Soft robotic devices, known for their high compliance, are increasingly being used in assistance and rehabilitation. However, the limited force output of soft actuators has hindered their broader adoption. In this study, a lobster-tail-inspired high-force-output soft pneumatic bending actuator (SPBA) is developed, featuring a soft deformable body and a rigid kirigami limiting shell. The SPBA, with a radius of 10 mm, can generate forces of approximately 22 N at an internal pressure of 0.1 MPa and 36.43 N at 0.16 MPa. An analytical model based on the Euler-Bernoulli beam theory, incorporating a hyperelastic material model, has been constructed to predict the deformation and force of the actuated SPBA. This model demonstrates good agreement with simulated and experimental results. For assistance, a soft robotic gripper with four SPBAs can lift a weight of 5.38 kg at 0.26 MPa. For rehabilitation, an SPBA-based hand exoskeleton has been developed, demonstrating significant effectiveness in mitigating hand spasticity following strokes. This study introduces a novel SPBA design with promising potential for future applications in grasping, assistance, and rehabilitation.

Human-machine interfaces (HMIs) have been widely integrated with motor rehabilitation and augmentation systems. Forecasting movement transitions during human-robot interaction is crucial to ensure system safety, intuitiveness, and reactivity, particularly in anticipating human motor intentions under sudden perturbations or emergency scenarios. In this study, we investigated pre-movement neural signatures preceding sudden movement transitions during ongoing bimanual tasks. Informed by these findings, we propose a physiology-informed EEG Transformer (PI-EEGformer) for EEG-based motor intention recognition. An EEG dataset collected from a bimanual movement task, where one hand was required to switch motor states in response to unexpected cues, was used to evaluate the performance of the PI-EEGformer in comparison with seven state-of-the-art models. Results showed that, prior to the movement transition, EEG power spectrum decreased, and movement-related cortical potentials (MRCPs) could be accurately extracted from the contralateral motor cortex. PI-EEGformer reached an average accuracy of 0.912 in inter-subject tests and 0.829 in cross-subject tests in detecting movement transitions using EEG from 500 ms to 100 ms prior to the actual movement. This performance was superior to all the state-of-the-art models tested. These results demonstrate that EEG neural signatures can predict sudden movement transitions during ongoing bimanual tasks. The PI-EEGformer, designed with these physiological signatures, can enable accurate prediction of sudden movement transitions. This study will help improve the response of HMI systems to sudden disturbances, contributing to a more realistic HMI system.

Brain-computer interface (BCI)-based neurorehabilitation holds promise in enhancing motor recovery after stroke. However, recent research has reported heterogeneous results, indicating both responders and non-responders to BCI therapy. Using explainable artificial intelligence (XAI) methods, this study aims to investigate the independent and combined importance of multimodal behavioral data to predict patients’ response to BCI therapy. Forty-two subacute stroke patients with lower-limb motor impairment underwent behavioral assessments, and received two-week BCI rehabilitation training. Linear regression, elastic net and artificial neural network models were developed to predict response to BCI therapy. Two XAI techniques, the stepwise method and Shapley additive explanation, were used to interpret model outcomes. The multivariate model (R2=0.852, P<0.001) that combines an optimal subset of multimodal behavioral data outperformed the univariate model (R2=0.758, P<0.001) trained on a single variable. Elastic net and artificial neural network models both demonstrated high prediction performance, as indicated by classification accuracies of 0.810 and 0.762, and areas under the receiver operating characteristic curve of 0.782 and 0.771. Our results revealed that multimodal behavioral data, including demographic, clinical, and biomechanical characteristics, provided unique and complementary information for interpreting the response of subacute patients to BCI therapy. Particularly, baseline motor impairment, muscle spasticity and balance function were primary predictors. Our findings highlight the core role of XAI methods towards precision medicine, which can help clinicians to identify individual recovery potentials and plan optimal treatment strategies.

Upper-limb amputation disrupts natural somatosensory pathways and impairs motor control, increasing reliance on visual feedback during prosthesis operation and reducing intuitiveness and embodiment. Although haptic feedback can improve controllability, most commercial myoelectric prostheses still lack effective closed-loop feedback. Here, we present a flexible Bidirectional Haptic Feedback System (BHFS) integrating triboelectric multidimensional tactile sensing with multichannel transcutaneous electrical stimulation (TES). The customized Triboelectric Flexible Tactile Sensor (TFT-Sensor), featuring a strontium titanate (SrTiO3)-modified triboelectric layer with a pyramid microstructure, achieves a 75% increase in open-circuit voltage compared to the baseline, enabling zero-power sensing of pressure, shear force, and surface texture. A flexible electrode armband driven by a multichannel electrical stimulator delivers spatiotemporally encoded electrical patterns through closed-loop mapping algorithms, providing intuitive multidimensional somatosensory feedback. In simulated prosthetic-hand experiments under audiovisual deprivation, subjects successfully adjusted grip force in real time, maintained stable grasping, and distinguished different surface textures. By establishing a closed-loop "sensing-mapping-stimulation" framework, the proposed system offers a promising strategy for restoring naturalistic somatosensation in prosthetic devices and advancing rehabilitation engineering and human-machine interfaces.

Objective. Hybrid brain-computer interface (BCI) systems incorporate electroencephalography (EEG) and electromyography (EMG) signals to extract corticomuscular coherence (CMC) features, enabling self-modulation of neural communication. While promising for stroke rehabilitation, the neurophysiological mechanism underlying hybrid BCI therapy remains poorly understood. To address this gap, we characterized post-stroke CMC dynamics during ankle dorsiflexion and further established their relationship with functional motor recovery.Approach. We acquired synchronous EEG and high-density EMG recordings from 13 subacute stroke patients (with their affected limb) before and after three-week rehabilitation, and 9 age-matched healthy controls (using their dominant limb) during isometric ankle dorsiflexion. Using multivariate coupling analysis, we computed EEG and EMG projection vectors to identify optimal coupling patterns. Subsequently, we derived CMC spectra and topographies through coherence analysis to characterize corticomuscular interactions at spatial and spectral scales.Main results. Compared to healthy controls, stroke patients demonstrated reduced beta-band CMC patterns, particularly within the sensorimotor areas involved in the foot movement. No significant differences in CMC patterns were observed between stroke patients before and after rehabilitation training. Further analysis revealed significant correlation between beta-band CMC changes and clinical improvements measured by the Berg balance scale.Significance. Beta-band CMC is a potential neurophysiological biomarker of motor recovery following stroke. These findings provide novel insights into the disrupted corticomuscular communication underlying post-stroke motor dysfunction, while offering mechanistic evidence to guide the design and implementation of hybrid BCI systems that target these specific biomarkers for therapeutic intervention.

Brain-computer interfaces (BCIs) promise to extend human movement capabilities by enabling direct neural control of supernumerary effectors, yet integrating augmented commands with multiple degrees of freedom without disrupting natural movement remains a key challenge. Here, we propose a tactile-encoded BCI that leverages sensory afferents through a tactile-evoked P300 paradigm, allowing reliable decoding of supernumerary motor intentions even when superimposed with voluntary actions. The interface was evaluated in a multi-day experiment comprising a single motor recognition task to validate baseline BCI performance and a dual-task paradigm to assess the potential influence between the BCI and natural human movement. The interface achieved real-time and reliable decoding of four supernumerary degrees of freedom, with significant performance improvements after three days of training. After training, performance did not differ significantly between the single-task and dual-task conditions, and natural movement remained unimpaired during concurrent supernumerary control. Lastly, the interface was deployed in a movement augmentation task, demonstrating its ability to command two supernumerary robotic arms for functional assistance during bimanual tasks. These results establish a neural interface paradigm for movement augmentation through stimulation of sensory afferents, expanding motor degrees of freedom without impairing natural movement.

Withdrawal Statement The authors have withdrawn this manuscript because the authors have decided to conduct a comprehensive and substantial revision of the manuscript. This revision will involve significant adjustments to the study design, data analysis, and key conclusions, which will fundamentally change the content and focus of the original manuscript. Therefore, we believe it is inappropriate to keep the current version as a preprint, as it does not reflect the final direction and quality of our research. Therefore, the authors do not wish this work to be cited as reference for the project. If you have any questions, please contact the corresponding author.

Multivariate cortico-muscular analysis has recently emerged as a promising approach for evaluating the corticospinal neural pathway. However, current multivariate approaches encounter challenges such as high dimensionality and limited sample sizes, thus restricting their further applications. In this paper, we propose a structured and sparse partial least squares coherence algorithm (ssPLSC) to extract shared latent space representations related to cortico-muscular interactions. Our approach leverages an embedded optimization framework by integrating a partial least square (PLS)-based objective function with sparsity and connectivity-based structured constraints, addressing the generalizability, sparsity and spatial structure. To solve the optimization problem, we develop an efficient alternating iterative algorithm within a unified framework and prove its convergence experimentally. Extensive experimental results from one synthetic and several real-world datasets have demonstrated that ssPLSC can achieve competitive or better performance over some representative multivariate cortico-muscular fusion methods, particularly in scenarios characterized by limited sample sizes and high noise levels. This study provides a novel multivariate fusion method for cortico-muscular analysis, offering a potential tool for the evaluation of corticospinal pathway integrity in neurological disorders.

Hemifacial spasm (HFS) is a neurological disorder characterized by involuntary contractions of the facial muscles, which can significantly influence patients' quality of life. Traditional diagnostic methods are often subjective, and electromyography (EMG) monitoring is constrained by equipment limitations and interference. Current treatments include short-term Botulinum toxin (BTX) injections and high-risk microvascular decompression (MVD), both of which suffer from low patient compliance. This study introduces a closed-loop facial nerve stimulation system integrated into eyewear, featuring triboelectric sensors doped with butylated melamine formaldehyde (BMF)-CaCu3Ti4O12 (CCTO), and constructed with micrometer-scale hemispherical structures, which enhance performance by approximately 2.3 times. These sensors capture subtle dynamic signal changes in real-time, suitable for monitoring minute facial muscle activities, while consuming zero power. Additionally, a customized electrical stimulation module with adjustable parameters and a high-precision HFS detection model have been developed, enabling rapid activation of facial nerve stimulators for targeted neuromodulation upon detecting spasms. The system achieves a recognition accuracy of 98% for HFS. Preliminary clinical validation demonstrates effectiveness in reducing spasm severity with inter-patient variability in two involved patients. Overall, this integrated system offers enhanced convenience and patient compliance, presenting a promising solution for HFS treatment.

Wind speed and wind direction sensors are crucial sensor categories in the Internet of Things (IoT), particularly vital in fields such as meteorological monitoring, construction engineering, transportation engineering, and ocean engineering. However, power supply remains a key limiting factor for the widespread application of these sensors in large-scale sensor networks. In this paper, a self-powered, non-contact wind speed and direction sensor based on the triboelectric nanogenerator (SD-TENG) is proposed. The optimized wind speed measurement structure has a start-up wind speed as low as 0.2 m/s and exhibits good linearity in the range of 0.2-29 m/s. Additionally, the sensor demonstrates high temperature and humidity resistance, with a voltage attenuation of 2.4 % at 45 degrees C ambient temperature and 9.8 % at 95 % relative humidity. For wind direction measurement, the design of non-uniform electrodes enhances the recognition capability of different channels. To meet the demands of remote monitoring, we have designed an advanced signal processing circuit that can directly convert the raw output of a wind speed sensor into wind speed information and upload it to a cloud platform via a host. This system not only records and displays wind speed data in real-time but also features historical data storage and alarm functionalities, enhancing the intelligence and automation levels of wind speed monitoring. Additionally, users can access and analyze wind speed data through both computer and mobile devices, ensuring the system's efficiency and reliability. This work provides crucial technical support for the advancement of smart cities, clean energy, and environmental monitoring, thereby promoting the application and dissemination of IoT technology in the environmental field.

Embodied intelligence and humanoid robots aim to mimic interpersonal interactions to achieve affective human-robot interaction (HRI). A major challenge in advancing HRI lies in effectively emulating interpersonal affective interactions and evaluating the resulting artificial empathy. To address these challenges, we propose SpatialChannel Interaction Attention Neural Networks (SCIANN)—a novel EEG-based architecture that combines topological brain activation and connectivity patterns to decode empathy in motor collaboration. A private EEG dataset from a collaborative brain-computer interface motor control experiment and a public EEG dataset from a dyadic perceptual crossing experiment were used for evaluating SCIANN's performance with comparisons with five baseline models. Results showed that SCIANN outperformed the state-of-the-art baseline models. In the private dataset, SCIANN reached an accuracy of 100% both in inter-subject and cross-subject tests for detecting whether empathy is induced or not. For classifying 4-class empathy, it achieved an accuracy of 98.3% in the inter-subject test, and 48.1% in the cross-subject test. In the public dataset, SCIANN reached a classification accuracy of 92.2% in inter-subject and 91.7% in cross-subject tests for detecting whether empathy is induced or not. Feature visualization results revealed that contributing EEG channel importance features and channel interaction features aligned with established neurophysiological findings. These results collectively demonstrate SCIANN's potential as a robust, generalizable framework for artificial empathy assessment in HRI applications.

Stroke stands as a leading cause of disability, often resulting in sensory and motor impairments, particularly in upper limbs. Sensory rehabilitation is vital for functional recovery but is hindered by its reliance on healthcare professionals and the prioritization of motor recovery over sensory restoration. This study introduces a Triboelectric Sensor and Pressure Feedback Ring (TSPF-Ring) as a solution to bridge this gap by amalgamating triboelectric sensing and pneumatic feedback into a wearable device. The sensitive tactile sensor is capable of recognizing multi-dimensional changes such as pressure, proximity and texture, converting these into visual stimuli with a classification accuracy exceeding 99%. Meanwhile, the pneumatic actuator provides adjustable tactile feedback within a 0-12N range. A visual-tactile synchronized rehabilitation training utilizing the TSPF-Ring system was implemented to effectively enhance activation in the patient's sensorimotor cortex, as validated by electroencephalogram experiments. The results indicate that the TSPF-Ring holds promise in improving hand sensory function in stroke patients by promoting neural remodeling through synchronized visual-tactile stimulation, offering a novel wearable device solution for sensory rehabilitation.

Objective: Ultrasound-guided puncture often faces challenges in visualizing the needle. Needle positioning systems can provide real-time needle position information to the doctor. Due to its large spatial footprint and limited portability, positioning methods based on external tracking systems have not been widely adopted. In this study, we developed a multipole magnetic needle positioning method for ultrasound-guided puncture, aiming to maintain the portability advantages of ultrasound while achieving good positioning accuracy. Methods: A magnetic sensor array is installed within the ultrasound probe. The needle continuously generates a specific magnetic field through multipole magnetization. A positioning algorithm combining magnetic gradient tensor method and direct inversion method can accurately locate the position of the needle. To improve localization accuracy, an environmental magnetic field identification method based on machine learning is employed. Results: The environmental magnetic field identification method achieved an accuracy, precision, recall, and F1 score of 98.38%, 98.70%, 98.06%, and 98.38%, respectively. During the puncture process, the maximum positioning errors of tip and direction are respectively 3.49 mm and 4.93 degrees. In the phantom puncture experiment, novices who use our positioning system have a higher first-time success rate. Conclusion: This needle positioning method can accurately locate the multipole magnetic needle. The ultrasound-guided puncture system using this method can display the position of the puncture needle in real time. It can help novices complete puncture tasks more easily. Significance: This system provides a new approach to the design of ultrasound-guided puncture navigation systems. The positioning algorithm can also be applied to locate other elongated ferromagnetic objects.

Upper-limb motor impairment following stroke predominantly results from the damage to corticospinal tract (CST) integrity. Current clinical assessments of CST integrity face significant limitations, including high costs, specialized equipment, and inability to guide state-dependent closed-loop rehabilitation therapies. Corticomuscular coherence (CMC), which measures the functional coupling between sensorimotor cortical rhythms and muscular activity, represents a potentially accessible, and clinically feasible alternative for evaluating CST damage in stroke patients. However, it remains unclear whether CMC is a reliable biomarker of CST integrity and poststroke motor recovery. To address this issue, we measured electroencephalography (EEG), electromyography (EMG) and motor-evoked potential (MEP) status from subacute patients during grip and finger extension tasks performed with both affected and unaffected hands. Using a multivariate analysis approach, we identified abnormal modulations of CMC and event-related desynchronization (ERD), characterized by frequency-specific disruptions and distinctive spatial distributions. Crucially, our results also demonstrated that CMC reflects neurophysiological mechanisms distinct from cortical activation. Further analysis revealed significant CMC differences between patient groups stratified by MEP status, and confirmed the predictive value of CMC features for assessing functional CST integrity. Additionally, there existed significant associations between beta-band CMC and clinical motor assessments. These findings highlight the potential utility of CMC as a valuable tool for assessing functional CST integrity and motor recovery after stroke.

The atmospheric pressure microplasma jet (APMJ) is a low-energy jet with widespread applications. However, the bulkiness, high cost, immobility, and danger of commercial devices limit their further development. Here, a dielectric barrier discharge (DBD) microplasma, which is characterized to be portable, inexpensive, easy, and safe based on a triboelectric nanogenerator (TENG), is proposed to generate an APMJ. Four typical electrodes are compared in terms of the generation performance of the triboelectric microplasma, and the best one, with a ring electrode surrounding the capillary and a wire electrode located in the center, is chosen for the experiments. The effects of the electrode structural parameters on the spectral intensity and discharge current are explored through several experiments. Moreover, the electric field and potential distributions are obtained through theoretical analysis and simulation. Finally, an extra drainage electrode is incorporated and placed beside the nozzle of the capillary for enhancing the performance of the APMJ. Consequently, the spectral intensity of the APMJ with a drainage electrode is increased by 53.1% and the flame length by 35.7% when compared to those without one. The newly proposed APMJ has great potential for application in biomedical fields, such as cell processing, sterilization, and wound disinfection.

The healthcare sector is challenged by critical workforce shortages, and this is causing an urgent need for innovative technologies to support or augment human roles. Although much of the research effort has focused on support and training of functional tasks, the emotional impacts that humans bring to the loop have often been overlooked. This gap is particularly pressing in healthcare and therapy, where empathy and emotional support are central to patient well-being. Unlike machines, humans possess a unique capacity for empathy, connecting emotionally with others and providing the essential support that fosters healing. Bridging this gap requires integrating affective elements, such as empathy, into therapeutic systems, which is the key to improving their effectiveness. This review explores groundbreaking techniques that integrate interpersonal interactions within therapy and healthcare, focusing on multiplayer games that strengthen real-time social connections, alongside social robots and virtual agents designed to simulate human-like affective interactions. Using artificial intelligence, these technologies aim to replicate complex human dynamics and foster artificial empathy, thus revolutionizing how we deliver care and support.

Brain-computer interfaces (BCIs) promise to extend human movement capabilities by enabling direct neural control of supernumerary effectors, yet integrating augmented commands with multiple degrees of freedom without disrupting natural movement remains a key challenge. Here, we propose a tactile-encoded BCI that leverages sensory afferents through a novel tactile-evoked P300 paradigm, allowing intuitive and reliable decoding of supernumerary motor intentions even when superimposed with voluntary actions. The interface was evaluated in a multi-day experiment comprising of a single motor recognition task to validate baseline BCI performance and a dual task paradigm to assess the potential influence between the BCI and natural human movement. The brain interface achieved real-time and reliable decoding of four supernumerary degrees of freedom, with significant performance improvements after only three days of training. Importantly, after training, performance did not differ significantly between the single- and dual-BCI task conditions, and natural movement remained unimpaired during concurrent supernumerary control. Lastly, the interface was deployed in a movement augmentation task, demonstrating its ability to command two supernumerary robotic arms for functional assistance during bimanual tasks. These results establish a new neural interface paradigm for movement augmentation through stimulation of sensory afferents, expanding motor degrees of freedom without impairing natural movement.

In the past decade, advances in IT, microelectronics, materials science, and the growing demand for new medical solutions in an aging society have greatly boosted wearable devices' ability to monitor physiological signals. However, traditional methods of physiological signal analysis have limitations when it comes to processing complex, multimodal data, particularly in the context of nonlinear, non-stationary, and highly personalized information. Recently, AI technologies-especially deep learning, machine learning, and multimodal data fusion-have introduced new solutions for physiological signal analysis, significantly improving the accuracy and real-time performance of signal processing. This work reviews the latest advancements in AI within the realm of wearable physiological signal monitoring. It systematically explores the advantages of AI in enhancing the accuracy of signal extraction and classification, enabling personalized health monitoring and disease prediction, and optimizing human-computer interaction. Additionally, it analyzes specific applications of AI in the analysis of bioelectric, mechanical, chemical, and temperature signals. The work also discusses challenges such as data privacy, algorithm generalization, real-time processing, and model interpretability. Finally, it prospects the development trends of AI-driven wearable physiological monitoring technology, focusing on materials, algorithms, chips, and multidisciplinary collaborative innovation.

Combination therapy with motor imagery (MI)-based brain-computer interface (BCI) and repetitive transcranial magnetic stimulation (rTMS) is a promising therapy for poststroke neurorehabilitation. However, with patients' individual differences, the clinical effects vary greatly. This study aims to explore the hypothesis that stroke patients show individualized cortical response to rTMS treatments, which determine the effectiveness of rTMS-induced MI decoding enhancement. We applied four kinds of rTMS treatments respectively to four groups of subacute stroke patients, twenty-six patients in total, and observed their EEG dynamics, MI decoding performance, and Fugl-Meyer assessment changes following 2-week neuromodulation. Four treatments consisted of ipsilesional 10 Hz rTMS, contralesional 1 Hz rTMS, ipsilesional 1 Hz rTMS, and sham stimulation. Results showed stroke patients with different neural reorganization patterns responded individually to rTMS therapy. Patients with cortical lesions mostly showed contralesional recruitment and patients without cortical lesions mostly presented ipsilesional focusing. Significant activation increases in the ipsilesional hemisphere (pre: -15.7% ∓ 8.2%, post: -17.3% ∓ 8.1%, p = 0.037) and MI decoding accuracy enhancement (pre: 76.3 ± 13.8%, post: 86.6 ± 8.2%, p = 0.037) were concurrently found in no-cortical-lesion patients with ipsilesional activation treatment. In the group of patients without cortical lesions, recovery rate in those receiving ipsilesional activation therapy (23.5 ± 10.4%) was higher than those receiving ipsilesional suppression therapy (9.9 ± 9.3%) (p = 0.041). This study reveals that tailoring neuromodulation therapy by recognizing cortical activation patterns is promising for improving effectiveness of the combination therapy with BCI and rTMS.