IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"A Wearable Brain-Computer Interface With Fewer EEG Channels for Online Motor Imagery Detection","authors":"Zuguang Rao;Junbiao Zhu;Zilin Lu;Rui Zhang;Kendi Li;Zijing Guan;Yuanqing Li","doi":"10.1109/TNSRE.2024.3502135","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3502135","url":null,"abstract":"Motor imagery-based brain-computer interfaces (MI-BCIs) have significant potential for neurorehabilitation and motor recovery. However, most BCI systems employ multi-channel electroencephalogram (EEG) recording devices, during which the pre-experimental preparation and post-experimental hair cleaning are time-consuming and inconvenient for stroke patients, and potentially affect their motivation for rehabilitation training. In this paper, we introduced a wearable MI-BCI system for online MI classification using a wireless headband device with four EEG channels to reduce setup time while enhancing portability. To validate the performance of the system in decoding MI-EEG signals, extensive experiments and comparisons were performed on sixty-six healthy subjects. Specifically, an offline and an online experiment with forty-six subjects were conducted, with the system achieving average offline and online accuracies of 85.21% and 76.54%, respectively. Furthermore, a comparison experiment involving another twenty subjects showed that the online performance of our headband device (77.84%) was comparable to that of a mature commercial Neuroscan device (76.50%). Compared to several existing portable systems, our wearable system achieved superior performance with fewer channels and was validated on a larger number of subjects. These results demonstrated that our wearable BCI system can reduce preparation time, enhance portability, and meet the classification performance requirements for BCI-based rehabilitation intervention, indicating its substantial potential for large-scale clinical applications in enhancing motor recovery of stroke patients.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4143-4154"},"PeriodicalIF":4.8,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10756748","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142736238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FACT-Net: A Frequency Adapter CNN With Temporal-Periodicity Inception for Fast and Accurate MI-EEG Decoding","authors":"Sixiong Ke;Banghua Yang;Yiyang Qin;Fenqi Rong;Jiayang Zhang;Yanyan Zheng","doi":"10.1109/TNSRE.2024.3499998","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3499998","url":null,"abstract":"Motor imagery brain-computer interface (MI-BCI) based on non-invasive electroencephalogram (EEG) signals is a typical paradigm of BCI. However, existing decoding methods face significant challenges in terms of signal decoding accuracy, real-time processing, and deployment. To overcome these challenges, we propose FACT-Net, an innovative deep-learning network for the fast and accurate decoding of MI-EEG signals. FACT-Net incorporates a Frequency Adapter (FA) module designed for processing the frequency features of MI-EEG data, as well as a Temporal-Periodicity Inception (TPI) module specifically for handling global periodic signals in MI. To evaluate the proposed model, we conduct the experiments on the cross-day dataset collected from 67 subjects and the BCIC-IV-2a dataset. The FACT-Net achieved an accuracy of 48.32% and 80.67% higher than the state-of-the-art (SOTA) approaches, demonstrating excellent performance in MI decoding. Additionally, it exhibits exceptional memory efficiency and inference time, indicating significant potential for practical applications. We anticipate that FACT-Net will set a new baseline for MI-EEG decoding. The code is available in \u0000<uri>https://github.com/Ktn1ga/EEG_FACT</uri>\u0000.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4131-4142"},"PeriodicalIF":4.8,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10755982","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142736239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Intensity Focused Ultrasound Stimulation on Fingertip Can Evoke Fine Tactile Sensations and Different Local Hemodynamic Responses","authors":"Liuni Qin;Mingyang Dou;Lili Niu;Laixin Huang;Fei Li;Shichun Bao;Xinping Deng;Guanglin Li;Yanjuan Geng","doi":"10.1109/TNSRE.2024.3493925","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3493925","url":null,"abstract":"Low-intensity focused ultrasound stimulation (LIFUS) has been proved effective in eliciting vibrotactile in addition to warm, cold and nociceptive pain when applied to human peripheral endings. However, if it can evoke fine tactile sensations has been rarely investigated by far despite the importance of fine tactile feedback in motor control. To explore this issue, 14 healthy volunteers were recruited in this study. A psychophysical experiment was firstly conducted to determine the appropriate range of pulse repetition frequency (PRF) and acoustic intensity (AI). Then, participants were asked to perceive and discriminate different tactile stimulations under LIFUS, so as to evaluate if multiple fine tactile sensations could be reliably elicited by modulating the PRF and AI. For objective assessment, the local blood perfusion volume (BPV) response beneath stimulated fingertip was recorded and characterized. Our results showed that four types of tactile sensations, including tapping, vibrating, electrical, and pressure could be reliably elicited by modulating the PRF and AI within a specific range, and there was a significant impact of PRF and AI on both participants’ tactile discrimination and amplitude features of BPV response. This study would facilitate the application of LIFUS to some human-machine interaction scenarios, and shed valuable insights on the physiological mechanisms of peripherally applied ultrasound stimulation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4086-4097"},"PeriodicalIF":4.8,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10755139","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semi-Autonomous Continuous Robotic Arm Control Using an Augmented Reality Brain-Computer Interface","authors":"Kirill Kokorin;Syeda R. Zehra;Jing Mu;Peter Yoo;David B. Grayden;Sam E. John","doi":"10.1109/TNSRE.2024.3500217","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3500217","url":null,"abstract":"Noninvasive augmented-reality (AR) brain-computer interfaces (BCIs) that use steady-state visually evoked potentials (SSVEPs) typically adopt a fully-autonomous goal-selection framework to control a robot, where automation is used to compensate for the low information transfer rate of the BCI. This scheme improves task performance but users may prefer direct control (DC) of robot motion. To provide users with a balance of autonomous assistance and manual control, we developed a shared control (SC) system for continuous control of robot translation using an SSVEP AR-BCI, which we tested in a 3D reaching task. The SC system used the BCI input and robot sensor data to continuously predict which object the user wanted to reach, generated an assistance signal, and regulated the level of assistance based on prediction confidence. Eighteen healthy participants took part in our study and each completed 24 reaching trials using DC and SC. Compared to DC, SC significantly improved (paired two-tailed t-test, Holm-corrected \u0000<inline-formula> <tex-math>$alpha lt 0.05$ </tex-math></inline-formula>\u0000) mean task success rate (\u0000<inline-formula> <tex-math>${p} lt 0.0001$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$mu =36.1$ </tex-math></inline-formula>\u0000%, 95% CI [25.3%, 46.9%]), normalised reaching trajectory length (\u0000<inline-formula> <tex-math>${p} lt 0.0001$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$mu = -26.8$ </tex-math></inline-formula>\u0000%, 95% CI [−36.0%, −17.7%]), and participant workload (\u0000<inline-formula> <tex-math>${p} =0.02$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$mu = -11.6$ </tex-math></inline-formula>\u0000, 95% CI [−21.1, −2.0]) measured with the NASA Task Load Index. Therefore, users of SC can control the robot effectively, while experiencing increased agency. Our system can personalise assistive technology by providing users with the ability to select their preferred level of autonomous assistance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4098-4108"},"PeriodicalIF":4.8,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10755142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing Knee Joint Loads During Stance Phase With a Rigid-Soft Hybrid Exoskeleton","authors":"Xiaolin Dai;Zhihao Zhou;Zilu Wang;Lecheng Ruan;Rongli Wang;Xuewen Rong;Yibin Li;Qining Wang","doi":"10.1109/TNSRE.2024.3498044","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3498044","url":null,"abstract":"High mechanical loads generated during walking may accelerate the wear of the knee joint. General knee exoskeletons mainly reduce knee joint load by applying pure torque assistance to reduce the force required by knee extensor muscles. This study aims to further reduce the knee joint load during the early and middle stance phases through a gait intervention strategy that combines torque assistance and vertical force assistance. Comprehensive experiments were conducted to verify the gait intervention strategy in reducing the knee joint load. The results demonstrated that the strategy significantly reduced the maximum and mean knee joint force during the early and middle stance phases. Our studies indicated that the strategy may have the potential to reduce the knee joint load from multiple factors, including muscles, ligaments, and the ground reaction force.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4164-4173"},"PeriodicalIF":4.8,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10753083","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142736527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Neural Basis of the Effect of Transcutaneous Auricular Vagus Nerve Stimulation on Emotion Regulation Related Brain Regions: An rs-fMRI Study","authors":"Yujiao Zhang;Pan Lin;Ruimin Wang;Jiang Zhou;Xiaoquan Xu;Jianwei Wang;Sheng Ge","doi":"10.1109/TNSRE.2024.3497893","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3497893","url":null,"abstract":"Transcutaneous auricular vagus nerve stimulation (taVNS) is a promising neurostimulation approach for emotion regulation. This research aimed to clarify the underlying neural basis responsible for taVNS’s impact on emotional regulation related brain regions. Thirty-two healthy volunteers were allocated into a taVNS group, which received electrical stimulation at the concha area of the ear, and a sham group, which received earlobe stimulation. Resting-state functional magnetic resonance imaging data were collected from both the taVNS and sham groups pre- and post-stimulation. To evaluate the alterations in neural activity and connectivity resulting from auricular electrical stimulation, degree centrality and functional connectivity analyses were used. The results indicated that taVNS modulated the neural activity of several brain regions, including the bilateral precuneus, temporal gyrus, precentral gyrus, and postcentral gyrus, whereas earlobe stimulation did not produce such effects. taVNS may improve emotion regulation by modulating neural activation and functional connectivity in key brain regions, then facilitating the integration of emotional responses, memories, and experiences. Thus, these brain regions may serve as potential therapeutic targets for taVNS in treating disorders associated with emotional dysregulation. These findings provide insight into the neural basis through which taVNS influences emotion regulation and hold potential for the development of neuromodulation-based therapeutic strategies for emotional disorders.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4076-4085"},"PeriodicalIF":4.8,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10752590","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Asynchronous Training-Free SSVEP-BCI Detection Algorithm for Non-Equal Prior Probability Scenarios","authors":"Junsong Wang;Yuntian Cui;Hongxin Zhang;Haolin Wu;Chen Yang","doi":"10.1109/TNSRE.2024.3496727","DOIUrl":"10.1109/TNSRE.2024.3496727","url":null,"abstract":"SSVEP-based brain-computer interface (BCI) systems have received a lot of attention due to their relatively high Signal to Noise Ratio (SNR) and less training requirements. Most of the existing steady-state visual evoked potential (SSVEP) detection algorithms treat the prior probability of each alternative target being selected as equal. In this study, the prior probability distribution of alternative targets was introduced into the SSVEP recognition algorithm, and an asynchronous training-free SSVEP-BCI detection algorithm for non-equal prior probability scenarios was proposed. This algorithm is based on the Spatio-temporal equalization multi-window technique (STE-MW) and introduces the Maximum A Posteriori criterion (MAP), which makes full use of prior information to improve the performance of the asynchronous training-free BCI system. In addition, we proposed a mutual information-based performance evaluation metric called Mutual information rate (MIR) specifically for non-equal prior probability scenarios. This evaluation framework is designed to provide a more accurate estimation of the information transmission performance of BCI systems in such scenarios. A 10-target simulated vehicle control offline experiment involving 17 subjects showed that the proposed method improved the average MIR by 6.48%. Online free control experiments involving 12 subjects showed that the proposed method improved the average MIR by 14.93%, and significantly reduced the average instruction time. The proposed algorithm is more suitable for practical engineering application scenarios that are asynchronous and training-free; the extremely high accuracy is guaranteed while maintaining a low false alarm rate, which can be applied to asynchronous BCI systems that require high stability.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4120-4130"},"PeriodicalIF":4.8,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10750850","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142619341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dyslexia Analysis and Diagnosis Based on Eye Movement","authors":"R. Vaitheeshwari;Chih-Hsuan Chen;Chia-Ru Chung;Hsuan-Yu Yang;Shih-Ching Yeh;Eric Hsiao-Kuang Wu;Mukul Kumar","doi":"10.1109/TNSRE.2024.3496087","DOIUrl":"10.1109/TNSRE.2024.3496087","url":null,"abstract":"Dyslexia is a complex reading disorder characterized by difficulties in accurate or fluent word recognition, poor spelling, and decoding abilities. These challenges are not due to intellectual, visual, or auditory deficits. The diagnosis of dyslexia is further complicated by symptom variability, influenced by cultural and personal factors. This study leverages Virtual Reality (VR) advancements, eye movement tracking, and machine learning to create a virtual reading environment that captures eye movement data. This data extracts features such as eye movement metrics, word vectors, and saliency maps. We introduce a novel fusion model that integrates various machine learning algorithms to objectively and automatically assess dyslexia using physiological data derived from user interactions. Our findings suggest that this model significantly enhances the accuracy and efficiency of dyslexia diagnosis, marking an important advancement in educational technology and providing robust support for individuals with dyslexia. Although the sample size was limited to 10 dyslexic and 4 control participants, the results offer valuable insights and lay the groundwork for future studies with larger cohorts.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4109-4119"},"PeriodicalIF":4.8,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10750264","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142619343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Gluteus-Specific Muscle Synergy Recruited During the First Recovery Step Following a Backward Pitch Perturbation","authors":"Huijie Lin;Xiping Ren;Christoph Lutter;Haidan Liang;Fengxue Qi;Qining Yang;Maeruan Kebbach;Martin Schlegel;Sven Bruhn;Rainer Bader;Thomas Tischer","doi":"10.1109/TNSRE.2024.3495514","DOIUrl":"10.1109/TNSRE.2024.3495514","url":null,"abstract":"The central nervous system momentarily activates a set of specific muscle synergies to maintain balance when external mechanical perturbations induce walking instability, which is critically involved in preventing falls. The activation patterns and composition of the muscle synergies recruited in the perturbed leg have not been fully characterized, and even less so for the recovery step. Here, we addressed this research gap by measuring the surface electromyographic data of the relevant muscles during a backward-pitched perturbed walk, and then extracting muscle synergy-related parameters using a non-negative matrix factorization algorithm. Our findings indicated that 1) a common set of four muscle synergies was activated in normal, perturbated and first recovery steps; 2) a specific muscle synergy controlled hip movement was recruited in the first recovery step; and 3) the main temporal activation phases of several muscle synergies were prolonged in the perturbed or the first recovery step. These results emphasize the potential significance of exploring the neurological control strategies of muscle synergy in fall prevention.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4033-4041"},"PeriodicalIF":4.8,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10749836","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142619339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Swing-Assist Controller for Enhancing Knee Flexion in a Semi-Powered Transfemoral Prosthesis","authors":"David M. Marsh;Marco Puliti;Michael Goldfarb","doi":"10.1109/TNSRE.2024.3495517","DOIUrl":"10.1109/TNSRE.2024.3495517","url":null,"abstract":"This work proposes a new swing controller for semi-powered low impedance transfemoral prostheses that resolves the issue of potentially competing inputs between artificial assistive power and user-sourced power. Rather than add power as an exogeneous input, the control approach uses power to modify the homogeneous portion of the shank dynamics, and therefore need not construct or curate an input that is coordinated with user input. The implemented controller requires a single control parameter at a given walking speed, where the value of that parameter is a function of walking speed, as determined by an adaptive algorithm, such that peak knee angles are commensurate with walking-speed-dependent behaviors of individuals without any negative gait pathologies. The controller and parameter selection algorithm are described in the paper, and subsequently validated in walking experiments with three participants with unilateral transfemoral amputation. The experiments demonstrate that the proposed controller increases peak knee angle and minimum toe clearance during swing phase without increasing hip compensatory actions, relative to the users’ daily-use devices.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4052-4062"},"PeriodicalIF":4.8,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10749997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142619242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}