the lesion-specific activation of S1-M1 in stroke patients with different lesion profiles and types. Our study may contribute to a better understanding of the underlying mechanisms of cortical reorganization.

Enhancement of EEG-EMG coupling detection using corticomuscular coherence with spatial-temporal optimization.

Objective. Corticomuscular coherence (CMC) is widely used to detect and quantify the coupling between motor cortex and effector muscles. It is promisingly used in human-machine interaction (HMI) supported rehabilitation training to promote the closed-loop motor control for stroke patients. However, suffering from weak coherence features and low accuracy in contingent neurofeedback, its application to HMI rehabilitation robots is currently limited. In this paper, we propose the concept of spatial-temporal CMC (STCMC), which is the coherence by refining CMC with delay compensation and spatial optimization.Approach. The proposed STCMC method measures the coherence between electroencephalogram (EEG) and electromyogram (EMG) in the multivariate spaces. Specifically, we combined delay compensation and spatial optimization to maximize the absolute value of the coherence. Then, we tested the reliability and effectiveness of STCMC on neurophysiological data of force tracking tasks.Main results. Compared with CMC, STCMC not only enhanced the coherence significantly between brain and muscle signals, but also produced higher classification accuracy. Further analysis showed that temporal and spatial parameters estimated by the STCMC reflected more detailed brain topographical patterns, which emphasized the different roles between the contralateral and ipsilateral hemisphere.Significance. This study integrates delay compensation and spatial optimization to give a new perspective for corticomuscular coupling analysis. It is also feasible to design robotic neurorehabilitation paradigms by the proposed method.

Tailoring brain-machine interface rehabilitation training based on neural reorganization: towards personalized treatment for stroke patients.

Electroencephalogram (EEG)-based brain-machine interface (BMI) has the potential to enhance rehabilitation training efficiency, but it still remains elusive regarding how to design BMI training for heterogeneous stroke patients with varied neural reorganization. Here, we hypothesize that tailoring BMI training according to different patterns of neural reorganization can contribute to a personalized rehabilitation trajectory. Thirteen stroke patients were recruited in a 2-week personalized BMI training experiment. Clinical and behavioral measurements, as well as cortical and muscular activities, were assessed before and after training. Following treatment, significant improvements were found in motor function assessment. Three types of brain activation patterns were identified during BMI tasks, namely, bilateral widespread activation, ipsilesional focusing activation, and contralesional recruitment activation. Patients with either ipsilesional dominance or contralesional dominance can achieve recovery through personalized BMI training. Results indicate that personalized BMI training tends to connect the potentially reorganized brain areas with event-contingent proprioceptive feedback. It can also be inferred that personalization plays an important role in establishing the sensorimotor loop in BMI training. With further understanding of neural rehabilitation mechanisms, personalized treatment strategy is a promising way to improve the rehabilitation efficacy and promote the clinical use of rehabilitation robots and other neurotechnologies.

A Transferable Deep Learning Prognosis Model for Predicting Stroke Patients' Recovery in Different Rehabilitation Trainings.

Since the underlying mechanisms of neurorehabilitation are not fully understood, the prognosis of stroke recovery faces significant difficulties. Recovery outcomes can vary when undergoing different treatments; however, few models have been developed to predict patient outcomes toward multiple treatments. In this study, we aimed to investigate the potential of predicting a treatment's outcome using a deep learning prognosis model developed for another treatment. A total of 15 stroke survivors were recruited in this study, and their clinical and physiological data were measured before and after the treatment (clinical measurement, biomechanical measurement, and electroencephalography (EEG) measurement). Multiple biomarkers and clinical scale scores of patients who had completed manual stretching rehabilitation training were analyzed. Data were used to train deep learning prognosis models, yielding an 87.50% prognosis accuracy. Pre-trained prognosis models were then applied to patients who completed robotic-assisted stretching training, yielding a prognosis accuracy of 91.84%. Interpretation of the deep learning models revealed several key factors influencing patients' recoveries, including the plantar-flexor active range of movement (r = 0.930, P = 0.02), dorsiflexor strength (r = 0.932, P = 0.002), plantar-flexor strength (r = 0.930, P = 0.002), EEG power spectrum density and EEG functional connectivities in the occipital, central parietal, and parietal areas. Our results suggest (i) that deep learning can be a promising method for accurate prediction of the recovery potential of stroke patients in clinical scenarios and (ii) that it can be successfully applied to different rehabilitation trainings with explainable factors.

EEG-based evaluation of motion sickness and reducing sensory conflict in a simulated autonomous driving environment.

Autonomous driving offers significant potential for changes in the automotive industry. However, sensory conflict during autonomous driving can lead to motion sickness. Quantitative evaluation and effective preventions to predict and reduce motion sickness are needed. The goal of this study is to verify the objective indicator of motion sickness level based on encephalography (EEG) that we proposed before and investigate the influence of attenuating sensory conflict on motion sickness. A 6-degree of freedom (DOF) driving simulator platform was used to provide an autonomous driving environment to the subjects, and the subjective motion sickness level (MSL), as well as the EEG signals of 15 healthy subjects, were collected simultaneously during 3 conditions, i) autonomous driving, ii) autonomous driving with eyes blindfolded and iii) active driving. The MSLs were reported by the subjects every two minutes, providing a reference to the recorded EEG signals. The EEG signals were analyzed and compared among different conditions. Average MSLs were higher in autonomous driving than in autonomous driving with eyes blindfolded and active driving, together with the increase of the mean EEG frequency of theta band in the central, parietal and occipital areas (FC5, Cz, CP5, P3, and POz). These findings validated that EEG mean frequency of theta band could be an indicator of motion sickness, besides an attenuated visual input or active control of the vehicle can effectively reduce the generation of motion sickness.

Application, challenge and perspective of triboelectric nanogenerator as micro-nano energy and self-powered biosystem.

As a new type of energy harvesting technology, the triboelectric nanogenerator (TENG) can convert distributed energy into electrical energy. It is widely used in various fields such as wearable devices, biomedical devices, Internet of Things (IoT), natural environment, etc. However, there are still some issues that need to be solved for the commercial implementation of TENGs. This review focuses on four major kinds of applications for TENG as the platform of harvesting micro-nano energy: in vivo, in vitro, living environment and wild environment. The challenges and feasible techniques facing TENGs are summarized in three aspects, including low energy output, immature manufacturing technology and unreliable service life. We also review the recent progress in the strategies for improving the output performance and robustness of TENGs, including but not limited to material optimization, device engineering and power management. The aim is to establish a feasible framework of TENGs from laboratory to engineering application. Finally, the future trend of TENGs' application in distributed sensors and biomedical devices has prospected as a promising micro-nano energy for guiding the next innovation researches.

Recognizing the individualized sensorimotor loop of stroke patients during BMI-supported rehabilitation training based on brain functional connectivity analysis.

BACKGROUND: Electroencephalogram (EEG) based brain-machine interaction training can facilitate rehabilitation by closing the sensorimotor loop. However, it remains unclear how to evaluate whether the loop is closed, especially for stroke patients whose brain regions of motor control and sensorimotor feedback could be altered. Our hypothesis is that motor recovery depends on whether sensorimotor loop is established poststroke. This study aims to explore how to evaluate the establishment of sensorimotor loop based on the evolving neural reorganization patterns after stroke. NEW METHOD: 14 stroke patients participated in the experiment and EEG were recorded during three specific tasks: Movement Imagery (MI), Passive Movement (PM) and Movement Execution (ME). Activated brain regions correlated with movement intention expression and sensorimotor feedback were detected respectively during MI and PM. In ME, local-averaged Phase Lag Index (PLI) was analyzed to represent the functional connectivity between activated brain regions of MI and PM. RESULTS: Individualized cortical activation was found both in MI and PM. The overlapping brain activation during PM and MI did not correlate with patient's Fugl-Meyer Upper Extremity Motor Score (FMU) . However, we found that FMU of the group with higher local-averaged PLI was statistically higher than FMU of the group with lower local-averaged PLI compared with global-averaged PLI (p < 0.05). CONCLUSIONS: The findings demonstrate functional connectivity between activated brain regions of motor control and sensorimotor feedback may imply if the individualized sensorimotor loop is established poststroke. The successful formation of the closed loop can indicate stroke patients' motor recovery.

Brain oscillatory activity correlates with the relief of post-stroke spasticity following focal vibration.

BACKGROUND: Some evidence has demonstrated that focal vibration (FV) contributes to the relief of post-stroke spasticity (PSS). Although the changes of cortical activity correlating with the relief of PSS induced by FV have been explored using transcranial magnetic stimulation, brain oscillatory activity during the above-mentioned process has not been fully understood. OBJECTIVE: The main purpose of this study is to explore the correlation between the changes in brain oscillatory activity and the relief of PSS following FV. METHODS: A clinical experiment was carried out, in which FV (87 Hz, 0.28 mm) was applied over the antagonist muscle's belly of the spastic muscle of ten chronic spastic stroke patients. An electroencephalogram was recorded following before-FV and three sessions of FV. Muscle properties to assess the relief of PSS were tested before-FV and immediately after three sessions of FV. RESULTS: EEG analysis has shown that FV can lead to the significant decrease in the relative power at C3 and C4 in the beta1 (13, 18 Hz), as well as C3 and C4 in the beta3 band (21, 30 Hz), indicating the activation of primary sensorimotor cortex (S1-M1). Muscle properties analysis has shown that, in the state of flexion of spastic muscle, muscle compliance and muscle displacement of the spastic muscle significantly increased right after FV, illustrating the relief of the spasticity. Moreover, the increase of muscle compliance is positively correlated with the reduction of difference index of the activation of bilateral S1-M1. CONCLUSIONS: This finding indicated that the relief of PSS can be associated with the activation of bilateral S1-M1 where the activation of the ipsilesional S1-M1 was higher than that of the contralesional one. This study showed the brain oscillatory activity in the bilateral S1-M1 correlating with the relief of PSS following FV, which could contribute to establishing cortex oscillatory activity as a biomarker of the relief of PSS and providing a potential mechanism explanation of the relief of PSS.

Size-Controllable Eu-MOFs through Machine Learning Technology: Application for High Sensitive Ions and Small-Molecular Identification.

Metal-organic frameworks (MOFs) with the aggregation-induced emission (AIE) activities exhibit potential applications in the fields of energy and biomedical technology. However, the controllable synthesis of MOFs in the varied particle sizes not only affects their AIE activities, but also restricts their application scenarios. In this work, the varied particle sizes of Eu-MOFs are synthesized by adjusting the synthesis process parameters, and their variation rules combining the single factor analysis method with machine learning technology are studied. Based on the R2 score, the gradient boosting decision tree (GBDT) regression model (0.9535) is employed to calculate the weight and correlation between different synthesis process parameters and it is shown that all these parameters have synergic effects on the particle sizes of Eu-MOFs, and the Eu-precursors concentration dominates in their synthesis process. Furthermore, it is indicated that the large size of Eu-MOFs and strong structural stability contribute to their high AIE activities. Finally, a screen-printed pattern is fabricated using the sample of "120-0.3-6," and this pattern exhibits a bright red fluorescence under the UV light. More importantly, this kind of Eu-MOFs can also be used to identify varied ions (Fe3+ , F- , I- , SO42- , CO32- , and PO43- ) and citric acid.

Decoding lip language using triboelectric sensors with deep learning.

Lip language is an effective method of voice-off communication in daily life for people with vocal cord lesions and laryngeal and lingual injuries without occupying the hands. Collection and interpretation of lip language is challenging. Here, we propose the concept of a novel lip-language decoding system with self-powered, low-cost, contact and flexible triboelectric sensors and a well-trained dilated recurrent neural network model based on prototype learning. The structural principle and electrical properties of the flexible sensors are measured and analysed. Lip motions for selected vowels, words, phrases, silent speech and voice speech are collected and compared. The prototype learning model reaches a test accuracy of 94.5% in training 20 classes with 100 samples each. The applications, such as identity recognition to unlock a gate, directional control of a toy car and lip-motion to speech conversion, work well and demonstrate great feasibility and potential. Our work presents a promising way to help people lacking a voice live a convenient life with barrier-free communication and boost their happiness, enriches the diversity of lip-language translation systems and will have potential value in many applications.

5 Hz rTMS improves motor-imagery based BCI classification performance.

Brain-computer interface (BCI) based rehabilitation has been proven a promising method facilitating motor recovery. Recognizing motor intention is crucial for realizing BCI rehabilitation training. Event-related desynchronization (ERD) is a kind of electroencephalogram (EEG) inherent characteristics associated with motor intention. However, due to brain deficits poststroke, some patients are not able to generate ERD, which discourages them to be involved in BCI rehabilitation training. To boost ERD during motor imagery (MI), this paper investigates the effects of high-frequency repetitive transcranial magnetic stimulation (rTMS) on BCI classification performance. Eleven subjects participated in this study. The experiment consisted of two conditions: rTMS + MI versus sham rTMS + MI, which were arranged on different days. MI tests with 64-channel EEG recording were arranged immediately before and after rTMS and sham rTMS. Time-frequency analysis were utilized to measure ERD changes. Common spatial pattern was used to extract features and linear discriminant analysis was used to calculate offline classification accuracies. Paired-sample t-test and Wilcoxon signed rank tests with post-hoc analysis were used to compare performance before and after stimulation. Statistically stronger ERD (-13.93±12.99%) was found after real rTMS compared with ERD (-5.71±21.25%) before real rTMS (p<0.05). Classification accuracy after real rTMS (70.71±10.32%) tended to be higher than that before real rTMS (66.50±8.48%) (p<0.1). However, no statistical differences were found after sham stimulation. This research provides an effective method in improving BCI performance by utilizing neural modulation.Clinical Relevance- This study offers a promising treatment for patients who cannot be recruited in BCI rehabilitation training due to poor BCI classification performance.

CNN-Based Prognosis of BCI Rehabilitation Using EEG From First Session BCI Training.

Stroke is a world-leading disease for causing disability. Brain-computer interaction (BCI) training has been proved to be a promising method in facilitating motor recovery. However, due to differences in each patient's neural-clinical profile, the potential of recovery for different patients can vary significantly by conducting BCI training, which remains a major problem in clinical rehabilitation practice. To address this issue, the objective of this study is to prognosticate the outcome of BCI training using motor state electroencephalographic (EEG) collected during the first session of BCI tasks, with the aim of prescribing BCI training accordingly. A Convolution Neural Network (CNN) based prognosis model was developed to predict the outcome of 11 stroke patients' recovery following a 2-week rehabilitation training with BCI. In our study, functional connectivity and power spectrum have been evaluated and applied as the inputs of CNN to regress patients' recovery rate. A saliency map was used to identify the correlation between EEG channels with the recovery outcome. The performance of our model was assessed using the leave-one-out cross-validation. Overall, the proposed model predicted patients' recovery with R2 0.98 and MSE 0.89. According to the saliency map, the highest functional connectivity occurred in Fp2/Fpz-AF8, Fp2/F4/F8-P3, P1/PO7-PO5 and AF3-AF4. Our results demonstrated that deep learning method has the potential to predict the recovery rate of BCI training, which contributes to guiding individualized prescription in the early stage of clinical rehabilitation.