IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"Muscle Spindle Model-Based Non-Invasive Electrical Stimulation for Motion Perception Feedback in Prosthetic Hands.","authors":"Qichuan Ding, Chenyu Tong, Dongxu Liu, Bicen Yan, Fei Wang, Shuai Han","doi":"10.1109/TNSRE.2025.3556726","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3556726","url":null,"abstract":"<p><p>Prosthetic hands offer significant benefits for patients with hand amputations by partially replicating the function of real hands. However, most current prosthetics lack sensory feedback on movement, leading to a gap in proprioception for users. To bridge this gap and approximate the natural experience of hand use, prosthetic hands must offer detailed motion feedback. This paper introduces a non-invasive electrical stimulation approach, which can provide motion perception feedback through modeling muscle spindles. By employing transcutaneous electrical nerve stimulation (TENS), the method generates artificial sensory signals associated with the movement of a prosthetic hand, potentially restoring a degree of proprioception for patients with hand amputations. We developed an experimental framework involving an electronic prosthetic hand, an electrical stimulator, and surface electrodes to assess our approach. Five able-body and three forearm amputees took part in our experiments. The experimental results indicated that the subjects were able to accurately discern the movement angle of the prosthetic hand, and when the sensory feedback was biomimetic, the subjects were able to identify the prosthetic hand movement state better than using a traditional encoding algorithm that only relied on the current stimulation intensity.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143763669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AADNet: Exploring EEG Spatiotemporal Information for Fast and Accurate Orientation and Timbre Detection of Auditory Attention Based on A Cue-Masked Paradigm.","authors":"Keren Shi, Xu Liu, Xue Yuan, Haijie Shang, Ruiting Dai, Hanbin Wang, Yunfa Fu, Ning Jiang, Jiayuan He","doi":"10.1109/TNSRE.2025.3555542","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3555542","url":null,"abstract":"<p><p>Auditory attention decoding from electroencephalogram (EEG) could infer to which source the user is attending in noisy environments. Decoding algorithms and experimental paradigm designs are crucial for the development of technology in practical applications. To simulate real-world scenarios, this study proposed a cue-masked auditory attention paradigm to avoid information leakage before the experiment. To obtain high decoding accuracy with low latency, an end-to-end deep learning model, AADNet, was proposed to exploit the spatiotemporal information from the short time window of EEG signals. The results showed that with a 0.5-second EEG window, AADNet achieved an average accuracy of 93.46% and 91.09% in decoding auditory orientation attention (OA) and timbre attention (TA), respectively. It significantly outperformed five previous methods and did not need the knowledge of the original audio source. This work demonstrated that it was possible to detect the orientation and timbre of auditory attention from EEG signals fast and accurately. The results are promising for the real-time multi-property auditory attention decoding, facilitating the application of the neuro-steered hearing aids and other assistive listening devices.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143763668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"StimEMG: an Electromyogram Recording System with Real-time Removal of Time-varying Electrical Stimulation Artifacts.","authors":"Jiashun Zhao, Rui Yuan, Henry Shin, Run Ji, Yang Zheng","doi":"10.1109/TNSRE.2025.3555572","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3555572","url":null,"abstract":"<p><p>A closed-loop Functional Electrical Stimulation (FES) system that incorporates electromyogram (EMG) signal feedback provides more effective assistance to paralytic patients in maintaining and recovering their motor abilities. However, the closed-loop FES system with real-time adjustment of stimulation parameters tends to introduce time-varying stimulation artifacts in EMG signals, challenging the removal of stimulation artifacts that aims at more accurate monitoring of muscle contraction status. Therefore, an EMG acquisition system that embeds a stimulation artifact generation (SAG) circuit and the Recursive Least Squares (RLS) adaptive filter was developed in this study and named StimEMG. The SAG-RLS strategy was tested using the simulated contaminated EMG signals and the StimEMG system was tested in an experimental study with 8 subjects. Both the simulation and the experimental study showed that the SAG-RLS method obtained a higher correlation (R2) between the denoised EMG and the corresponding clean EMG or EMG segments compared with the current Gram-Schmidt-based (GSB) method (simulation study, 0.98±0.0044 v.s. 0.65±0.3217; experimental study, 0.99±0.0024 v.s. 0.52±0.2105). Meanwhile, the SAG-RLS method can suppress stimulation artifact more effectively, resulting a higher signal-to-noise ratio (simulation study: 12.83±2.1745 v.s. 1.54±1.3106) and higher noise rejection ratio (experimental study:2.32±0.7046 v.s. 1.92±0.8014). The significantly improved performance is speculated to result from the ability of the SAG unit to precisely and timely capture the variation of the stimulation artifacts caused by the change of stimulation parameters, unlike previous methods relying on the stability of the characteristic of stimulation artifacts in the contaminated EMG signals. The developed StimEMG system provides a robust EMG acquisition module for the closed-loop FES system.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143763672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An MRI-compatible system for characterizing supraspinal processing of walking-related foot-sole somatosensory stimulation.","authors":"Hao Yue, Bin Shen, Yishu Chen, Yufeng Zhang, Jiaojiao Lu, Shaobo Li, Brad Manor, Weijie Fu, Junhong Zhou","doi":"10.1109/TNSRE.2025.3555852","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3555852","url":null,"abstract":"<p><p>Foot soles are the only part in direct contact with the ground during walking. The mechanoreceptors on foot soles continuously obtain somatosensory information (e.g., ground reaction forces) that is delivered to spinal and supraspinal networks. The timely and accurate supraspinal processing of such information, which can be captured by the activation of the supraspinal regions, is critical to the regulation of walking. However, little is known about supraspinal somatosensory processing related to walking. Characterizing the supraspinal response to walking-related somatosensory inputs using MRI is challenging, because individuals are required to stay motionless during MRI scan. We thus developed a stimulation system that simulates the amplitude and timing of foot-sole pressure changes experienced during each step of overground walking, without inducing significant head motion. In the study to examine its validity and reliability of simulation, seven younger adults completed two trials of eight-meter walking. The temporal changes of foot-sole pressure of each step during walking were recorded using a pressure insole and used to program the motion of the system. The results indicated high validity and reliability of the stimulation (rho=0.94~0.98, p<0.0001). Phantom imaging test revealed that the signal-to-noise ratio of the MR image when the system working was similar to when the system was off, suggesting excellent MRI compatibility. Finally, block-designed test indicated that, compared to rest, multiple supraspinal regions (e.g., postcentral gyrus) were activated (p<0.005) by foot-sole stimulation. This MRI-compatible system provides a novel approach to characterizing the supraspinal sensorimotor control of walking via MRI.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Chronic CNT Fiber Interface with Median Nerve at Acupoint PC6 for Rat's Myocardial Ischemia Control.","authors":"Aotian Yu, Pengwei Li, Junge Yuan, Lei Han, Meng Li, Xiaodan Song, Chang Liu, Qixuan Fu, Simin Ning, Yemao Chai, Yuanyuan Shang, Anyuan Cao, Cunzhi Liu, Wenjing Xu","doi":"10.1109/TNSRE.2025.3555405","DOIUrl":"10.1109/TNSRE.2025.3555405","url":null,"abstract":"<p><p>Myocardial ischemia is one of the most prevalent cardiovascular diseases, underscoring the need for safer and effective therapeutic approaches. Peripheral nerve stimulation, particularly vagus nerve stimulation has emerged as a promising non-pharmaceutical therapy for managing myocardial ischemia. However, vagus nerve stimulation carries risks, such as off-target effects and adverse cardiac events due to its extensive innervation and mixed afferent/efferent fiber composition. Therefore, it is crucial to explore a safer and more user-friendly peripheral nerve interface. In this work, we developed a novel chronic median nerve interface using carbon nanotube fibers as electrodes to stimulate the median nerve at the acupoint PC6 for myocardial ischemia control. Carbon nanotube fibers exhibited excellent bio-compatibility, flexibility, conductivity, and charge storage capacity, making them ideal for reliable and prolonged median nerve stimulation. Our results demonstrated that median nerve stimulation at the acupoint PC6 achieved therapeutic effects comparable to electroacupuncture, including improvement in S-T segment values, LF/HF ratios, cardiac index and cardiac troponin T, while being safer and easier to operate than vagus nerve stimulation. Moreover, median nerve stimulation exhibited superior transient and residual effects compared to electroacupuncture, despite a slower response time. Additionally, histological and fluorescence analyses confirmed the safety of the CNTF-based interface over time. These findings suggested that median nerve stimulation at the acupoint PC6 combined the efficacy of nerve stimulation with the safety of acupuncture, offering a promising approach for myocardial ischemia control, particularly in chronic and repeated treatment scenarios. Further researches are warranted to optimize CNTF properties, elucidate the underlying mechanisms of median nerve stimulation, and explore its potential in clinical applications.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing Linearity in Multi-Joint Upper Limb Dynamics Under Small Perturbations for Reliable Mechanical Impedance Estimation.","authors":"Seongil Hwang, Hyunah Kang, Sang Hoon Kang","doi":"10.1109/TNSRE.2025.3554805","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3554805","url":null,"abstract":"<p><p>This study investigates the linear behavior of multi-joint upper limb dynamics under small perturbations, a prerequisite for stochastic estimation of upper limb mechanical impedance, which is crucial for understanding motor control and has the potential to assess neurological disorders. Conflicting reports exist on the linearity of upper limb dynamics under small perturbations, even for healthy individuals. We hypothesized that the multi-joint upper limb behaves linearly under small perturbations and that uncompensated nonlinear robot joint frictions degrade impedance estimation reliability. The upper limb multi-joint mechanical impedance of ten healthy individuals was estimated using a 2-degree-of-freedom direct-drive robot similar to MIT-MANUS, known for small joint frictions, under two conditions: without (using Cartesian proportional-derivative control) and with (using internal model based impedance control) friction compensation. Multiple and partial coherences were close to unity with friction compensation and significantly higher than without it, confirming that the upper limb behaves linearly under small perturbations and that previously reported nonlinearity detected by low coherences was due to small but significant robot joint frictions. It is expected that confirming the linearity of the upper limb under small perturbations allows for confident upper limb impedance estimation, thereby promoting motor control studies and complementing the diagnosis of the altered upper-limb dynamics post-stroke.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The neural correlates and behavioral impact of peripheral noise electrical stimulation on motor learning.","authors":"Li-Wei Chou, Man-Wai Kou, Hui-Min Lee, Felipe Fregni, Vincent Chen, Chung-Lan Kao","doi":"10.1109/TNSRE.2025.3555203","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3555203","url":null,"abstract":"<p><p>Somatosensory input plays a critical role in motor learning. Noise reduces the neural activation threshold and enhances the sensitivity of sensory neurons. While research has demonstrated that peripheral electrical stimulation with noise waveform improves motor performance and functions, the effects of noise electrical stimulation on motor learning remain unknown. This study aimed to investigate the immediate effects of peripheral noise electrical stimulation on motor learning and corresponding neural activities in the motor cortex. Eighteen healthy adults participated in 2 experimental sessions (i.e., noise and sham electrical stimulation conditions) on 2 separate days. Participants performed a grip force tracking task to follow a 0.5 Hz continuous sine wave with amplitudes of 10, 20, and 30% maximal voluntary isometric contraction while the electroencephalogram (EEG) of the sensorimotor cortex and the electromyography (EMG) of the right finger flexors were recorded. The differences (force error) between the actual and the targeted force were calculated, and motor learning was achieved by reducing the force error to a plateau. The efficiency of motor learning was defined as how fast the force error reached a plateau. Two-way (conditions [noise vs sham stimulation] by time [during vs post]) analysis of variance with repeated measures was used to compare the differences in force error, EEG power spectrum density (PSD), and EEG-EMG (corticomuscular) coherence (CMC). The significance level was set at 0.05. Noise electrical stimulation significantly reduced the force error both during and post motor learning (p < 0.05) and required less time to reach a plateau of force error (p < 0.05); however, for percipients who received sham stimulation first, the effect of noise on learning may not be optimal and thus not represent the net effect of stochastic resonance. For neural activities in the brain, noise electrical stimulation induced an immediate reduction in the EEG beta (15-30 Hz) band and gamma (> 30 Hz) CMC. We also observed that motor learning resulted in a decrease in EEG PSD beta band and gamma CMC. This study demonstrated that noise electrical stimulation during motor learning significantly reduced the time required to learn a motor task. We also identified neurophysiological signatures that associate with motor learning, including desynchronization of EEG beta power and reduced functional connectivity between the brain and muscles. These findings could potentially help develop novel motor training strategies and precision interventions.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the Impact of Training Protocols on Myoelectric Pattern Recognition Control in Upper-Limb Amputees.","authors":"Elaheh Mohammadreza, Vinicius Prado Da Fonseca, Xianta Jiang","doi":"10.1109/TNSRE.2025.3555100","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3555100","url":null,"abstract":"<p><p>Myoelectric control schemes, pivotal in the control of prosthetic limbs, are often developed and evaluated in ideal laboratory conditions. However, these controlled environments may not fully represent the diverse challenges users face in real-world scenarios. The present study aims to tackle some of the existing research limitations by exploring the influence of various model training protocols on myoelectric pattern recognition within a semi-autonomous control system, which has been shown to reduce user cognitive load and enhance overall system performance. Specifically, we focus on the effects of limb movement and weight-bearing activities. We investigate the effect of four distinct training protocols in pattern recognition control for upper-limb prostheses, including training without a prosthetic hand, training with a prosthetic hand and static gestures, training with a prosthetic hand and dynamic movements guided by a graphical user interface (GUI), and training with a prosthetic hand having dynamic transfers and unguided. By examining these conditions, we aim to provide an understanding of how different training protocols and different labeling methods influence myoelectric pattern recognition control. Our results, based on experiments conducted with 14 able-bodied and one amputee participant, suggest that introducing the weight of the prosthetic hand and dynamic movements of the arm to the training data improves the accuracy and robustness of the control scheme. Real-time control experiments with a group of five able-bodied and one amputee participant using a multi-DOF prosthetic hand also verify our findings.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Deep-Learning Empowered, Real-Time Processing Platform of fNIRS/DOT for Brain Computer Interfaces and Neurofeedback","authors":"Yunjia Xia;Jianan Chen;Jinchen Li;Tingchen Gong;Ernesto E. Vidal-Rosas;Rui Loureiro;Robert J. Cooper;Hubin Zhao","doi":"10.1109/TNSRE.2025.3553794","DOIUrl":"10.1109/TNSRE.2025.3553794","url":null,"abstract":"Brain-Computer Interfaces (BCI) and Neurofeedback (NFB) approaches, which both rely on real-time monitoring of brain activity, are increasingly being applied in rehabilitation, assistive technology, neurological diseases and behavioral disorders. Functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) are promising techniques for these applications due to their non-invasiveness, portability, low cost, and relatively high spatial resolution. However, real-time processing of fNIRS/DOT data remains a significant challenge as it requires establishing a baseline of the measurement, simultaneously performing real-time motion artifact (MA) correction across all channels, and (in the case of DOT) addressing the time-consuming process of image reconstruction. This study proposes a real-time processing system for fNIRS/DOT that integrates baseline calibration, denoising autoencoder (DAE) based MA correction model with a sliding window strategy, and a pre-calculated inverse Jacobian matrix to streamline the reconstructed 3D brain hemodynamics. The DAE model was trained on an extensive whole-head high-density DOT (HD-DOT) dataset and tested on separate motor imagery dataset augmented with artificial MA. The system demonstrated the capability to simultaneously process approximately 750 channels in real-time. Our results show that the DAE-based MA correction method outperformed traditional MA correction in terms of mean squared error and correlation to the known MA-free data while maintaining low latency, which is critical for effective BCI and NFB applications. The system’s high-channel, real-time processing capability provides channel-wise oxygenation information and functional 3D imaging, making it well-suited for fNIRS/DOT applications in BCI and NFB, particularly in movement-intensive scenarios such as motor rehabilitation and assistive technology for mobility support.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1220-1230"},"PeriodicalIF":4.8,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143673840","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":"Impact of Generation Rate of Speech Imagery on Neural Activity and BCI Decoding Performance: A fNIRS Study","authors":"Zengzhi Guo;Lisheng Xu;Wenjun Tan;Fei Chen","doi":"10.1109/TNSRE.2025.3552606","DOIUrl":"10.1109/TNSRE.2025.3552606","url":null,"abstract":"Brain-computer interface (BCI) enables stroke patients to actively modulate neural activity, fostering neuroplasticity and thereby accelerating the recovery process. Due to being portable, non-invasive, and safe, functional near-infrared spectroscopy (fNIRS) has become one of the most widely used neuroimaging techniques. Current BCI research primarily focuses on improving the decoding performance. However, a key aspect of stroke rehabilitation lies in inducing stronger cortical activations in the damaged brain areas, thereby accelerating the recovery of brain functions. This study investigated the regulatory mechanism of the generation rate of speech imagery on neural activity and its impact on BCI decoding performance based on fNIRS. As the generation rate increased from 1 word/4 s to 1 word/2 s, and finally to 1 word/1 s, neural activity in speech-related brain regions steadily enhanced. Correspondingly, the accuracy of detecting speech imagery tasks increased from 83.83% to 85.39%, and ultimately showed a significant improvement, reaching 88.28%. Additionally, the differences in neural activities between the “yes” and “no” speech imagery tasks became more pronounced as the generation rate increased, leading to an improvement in classification performance from 62.81% to 65.78%, and ultimately to 67.50%. This study demonstrates that the neural activity level of most speech-related brain regions during speech imagery enhanced as the generation rate increased. Therefore, accelerating the generation rate of speech imagery induces stronger neural activity and more distinct response patterns between different tasks, which holds the potential to facilitate the development of a BCI feedback system with higher neuroplasticity induction and improved decoding performance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1180-1190"},"PeriodicalIF":4.8,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10931033","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657155","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}