Traditional rehabilitation strategies become difficult in the chronic phase stage of stroke prognosis. Brain-computer interface (BCI) combined with external devices may improve motor function patients, but it lacks comprehensive assessments neurological changes regarding functional rehabilitation. This study aimed to comprehensively and quantitatively investigate brain activity induced by BCI-FES training patients stroke. We analyzed EEG two groups stroke, one group received electrical...

Abstract Objective . Multi-channel electroencephalogram (EEG) technology in brain–computer interface (BCI) research offers the advantage of enhanced spatial resolution and system performance. However, this also implies that more time is needed data processing stage, which not conducive to rapid response BCI. Hence, it a necessary challenging task reduce number EEG channels while maintaining decoding effectiveness. Approach In paper, we propose local optimization method based on Fisher score...

Fatigue is believed to be the leading factor for traffic accidents (e.g., fatigue driving) and health problems heart disease diabetes). However, fatigue-related risks are difficult quantify because there no efficient reliable detection method comparable blood alcohol testing drunk drivers. Conventional methods either require wiring of sensors EEG ECG) that inconvenient or leverage video camera systems lighting sensitive may leak privacy. We present Ubi-Fatigue, a comfortable contactless...

Abstract Objective. Denoising artifacts, such as noise from muscle or cardiac activity, is a crucial and ubiquitous concern in neurophysiological signal processing, particularly for enhancing the signal-to-noise ratio electroencephalograph (EEG) analysis. Novel methods based on deep learning demonstrate notably prominent effect compared to traditional denoising approaches. However, those still suffer certain limitations. Some often neglect multi-domain characteristics of artifact signal....

Asthma is a common respiratory disease in modern society. However, people are rarely aware of the symptoms asthma because early stage similar to that cold (e.g., wheeze, cough, and shortness breath). To tackle this challenge, we propose an detection system, Ubi-Asthma, based on smartwatch. Ubi-Asthma combines breathing signals guttural sound cough throat-clearing sound) realize passive accurate without interrupting user. Not only can extract from user even if walking but also recognize when...

Wrist exoskeletons are increasingly being used in the rehabilitation of stroke and hand dysfunction because its ability to assist patients high intensity, repetitive, targeted interactive training. However, existing wrist cannot effectively replace work therapist improve function, mainly perform natural movement covering entire physiological motor space (PMS). Here, we present a bioelectronic controlled hybrid serial-parallel exoskeleton HrWr-ExoSkeleton (HrWE) which is based on PMS design...

EEG is widely applied in motor imagery because of its non-invasive and easy access. However, multi-channel signals cause noise interference redundant information. Channel selection can reduce the noisy signal to obtain more real signals. Therefore, many studies focus on influence channel algorithms motion decoding. This paper summarizes characteristics methods for decoding imagination tasks compares their results. One way select based neural network takes as input parameter network; Another...

Abstract Objective. The brain-computer interface (BCI) system based on sensorimotor rhythm can convert the human spirit into instructions for machine control, and it is a new human-computer interaction with broad applications. However, spatial resolution of scalp electroencephalogram (EEG) limited due to presence volume conduction effects. Therefore, very meaningful explore intracranial activities in noninvasive way improve EEG. Meanwhile, low-delay decoding an essential factor development...

Blood pressure (BP) is an essential vital sign related to many severe diseases, such as heart failure, kidney failure. Frequent BP detection can provide doctors more information treat the disease. However, conventional at-home devices require completely blocking blood flow, which lead discomfort and disruption of normal activity when users want perform frequent assessments. So a convenient solution should reduce trouble detecting in daily life. In this work, we have designed evaluated...

This article presented an experiment to determine the effect of dynamic 3D vision-evoked modules on performance system we designed steer a four-rotor unmanned aerial vehicle (UAV). Nowadays, UAV is widely used in various industries, and control has always been focus research. The Brain-Computer Interface (BCI) was based well-known steady-state visually evoked potentials (SSVEP). specificity interface integration paradigms virtual reality. In order achieve more immersive interactive scene, VR...

Steady-state visual evoked potential (SSVEP) is one of the main paradigms brain-computer interface (BCI). However, acquisition method SSVEP can cause subject fatigue and discomfort, leading to insufficiency databases. Inspired by generative determinantal point process (GDPP), we utilize in adversarial network (GAN) generate signals. We investigate ability synthesize signals from Benchmark dataset. further use some evaluation metrics verify its validity. Results prove that usage this...

The invasive brain-computer interface uses large-scale sampling to directly record intracranial electrophysiology by implanting electrode arrays into the brain. It is widely used treat mental illnesses such as epilepsy, Alzheimer's disease, and stroke. In recent years, there has been an increase in research on analyzing SEEG signals obtaining brain illness. Commonly analysis methods include quantifying high-frequency oscillations or functional connectivity changes. This article reviewed main...

Event-related potentials (ERP) are brain-evoked that reflect the neural activity of brain. However, it is difficult to isolate ERP components our interest because single-trial EEG disturbed by other signals, and average analysis in turn loses information. In this paper, we used electrophysiological source imaging (ESI) analyze N170 component triggered face stimulation. The results show ESI feasible for there left-right differences area fusiform gyrus associated with stimulation Clinical...

The simulation of two basic equivalent circuit models the implantable neural interface is described in this paper. simulated circuits are created based on physicochemical mechanism charge transfer surface interface. Each parameter model was varied to investigate regular pattern individual element affecting performance In paper, one process, and another mixed diffusion process. split into parts. device part, rest that part. electrochemical impedance data acquired firstly by simulating with...

Facial stimulation can produce specific event-related potential (ERP) component N170 in the fusiform gyrus region. However, role of region facial preference tasks is not clear at present, and current research analysis based on EEG signals mostly carried out scalp domain. This paper explores whether involved processing face emotions terms distribution energy over source domain, finds that pars orbitalis cortex most energetically active task there are significant differences between left right...

The presence of artifacts seriously affects the readability EEG signals, and manual labeling is very time-consuming. So this study aims to design a new automatic artifact removal algorithm, get appropriate threshold identify neuron activity components by calculating permutation entropy kurtosis each component after Independent Component Analysis (ICA). Then, use wavelet denoising technology retain neuronal in avoid losing useful information denoising. In addition, existence volume conduction...

Brain-computer interface (BCI) system based on sensorimotor rhythm (SMR) is a more natural brain-computer interaction system. In this paper, we propose new multi-task motor imagery EEG (MI-EEG) classification framework. Unlike traditional decoding algorithms, perform the task in source domain rather than sensor domain. proposed algorithm, first build conduction model of signal using public ICBM152 head and boundary element method (BEM). The was then mapped to selected cortex region...

Graph neural networks (GNN) have been applied in EEG signal analysis. However, it is not clear how to describe the connection relationships between electrodes, and a reasonable representation of adjacency matrix cannot be neglected for study GNN based on signals. In this paper, we use brain functional connectivity analyze face preferences humanoid robot explore feasibility using obtained measurements as matrix. The results show that feasible an average accuracy 73.47 <sup...

Gesture recognition based on surface electromyography (sEMG) is a popular topic in teleoperation field, which has the characteristics of convenience, maneuverability, flexibility and adaptability. With continuous development deep learning technology, variety accuracy gesture are constantly improving. In our previous research, new neural network graph convolutional temporal (STCN-GR) was proposed achieved good results task. this paper, we develop teleoperated manipulator control system...

To develop a manipulator system based on spontaneous EEG signal control, this paper proposes common spatial pattern method combined with the Bhattacharyya distance of time-frequency (TB-CSP) for feature extraction. Firstly, different subjects, original is divided by specific time window and frequency band; Secondly, average bands in calculated to select optimal input it CSP extraction; Finally, extracted features are into SVM LDA classify complete control manipulator. The proposed achieves...