Abstract Humanoid robots, intelligent machines resembling the human body in shape and functions, cannot only replace humans to complete services dangerous tasks but also deepen own understanding of mimicking process. Nowadays, attaching a large number sensors obtain more sensory information efficient computation is development trend for humanoid robots. Nevertheless, due constraints von Neumann‐based structures, robots are facing multiple challenges, including tremendous energy consumption,...

Brain computer interface (BCI) based training had shown promising in treating patients who have suffered from stroke with upper limb (UL) paralysis. However, the real world study, most received comprehensive treatment, not only includes BCI but also routine training. The purpose of this study was to investigate topological alterations brain functional networks following treatment including subacute stage stroke. Twenty-five hospitalized moderate severe UL paralysis were assigned into 2...

The brain, as a complex dynamically distributed information processing system, involves the coordination of large-scale brain networks such neural synchronization and fast state transitions, even at rest. However, mechanisms underlying states impact dysfunction following injury on dynamics remain poorly understood. To this end, we proposed microstate-based method to explore functional connectivity pattern associated with each microstate class. We capitalized features from eyes-closed...

Electromyography (EMG) is an integral part of many biomedical and healthcare applications. It has been used as a metric for tracking rehabilitation progress identifying diseases that affect muscle activation patterns. Although it widely in disciplines, conventional EMG recording interpretation techniques lack providing precise signal detection robust classification accuracy. In recent years, thanks to advances both material science artificial intelligence, are improving at rapid pace....

Background Bimanual motor training is an effective neurological rehabilitation strategy. However, its use has rarely been investigated in patients with paralysis caused by spinal cord injury (SCI). Therefore, we conducted a case study to investigate the effects of robot-assisted task-oriented bimanual (RBMT) on upper limb function, activities daily living, and movement-related sensorimotor activity patient SCI. Methods A bilateral paresis due incomplete cervical SCI underwent 20 sessions...

Stroke is a world-leading disease for causing disability. Brain-computer interaction (BCI) training has been proved to be promising method in facilitating motor recovery. However, due differences each patient's neural-clinical profile, the potential of recovery different patients can vary significantly by conducting BCI training, which remains major problem clinical rehabilitation practice. To address this issue, objective study prognosticate outcome using state electroencephalographic (EEG)...

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 helping to determine relationship between cortical neural activity recovery. EEG recorded different states could more accurately predict than single-state recordings. Here, we design a multi-state (combining eyes closed, EC, open, EO) fusion network predicting with after...

Since the underlying mechanisms of neurorehabilitation are not fully understood, prognosis stroke recovery faces significant difficulties. Recovery outcomes can vary when undergoing different treatments; however, few models have been developed to predict patient toward multiple treatments. In this study, we aimed investigate potential predicting a treatment's outcome using deep learning model for another treatment. A total 15 survivors were recruited in and their clinical physiological data...

Multimodal learning has gained significant attention in recent years for combining information from different modalities using Deep Neural Networks (DNNs). However, existing approaches often overlook the varying importance of and neglect uncertainty estimation, leading to limited generalization unreliable predictions. In this paper, we propose a novel algorithm, Dual-level Evidential Fusion (DDEF), address these challenges by integrating multimodal at both Basic Belief Assignment (BBA) level...

In the last decade, technology-assisted stroke rehabilitation has been focus of research. Electroencephalogram- (EEG-) based brain-computer interface (BCI) a great potential for motor in patients since closed loop between intention and actual movement established by BCI can stimulate neural pathways control. Due to deficits brain, expression may shift other brain regions during even after reorganization. The objective this paper was study event-related desynchronization (ERD) topography...

In clinical, the center of pressure (CoP) is commonly used for accessing stability a person's postural control, which highly associated with various neurological diseases and movement disorders such as Alzheimer's disease, Parkinson's chronic ankle instability. Such disease usually has long development or rehabilitation process requires long-term CoP monitoring. The current evaluation does not meet requirement, it often complicated expensive through either lab-based equipment clinical...

Hemispheric asymmetry or lateralization is a fundamental principle of brain organization. However, it poorly understood to what extent the asymmetries across different levels functional organizations are evident in health altered diseases. Here, we propose framework that integrates three degrees interactions (isolated nodes, node–node, and edge–edge) into unified analysis pipeline capture sliding window-based dynamics at both node hemisphere levels. We apply this resting-state EEG healthy...

Abstract Electroencephalogram (EEG)-based brain–machine interface (BMI) has the potential to enhance rehabilitation training efficiency, but it still remains elusive regarding how design BMI for heterogeneous stroke patients with varied neural reorganization. Here, we hypothesize that tailoring according different patterns of reorganization can contribute a personalized trajectory. Thirteen were recruited in 2-week experiment. Clinical and behavioral measurements, as well cortical muscular...

A randomized controlled pilot study.Bimanual therapy (BMT) is an effective neurorehabilitation for the upper limb, but its application to distal limb limited due methodological difficulties. Therefore, we applied exoskeleton hand perform robot-assisted task-oriented bimanual training (RBMT) in patients with stroke.To characterize effectiveness of RBMT hemiplegic stroke motor impairment.A total 19 subacute (1-6 months from onset) were and allocated conventional (CT) groups. The CT groups...

Ankle function impairment is a critical factor impairing normal walking in survivors of stroke. The soft robotic exoskeleton (SRE) novel, portable, lightweight assistive device with promising therapeutic potential for gait recovery during post-stroke rehabilitation. However, whether long-term SRE-assisted training influences and quality patients following subacute stroke unknown. Therefore, the primary objective this study was to assess effects on clinical biomechanical outcomes...

Brain plasticity, including anatomical changes and functional reorganization, is the physiological basis of recovery after spinal cord injury (SCI). The correlation between brain reorganization SCI unclear. This study aimed to explore whether alterations cortical structure network function are concomitant in sensorimotor areas incomplete SCI. Eighteen patients with (mean age 40.94 ± 14.10 years old; male:female, 7:11) 18 healthy subjects (37.33 11.79 were studied by resting state magnetic...

Background: Stroke survivors with impaired control of the ankle due to stiff plantarflexors often experience abnormal posture control, which affects balance and locomotion. Forceful stretching may decrease stiffness improve balance. Recently, a robot-aided device was developed patient post-stroke, however, their benefits compared manual exercises have not been done in randomized controlled trial, correlations between joint biomechanical properties are unclear. Objective: To compare effects...

Abstract Applying sensors in biomedical institutions and home‐based stroke rehabilitation is now a global research focus. In this review paper, the relationship between diseases’ physiology mechanism diverse sensors’ functionalities detailed explained. The starts by interpreting how influences motion abilities then introduces broadly adopted physical training methods. After, working principles of their use to objectively provide patients’ body information for status are discussed. content...

OBJECTIVE: To explore the impact of rehabilitation robot training (RRT) on upper limb motor function and daily activity ability in patients with stroke. METHODS: Forty meeting inclusion criteria were randomly divided into treatment group (TRE) control (CON). Group TRE was trained an CON traditional occupational therapy. The time six weeks, activities then assessed. RESULTS: (1) There no statistical significance Fugl-Meyer (FM) score, Wolf Motor Function Test (WMFT) Modified Barthel Index...

Sensor-based rehabilitation physical training assessment methods have attracted significant attention in refined evaluation scenarios. A method combines the expertise of clinicians with advanced sensor-based technology to capture and analyze subtle movement variations often unobserved by traditional subjective methods. Current approaches center on either body postures or muscle strength, which lack more sophisticated analysis features activation coordination, thereby hindering efficacy deep...