Pub Date : 2025-01-28DOI: 10.1109/TNSRE.2025.3535639
Ruikai Cao;Yixuan Sheng;Anqin Dong;Honghai Liu
It is evident that voluntary effort plays a crucial role in electrical stimulation rehabilitation, facilitating neuroplasticity enhancement in patients with neurological disorders. In this paper, we present a multichannel system designed for simultaneous functional electrical stimulation (FES) and volitional EMG (vEMG) acquisition using shared electrodes. The system employs hardware blanking with electrodes shorting to suppress stimulation artifacts and accelerate residual charge dissipation. Additionally, we adapt the Savitzky-Golay filter to extract high-quality, real-time vEMG from FES-contaminated signals, with the optimal filter parameters for different stimulation and blanking periods determined using a genetic algorithm and semi-synthesized signals. Simulation and experimental results confirm that the proposed system ensures robust and high-quality vEMG acquisition, even under varying parameters and across different individuals. In summary, this work advances the development of closed-loop rehabilitation applications and enables further investigation of neuromuscular characteristics under FES.
{"title":"Design of a Savitzky-Golay Filter-Based vEMG-FES System","authors":"Ruikai Cao;Yixuan Sheng;Anqin Dong;Honghai Liu","doi":"10.1109/TNSRE.2025.3535639","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3535639","url":null,"abstract":"It is evident that voluntary effort plays a crucial role in electrical stimulation rehabilitation, facilitating neuroplasticity enhancement in patients with neurological disorders. In this paper, we present a multichannel system designed for simultaneous functional electrical stimulation (FES) and volitional EMG (vEMG) acquisition using shared electrodes. The system employs hardware blanking with electrodes shorting to suppress stimulation artifacts and accelerate residual charge dissipation. Additionally, we adapt the Savitzky-Golay filter to extract high-quality, real-time vEMG from FES-contaminated signals, with the optimal filter parameters for different stimulation and blanking periods determined using a genetic algorithm and semi-synthesized signals. Simulation and experimental results confirm that the proposed system ensures robust and high-quality vEMG acquisition, even under varying parameters and across different individuals. In summary, this work advances the development of closed-loop rehabilitation applications and enables further investigation of neuromuscular characteristics under FES.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"610-619"},"PeriodicalIF":4.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10856274","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361095","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}
Pub Date : 2025-01-28DOI: 10.1109/TNSRE.2025.3535681
Junxiang Zheng;Bing Jiang;Saurabh Biswas;Su Young Lee;Erin Ealba Bumann;Teresa E. Lever;Jeonghee Kim;Hangue Park
Mastication plays an important role in effective food digestion and nutrient absorption. Therefore, regulating masticatory force in people with declining mastication function is significant for maintaining health and quality of life. In this study, we tested the effect of tactile augmentation on mastication force. To augment tactile feedback during mastication, we applied closed-loop electrical stimulation onto the mandibular vestibule using an intraoral tooth-borne electronic system. We hypothesized that closed-loop electrical stimulation, timed with mastication and applied to the nerves delivering tactile feedback to the brain, would evoke an increase in masticatory force. Experiments were completed using the intraoral system with six healthy human subjects who masticated soft and hard foods with and without stimulation during the experiment. Their mastication forces were recorded ten times per condition. The recorded mastication force profile showed that mastication force was higher with the harder food. Also, mastication force increased when electrical stimulation was applied, compared to the non-stimulated condition. These results support the hypothesis that tactile augmentation by intraoral closed-loop electrical stimulation will increase masticatory force. Other mastication parameters including period, spike width, and duty cycle are also changed by electrical stimulation. Further, stimulation left a strong aftereffect on these mastication parameters.
{"title":"Alteration of Mastication Force via Intraoral Closed-Loop Electrical Stimulation","authors":"Junxiang Zheng;Bing Jiang;Saurabh Biswas;Su Young Lee;Erin Ealba Bumann;Teresa E. Lever;Jeonghee Kim;Hangue Park","doi":"10.1109/TNSRE.2025.3535681","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3535681","url":null,"abstract":"Mastication plays an important role in effective food digestion and nutrient absorption. Therefore, regulating masticatory force in people with declining mastication function is significant for maintaining health and quality of life. In this study, we tested the effect of tactile augmentation on mastication force. To augment tactile feedback during mastication, we applied closed-loop electrical stimulation onto the mandibular vestibule using an intraoral tooth-borne electronic system. We hypothesized that closed-loop electrical stimulation, timed with mastication and applied to the nerves delivering tactile feedback to the brain, would evoke an increase in masticatory force. Experiments were completed using the intraoral system with six healthy human subjects who masticated soft and hard foods with and without stimulation during the experiment. Their mastication forces were recorded ten times per condition. The recorded mastication force profile showed that mastication force was higher with the harder food. Also, mastication force increased when electrical stimulation was applied, compared to the non-stimulated condition. These results support the hypothesis that tactile augmentation by intraoral closed-loop electrical stimulation will increase masticatory force. Other mastication parameters including period, spike width, and duty cycle are also changed by electrical stimulation. Further, stimulation left a strong aftereffect on these mastication parameters.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"675-686"},"PeriodicalIF":4.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10856227","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361197","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}
Pub Date : 2025-01-24DOI: 10.1109/TNSRE.2025.3534096
Johnnidel Tabucol;Vera G. M. Kooiman;Marco Leopaldi;Ruud Leijendekkers;Giacomo Selleri;Marcello Mellini;Nico Verdonschot;Magnús Oddsson;Raffaella Carloni;Andrea Zucchelli;Tommaso M. Brugo
Most commercially available foot prostheses are passive ESR feet, which store and release energy to reduce metabolic costs and improve comfort but cannot adjust to varying walking conditions. In contrast, bionic feet adapt to different tasks but are hindered by high weight, power consumption, and cost. This paper presents MyFlex-$zeta $ , an ESR foot with a variable stiffness system, as a compromise between these two categories. MyFlex-$zeta $ adjusts stiffness by varying the sagittal-plane distance between two key points, altering force interactions within the prosthesis and affecting overall stiffness. Clinical tests with three transfemoral amputees evaluated stiffness variation across two sessions: the first subjective, where participants assessed stiffness settings during different tasks, and the second biomechanical, measuring performance parameters. Two participants selected different stiffness settings for various tasks, while the third, with limited perception of stiffness changes, showed less distinction in outcomes. Greater sagittal-plane rotation and higher energy absorption were observed in most tasks with more compliant settings, although one participant’s results were limited due to selecting close stiffness settings. Overall, these findings suggest MyFlex-$zeta $ offers adaptability and performance improvements over traditional ESR feet. With further actuation and control system development, MyFlex-$zeta $ could mark significant progress in prosthesis technology.
{"title":"The MyFlex-ζ Foot: A Variable Stiffness ESR Ankle-Foot Prosthesis","authors":"Johnnidel Tabucol;Vera G. M. Kooiman;Marco Leopaldi;Ruud Leijendekkers;Giacomo Selleri;Marcello Mellini;Nico Verdonschot;Magnús Oddsson;Raffaella Carloni;Andrea Zucchelli;Tommaso M. Brugo","doi":"10.1109/TNSRE.2025.3534096","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3534096","url":null,"abstract":"Most commercially available foot prostheses are passive ESR feet, which store and release energy to reduce metabolic costs and improve comfort but cannot adjust to varying walking conditions. In contrast, bionic feet adapt to different tasks but are hindered by high weight, power consumption, and cost. This paper presents MyFlex-<inline-formula> <tex-math>$zeta $ </tex-math></inline-formula>, an ESR foot with a variable stiffness system, as a compromise between these two categories. MyFlex-<inline-formula> <tex-math>$zeta $ </tex-math></inline-formula> adjusts stiffness by varying the sagittal-plane distance between two key points, altering force interactions within the prosthesis and affecting overall stiffness. Clinical tests with three transfemoral amputees evaluated stiffness variation across two sessions: the first subjective, where participants assessed stiffness settings during different tasks, and the second biomechanical, measuring performance parameters. Two participants selected different stiffness settings for various tasks, while the third, with limited perception of stiffness changes, showed less distinction in outcomes. Greater sagittal-plane rotation and higher energy absorption were observed in most tasks with more compliant settings, although one participant’s results were limited due to selecting close stiffness settings. Overall, these findings suggest MyFlex-<inline-formula> <tex-math>$zeta $ </tex-math></inline-formula> offers adaptability and performance improvements over traditional ESR feet. With further actuation and control system development, MyFlex-<inline-formula> <tex-math>$zeta $ </tex-math></inline-formula> could mark significant progress in prosthesis technology.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"653-663"},"PeriodicalIF":4.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10852407","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361199","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}
Pub Date : 2025-01-24DOI: 10.1109/TNSRE.2025.3534121
Genchang Peng;Mehrdad Nourani;Jay Harvey
Epilepsy patients with drug-resistant seizures emanating from two or more distinct regions of left and right hemispheres are the primary candidates for neurostimulation treatment. Stereo-electroencephalography (SEEG) is a minimally invasive technique to monitor and evaluate brain activities during seizures before stimulator implantation. This work proposes a seizure network modeling method using SEEG to analyze the functional connectivity of epileptogenic zone during bilateral seizures. Network nodes are selected subset of SEEG contact points, and network edges are directed signal correlations calculated from directed transfer function. Based on signal directionality, four connectivity values are extracted to measure the intra- and inter-activities that are within or between the left and right hemispheres, respectively. Statistical difference between connectivity values is used to quantify the seizure impact of each hemisphere. A subset of network nodes is selected from impactful side as stimulation target candidates. Experimental results are validated on ten patients having different seizure types with bilateral onset. Each seizure type has specific connectivity patterns that show different importance from each brain side. Selection of neurostimulation targets from primary side are consistent with clinicians’ decision. Relationships are found among connectivity differences, seizure types and stimulation outcomes. Using SEEG signals, we can capture specific connectivity differences associated with bilateral seizure networks. Such differences are related with corresponding neurostimulation targets and stimulating outcomes. The proposed work elucidates the difference of network connectivity for bilateral patients, and assists clinicians to choose the stimulation targets and to predict the potential outcomes.
{"title":"SEEG-Based Bilateral Seizure Network Analysis for Neurostimulation Treatment","authors":"Genchang Peng;Mehrdad Nourani;Jay Harvey","doi":"10.1109/TNSRE.2025.3534121","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3534121","url":null,"abstract":"Epilepsy patients with drug-resistant seizures emanating from two or more distinct regions of left and right hemispheres are the primary candidates for neurostimulation treatment. Stereo-electroencephalography (SEEG) is a minimally invasive technique to monitor and evaluate brain activities during seizures before stimulator implantation. This work proposes a seizure network modeling method using SEEG to analyze the functional connectivity of epileptogenic zone during bilateral seizures. Network nodes are selected subset of SEEG contact points, and network edges are directed signal correlations calculated from directed transfer function. Based on signal directionality, four connectivity values are extracted to measure the intra- and inter-activities that are within or between the left and right hemispheres, respectively. Statistical difference between connectivity values is used to quantify the seizure impact of each hemisphere. A subset of network nodes is selected from impactful side as stimulation target candidates. Experimental results are validated on ten patients having different seizure types with bilateral onset. Each seizure type has specific connectivity patterns that show different importance from each brain side. Selection of neurostimulation targets from primary side are consistent with clinicians’ decision. Relationships are found among connectivity differences, seizure types and stimulation outcomes. Using SEEG signals, we can capture specific connectivity differences associated with bilateral seizure networks. Such differences are related with corresponding neurostimulation targets and stimulating outcomes. The proposed work elucidates the difference of network connectivity for bilateral patients, and assists clinicians to choose the stimulation targets and to predict the potential outcomes.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"664-674"},"PeriodicalIF":4.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10852360","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361239","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}
Pub Date : 2025-01-20DOI: 10.1109/TNSRE.2025.3530421
Cheong-Un Kim;Seonghun Park;Chang-Hwan Im
The aim of this study is to develop a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system with enhanced performance in an augmented reality (AR) environment by dynamically adjusting colors of visual stimuli to contrast with the background seen through the transparent display. Our proposed method extracts the average color value from the area surrounding the visual stimulus location. It then calculates the contrast value using the HSV color model and applies this to the stimulus color. In an offline experiment, we determined the optimal visual stimulus presentation strategy by comparing the performances of three different methods for determining the colors of visual stimuli in an AR environment. We then evaluated the feasibility of the proposed strategy through online experiments conducted in both indoor and outdoor conditions. The classification performance of the SSVEP-BCI system in an AR environment based on our proposed stimulus presentation strategy was 95.0% for a window size of 3.5 s in offline experiments performed with 17 participants. This was significantly higher than the performance of the conventional black-and-white color strategy. Additionally, it was confirmed by the online experiments that there was no large performance degradation between indoor and outdoor uses.
本研究旨在开发一种基于稳态视觉诱发电位（SSVEP）的脑机接口（BCI）系统，通过动态调整视觉刺激物的颜色，使其与通过透明显示屏看到的背景形成对比，从而增强增强现实（AR）环境中的性能。我们提出的方法是从视觉刺激位置周围区域提取平均颜色值。然后使用 HSV 色彩模型计算对比度值，并将其应用于刺激物颜色。在离线实验中，我们通过比较在 AR 环境中确定视觉刺激颜色的三种不同方法的性能，确定了最佳视觉刺激呈现策略。然后，我们通过在室内和室外条件下进行的在线实验评估了所提策略的可行性。在有 17 名参与者参加的离线实验中，基于我们提出的刺激呈现策略，SSVEP-BCI 系统在 AR 环境中的分类性能在窗口大小为 3.5 秒时达到了 95.0%。这明显高于传统的黑白颜色策略。此外，在线实验还证实，室内和室外使用时的性能没有大幅下降。
{"title":"Performance Enhancement of an SSVEP-Based Brain–Computer Interface in Augmented Reality Through Adaptive Color Adjustment of Visual Stimuli for Optimal Background Contrast","authors":"Cheong-Un Kim;Seonghun Park;Chang-Hwan Im","doi":"10.1109/TNSRE.2025.3530421","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3530421","url":null,"abstract":"The aim of this study is to develop a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system with enhanced performance in an augmented reality (AR) environment by dynamically adjusting colors of visual stimuli to contrast with the background seen through the transparent display. Our proposed method extracts the average color value from the area surrounding the visual stimulus location. It then calculates the contrast value using the HSV color model and applies this to the stimulus color. In an offline experiment, we determined the optimal visual stimulus presentation strategy by comparing the performances of three different methods for determining the colors of visual stimuli in an AR environment. We then evaluated the feasibility of the proposed strategy through online experiments conducted in both indoor and outdoor conditions. The classification performance of the SSVEP-BCI system in an AR environment based on our proposed stimulus presentation strategy was 95.0% for a window size of 3.5 s in offline experiments performed with 17 participants. This was significantly higher than the performance of the conventional black-and-white color strategy. Additionally, it was confirmed by the online experiments that there was no large performance degradation between indoor and outdoor uses.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"514-521"},"PeriodicalIF":4.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10845833","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184383","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}
Pub Date : 2025-01-20DOI: 10.1109/TNSRE.2025.3531768
Faranak Akbarifar;Sean P. Dukelow;Albert Jin;Parvin Mousavi;Stephen H. Scott
Evaluating neurological impairments post-stroke is essential for assessing treatment efficacy and managing subsequent disabilities. Conventional clinical assessment methods depend largely on clinicians’ visual and physical evaluations, resulting in coarse rating systems that frequently miss subtle impairments or improvements. Interactive robotic devices, like the Kinarm Exoskeleton system, are transforming the assessment of motor impairments by offering precise and objective movement measurements. In this study, we analyzed kinematic data from 337 stroke patients and 368 healthy controls performing three Kinarm tasks. Using deep learning methods, particularly an evidential network, we distinguished impaired participants from healthy controls while generating measures of prediction uncertainty. By retraining the network with the least uncertain samples and refining the test set by excluding the top 10% most uncertain samples, we improved the sensitivity of detecting subtle impairments in minimally impaired stroke patients (those scoring normal on the CMSA) from 0.55 to 0.75. We further extended the model to detect impairments associated with transient ischemic attack (TIA), resulting in an increased detection accuracy from 0.86 to 0.92. The model’s ability to identify subtle motor deficits, even in TIA patients who show no observable symptoms on standard clinical exams, highlights its significant clinical utility. Detecting TIA is critical, as individuals who experience a TIA have a substantially higher risk of recurrent stroke. This work highlights the immense potential of integrating deep learning with uncertainty estimation to enhance the detection of stroke-related impairments, potentially paving the way for personalized post-stroke rehabilitation.
{"title":"Optimizing Stroke Detection Using Evidential Networks and Uncertainty-Based Refinement","authors":"Faranak Akbarifar;Sean P. Dukelow;Albert Jin;Parvin Mousavi;Stephen H. Scott","doi":"10.1109/TNSRE.2025.3531768","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3531768","url":null,"abstract":"Evaluating neurological impairments post-stroke is essential for assessing treatment efficacy and managing subsequent disabilities. Conventional clinical assessment methods depend largely on clinicians’ visual and physical evaluations, resulting in coarse rating systems that frequently miss subtle impairments or improvements. Interactive robotic devices, like the Kinarm Exoskeleton system, are transforming the assessment of motor impairments by offering precise and objective movement measurements. In this study, we analyzed kinematic data from 337 stroke patients and 368 healthy controls performing three Kinarm tasks. Using deep learning methods, particularly an evidential network, we distinguished impaired participants from healthy controls while generating measures of prediction uncertainty. By retraining the network with the least uncertain samples and refining the test set by excluding the top 10% most uncertain samples, we improved the sensitivity of detecting subtle impairments in minimally impaired stroke patients (those scoring normal on the CMSA) from 0.55 to 0.75. We further extended the model to detect impairments associated with transient ischemic attack (TIA), resulting in an increased detection accuracy from 0.86 to 0.92. The model’s ability to identify subtle motor deficits, even in TIA patients who show no observable symptoms on standard clinical exams, highlights its significant clinical utility. Detecting TIA is critical, as individuals who experience a TIA have a substantially higher risk of recurrent stroke. This work highlights the immense potential of integrating deep learning with uncertainty estimation to enhance the detection of stroke-related impairments, potentially paving the way for personalized post-stroke rehabilitation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"566-576"},"PeriodicalIF":4.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10845886","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361092","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}
The interface friction between prosthetic socket and residual limb tends to cause skin injury and pain. The frictional pain was systematically studied based on skin tribological behaviors and brain activation. The results showed that the skin frictional pain was affected by the combination of friction and mechanical properties of anatomic regions and liner materials. The low elastic modulus and good viscoelasticity of anatomic regions or high adhesion and good compliance of liner materials both can increase the frictional pain threshold and decease the injury. The main brain activation related to frictional pain located in the primary somatosensory cortex (SI), secondary somatosensory cortex (SII), and prefrontal cortex (PFC). The brain negative activation increased and the activation area decreased with the increased pain intensity. The features of $alpha $ activity, $beta $ activity, and $alpha _{text {peak}}$ extracted from EEG signals were effective in the recognition of pain state, but cannot recognize the pain intensities.
{"title":"Friction-Induced Pain: From Skin Surface to Brain Activation","authors":"Xingxing Fang;Wei Tang;Shousheng Zhang;Yanze Wu;Yifeng Zeng;Yangyang Xia;Ming Zhang","doi":"10.1109/TNSRE.2025.3532293","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3532293","url":null,"abstract":"The interface friction between prosthetic socket and residual limb tends to cause skin injury and pain. The frictional pain was systematically studied based on skin tribological behaviors and brain activation. The results showed that the skin frictional pain was affected by the combination of friction and mechanical properties of anatomic regions and liner materials. The low elastic modulus and good viscoelasticity of anatomic regions or high adhesion and good compliance of liner materials both can increase the frictional pain threshold and decease the injury. The main brain activation related to frictional pain located in the primary somatosensory cortex (SI), secondary somatosensory cortex (SII), and prefrontal cortex (PFC). The brain negative activation increased and the activation area decreased with the increased pain intensity. The features of <inline-formula> <tex-math>$alpha $ </tex-math></inline-formula> activity, <inline-formula> <tex-math>$beta $ </tex-math></inline-formula> activity, and <inline-formula> <tex-math>$alpha _{text {peak}}$ </tex-math></inline-formula> extracted from EEG signals were effective in the recognition of pain state, but cannot recognize the pain intensities.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"532-541"},"PeriodicalIF":4.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10848202","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184381","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}
Pub Date : 2025-01-17DOI: 10.1109/TNSRE.2025.3530992
Shuhao Ma;Yu Cao;Ian D. Robertson;Chaoyang Shi;Jindong Liu;Zhi-Qiang Zhang
Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework.
{"title":"Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics","authors":"Shuhao Ma;Yu Cao;Ian D. Robertson;Chaoyang Shi;Jindong Liu;Zhi-Qiang Zhang","doi":"10.1109/TNSRE.2025.3530992","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3530992","url":null,"abstract":"Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"522-531"},"PeriodicalIF":4.8,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10844911","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184384","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}
Pub Date : 2025-01-17DOI: 10.1109/TNSRE.2025.3531054
Agnese Grison;Jaime Ibáñez Pereda;Dario Farina
Recordings of electrical activity from muscles allow us to identify the activity of pools of spinal motor neurons that send the neural drive for muscle activation. Decoding motor unit and motor neuron activity from muscle recordings can be performed by high-density (HD) electrode systems, both non-invasively (surface, HD-sEMG) and invasively (intramuscular, HD-iEMG). HD-sEMG recordings are obtained by grids placed on the skin surface while HD-iEMG signals can be acquired by micro-electrode arrays. While it has been shown that HD-iEMG allows the accurate decoding of a larger number of motor units when compared to HD-sEMG, the dependence of motor unit yield on the parameters of the micro-electrode arrays is still unexplored. Here, we used recently developed HD-iEMG electrodes to record from hundreds of recording sites within the muscle. This allowed us to investigate the impact of electrode number, inter-electrode distance, and the number of muscle insertions on the ability to sample motor units within the muscle. Specifically, we recorded both HD-sEMG and HD-iEMG from the Tibialis Anterior muscle of two healthy subjects at various contraction intensities (10%, 30%, and 70% of maximum voluntary contraction, MVC). For the first time, we present intramuscular recordings with more than 140 electrodes inside a single muscle, achieved through multiple implants of high-density micro-electrode arrays. Through systematic offline analyses of these recordings, we tested different electrode configurations to identify optimal setups for accurately capturing motor unit activity. The results revealed that the density of electrodes in the micro-electrode arrays is the most critical factor for maximising the number of identified motor units and ensuring very high accuracy. Comparisons between intramuscular and surface recordings also confirmed that HD-iEMG consistently captures larger and more stable numbers of motor units across subjects and contraction levels. These results underscore the potential of HD-iEMG as a powerful tool for both clinical and research settings, particularly when precise motor unit decomposition is crucial.
{"title":"Motor Unit Sampling From Intramuscular Micro-Electrode Array Recordings","authors":"Agnese Grison;Jaime Ibáñez Pereda;Dario Farina","doi":"10.1109/TNSRE.2025.3531054","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3531054","url":null,"abstract":"Recordings of electrical activity from muscles allow us to identify the activity of pools of spinal motor neurons that send the neural drive for muscle activation. Decoding motor unit and motor neuron activity from muscle recordings can be performed by high-density (HD) electrode systems, both non-invasively (surface, HD-sEMG) and invasively (intramuscular, HD-iEMG). HD-sEMG recordings are obtained by grids placed on the skin surface while HD-iEMG signals can be acquired by micro-electrode arrays. While it has been shown that HD-iEMG allows the accurate decoding of a larger number of motor units when compared to HD-sEMG, the dependence of motor unit yield on the parameters of the micro-electrode arrays is still unexplored. Here, we used recently developed HD-iEMG electrodes to record from hundreds of recording sites within the muscle. This allowed us to investigate the impact of electrode number, inter-electrode distance, and the number of muscle insertions on the ability to sample motor units within the muscle. Specifically, we recorded both HD-sEMG and HD-iEMG from the Tibialis Anterior muscle of two healthy subjects at various contraction intensities (10%, 30%, and 70% of maximum voluntary contraction, MVC). For the first time, we present intramuscular recordings with more than 140 electrodes inside a single muscle, achieved through multiple implants of high-density micro-electrode arrays. Through systematic offline analyses of these recordings, we tested different electrode configurations to identify optimal setups for accurately capturing motor unit activity. The results revealed that the density of electrodes in the micro-electrode arrays is the most critical factor for maximising the number of identified motor units and ensuring very high accuracy. Comparisons between intramuscular and surface recordings also confirmed that HD-iEMG consistently captures larger and more stable numbers of motor units across subjects and contraction levels. These results underscore the potential of HD-iEMG as a powerful tool for both clinical and research settings, particularly when precise motor unit decomposition is crucial.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"620-629"},"PeriodicalIF":4.8,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10844937","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361152","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}
Pub Date : 2025-01-16DOI: 10.1109/TNSRE.2025.3529991
Tingting Zhang;Xu Yan;Xin Chen;Yi Mao
Stereovision is the visual perception of depth derived from the integration of two slightly different images from each eye, enabling understanding of the three-dimensional space. This capability is deeply intertwined with cognitive brain functions. To explore the impact of stereograms with varied motions on brain activities, we collected Electroencephalography (EEG) signals evoked by Dynamic Random Dot Stereograms (DRDS). To effectively classify the EEG signals induced by DRDS, we introduced a novel hybrid neural network model, XCF-LSTMSATNet, which integrates an XGBoost Channel Feature Optimization Module with the EEGNet and an LSTM Self-Attention Modules. Initially, in the channel selection phase, XGBoost is employed for preliminary classification and feature weight analysis, which can enhance our channel selection strategy. Following this, EEGNet employs deep convolutional layers to extract spatial features, while separable convolutions are subsequently used to derive high-dimensional spatial-temporal features. Meanwhile, the LSTMSAT Module, with its capability to learn long-term dependencies in time-series signals, is deployed to capture temporal continuity information. The incorporation of the self-attention mechanism further amplifies the model’s ability to grasp long-distance dependencies and enables dynamic weight allocation to the extracted features. In the end, both temporal and spatial features are integrated into the classification module, enabling precise prediction across three categories of EEG signals. The proposed XCF-LSTMSATNet was extensively tested on both a custom dataset and the public datasets SRDA and SRDB. The results demonstrate that the model exhibits solid classification performance across all three datasets, effectively showcasing its robustness and generalization capabilities.
{"title":"XCF-LSTMSATNet: A Classification Approach for EEG Signals Evoked by Dynamic Random Dot Stereograms","authors":"Tingting Zhang;Xu Yan;Xin Chen;Yi Mao","doi":"10.1109/TNSRE.2025.3529991","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3529991","url":null,"abstract":"Stereovision is the visual perception of depth derived from the integration of two slightly different images from each eye, enabling understanding of the three-dimensional space. This capability is deeply intertwined with cognitive brain functions. To explore the impact of stereograms with varied motions on brain activities, we collected Electroencephalography (EEG) signals evoked by Dynamic Random Dot Stereograms (DRDS). To effectively classify the EEG signals induced by DRDS, we introduced a novel hybrid neural network model, XCF-LSTMSATNet, which integrates an XGBoost Channel Feature Optimization Module with the EEGNet and an LSTM Self-Attention Modules. Initially, in the channel selection phase, XGBoost is employed for preliminary classification and feature weight analysis, which can enhance our channel selection strategy. Following this, EEGNet employs deep convolutional layers to extract spatial features, while separable convolutions are subsequently used to derive high-dimensional spatial-temporal features. Meanwhile, the LSTMSAT Module, with its capability to learn long-term dependencies in time-series signals, is deployed to capture temporal continuity information. The incorporation of the self-attention mechanism further amplifies the model’s ability to grasp long-distance dependencies and enables dynamic weight allocation to the extracted features. In the end, both temporal and spatial features are integrated into the classification module, enabling precise prediction across three categories of EEG signals. The proposed XCF-LSTMSATNet was extensively tested on both a custom dataset and the public datasets SRDA and SRDB. The results demonstrate that the model exhibits solid classification performance across all three datasets, effectively showcasing its robustness and generalization capabilities.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"502-513"},"PeriodicalIF":4.8,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10843300","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184379","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：