Objective. Recent studies have reported that the classification performance of electromyographic (EMG) signals degrades over time without proper retraining. This problem is relevant for applications EMG pattern recognition in control active prostheses. Approach. In this study we investigated changes 11 consecutive days eight able-bodied subjects and two amputees. Main results. It was observed that, when classifier trained on data from one day tested following day, error decreased...

To improve the efficacy of robotic exoskeleton-based rehabilitation training, active joint torque subjects should be detected. This paper presents a practical and adaptive method to estimate using electromyography (EMG) signals for custom lower limb exoskeleton with two degrees freedom (DOFs). estimator, constructed radial basis function neural networks (RBFNNs), was used form an extended Slotine-Li controller. controller eliminated need calibration EMG-torque model. The control estimation...

Restoring the interaction between disabled people and 3-D physical world via a brain-computer interface (BCI) is an exciting topic. To this end, we designed wearable BCI system based on steady-state visual evoked potential (SSVEP), which enables navigation of quadcopter flight with immersive first-person feedback using head-mounted device. In addition, to alleviate user's operational burden, paper provides asynchronous switch control for users. The transitional state due head movement in was...

Variations in muscle contraction effort have a substantial impact on performance of pattern recognition based myoelectric control. Though incorporating changes into training phase could decrease the effect, time would be increased and clinical viability limited. The modulation force relies coordination multiple muscles, which provides possibility to classify motions with different forces without adding extra samples. This study explores property frequency domain found that orientation...

Abstract Background The nonstationary property of electromyography (EMG) signals usually makes the pattern recognition (PR) based methods ineffective after some time in practical application for multinational prosthesis. conventional EMG PR, which is accomplished two separate steps: training and testing, ignores mismatch between testing conditions often discards useful information dataset. Method This paper presents a novel self-enhancing approach to improve classification performance (PR)....

Most prosthetic myoelectric control studies have concentrated on low density (less than 16 electrodes, LD) electromyography (EMG) signals, due to its better clinical applicability and computation complexity compared with high (more HD) EMG signals. Since HD electrodes been developed more conveniently wear respect the previous versions recently, signals become an alternative for prostheses. The electrode shift, which may occur during repositioning or donning/doffing of socket, is one main...

Robotic exoskeletons for physical rehabilitation have been utilized retraining patients suffering from paraplegia and enhancing motor recovery in recent years. However, users are not voluntarily involved most systems. This paper aims to develop a locomotion trainer with multiple gait patterns, which can be controlled by the active motion intention of users. A multimodal human-robot interaction (HRI) system is established enhance subject's participation during rehabilitation, includes...

A hybrid modality brain-computer interface (BCI) is proposed in this paper, which combines motor imagery with selective sensation to enhance the discrimination between left and right mental tasks, e.g., classification left/ stimulation right/ imagery. In paradigm, wearable vibrotactile rings are used stimulate both skin on wrists. Subjects required perform tasks according randomly presented cues (i.e., hand imagery, or sensation). Two-way ANOVA statistical analysis showed a significant group...

Control scheme design based on surface electromyography (sEMG) pattern recognition has been the focus of much research a myoelectric prosthesis (MP) technology. Due to inherent nonstationarity in sEMG signals, systems may need be recalibrated day after daily use applications; thereby, hindering MP usability. In order reduce recalibration time subsequent days following initial training, we propose domain adaptation (DA) framework, which automatically reuses models trained earlier as input for...

An all-chain-wireless brain-to-brain system (BTBS), which enabled motion control of a cyborg cockroach via human brain, was developed in this work. Steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) used for recognizing intention and an optimization algorithm proposed SSVEP to improve online performance the BCI. The by surgically integrating portable microstimulator that could generate invasive electrical nerve stimulation. Through Bluetooth communication,...

Motor imagery (MI) based brain-computer interface (BCI) has been developed as an alternative therapy for stroke rehabilitation. However, experimental evidence demonstrates that a significant portion (10-50%) of subjects are BCI-inefficient users (accuracy less than 70%). Thus, predicting BCI performance prior to clinical usage would facilitate the selection suitable end-users and improve efficiency In current study, we proposed two physiological variables, i.e., laterality index (LI)...

It is evident that the dominant therapy of functional electrical stimulation (FES) for stroke rehabilitation suffers from heavy dependency on therapists experience and lack feedback patients' status, which decrease voluntary participation, reducing efficacy. This paper proposes a closed loop FES system using surface electromyography (sEMG) bias bilateral arms enhancing upper-limb rehabilitation. wireless portable consists sEMG data acquisition modules, former used to measure analyze...

Objective.The electroencephalography (EEG)-based brain-computer interfaces (BCIs) have been used in the control of robotic arms. The performance non-invasive BCIs may not be satisfactory due to poor quality EEG signals, so shared strategies were tried as an alternative solution. However, most existing methods set arbitration rules manually, which highly depended on specific tasks and developer's experience. In this study, we proposed a novel model that automatically optimized commands...

Powered intelligent lower limb prostheses have been gaining interest as they provide functionality for walking on different terrains. This study proposes a hierarchical planner based sensor fusion and central pattern generator (CPG). Electromyographic (EMG) inertial measurement unit (IMU) signals were recorded fused in the feature decision levels. The high-level consists of cascade classifiers with gait phase dependence. A secondary classifier each stand swing was developed to recognize five...

Brain-computer interfaces (BCIs) are technologies that bypass damaged or disrupted neural pathways and directly decode brain signals to perform intended actions. BCIs for speech have the potential restore communication by decoding directly. Many studies demonstrated promising results using invasive micro-electrode arrays electrocorticography. However, use of stereo-electroencephalography (sEEG) has not been fully recognized.

When spacecraft execute missions in space, their solar panels—crucial components—often need to be folded, unfolded, and adjusted at an angle. These operations can induce numerous detrimental nonlinear vibrations. This paper addresses the issues of thermal-coupled vibration control within context space-based flexible panel systems. Utilizing piezoelectric smart hybrid technology, this study focuses on a plate augmented with active constrained layer damping. The panel, under thermal field...