IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献_第2页

Theory-Driven EEG Indexes for Tracking Motor Recovery and Predicting the Effects of Hybridizing tDCS With Mirror Therapy in Stroke Patients 理论驱动的脑电图指标，用于跟踪中风患者的运动恢复情况并预测 tDCS 与镜像疗法混合治疗的效果。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-08 DOI: 10.1109/TNSRE.2024.3493926

Chia-Lun Liu;Ken-Hsien Su;Yi-Shiung Horng;Chia-Ling Chen;Shou-Hsien Huang;Ching-Yi Wu

Stroke remains a leading cause of adult disability, underscoring why research continues to focus on advancing new treatment methods and neurophysiological indexes. While these studies may be effective, many lack a clear theoretical framework. The current study first determined the optimal combination effects of mirror therapy (MT) with transcranial direct current stimulation (tDCS) on the premotor or primary motor cortex on its short-term and sustained clinical outcomes. We then introduced electroencephalogram (EEG) indexes derived from the gating-by-inhibition model to explore the underlying therapeutic mechanisms. The EEG indexes used in this study focused on the functional involvement for motor generation: alpha power at temporal regions (inhibiting non-motor activity) and central-frontal regions (releasing motor regions from inhibition). Results showed that post-training benefits, measured by Fugl-Meyer Assessment (FMA), were similar across 3 tDCS interventions (premotor, primary motor, sham). EEG seemed more sensitive to the training, with notable responses in the premotor tDCS group. Three months after training, only the premotor tDCS group maintained the gains in FMA, with these improvements correlated with the EEG indexes. Again, this pattern was specific to premotor tDCS. Since the gating-by-inhibition model suggests that EEG index reflects an individual’s psychomotor efficiency, we also found that the baseline EEG index could predict FMA retention. Our findings demonstrate the superiority of combined premotor tDCS with MT and identify functionally oscillatory alpha-band activity in the temporal and central-frontal regions as potentially underlying the therapeutic mechanism. An individual’s spatial pattern of EEG may be effective in predicting upper extremity retention effect.

脑卒中仍然是导致成人残疾的主要原因，这也说明了为什么研究工作会继续关注新的治疗方法和神经生理指标。虽然这些研究可能有效，但许多研究缺乏明确的理论框架。本研究首先确定了镜像疗法（MT）与经颅直流电刺激（tDCS）对运动前皮层或初级运动皮层的短期和持续临床疗效的最佳组合效果。然后，我们引入了由门控抑制模型衍生的脑电图（EEG）指标，以探索潜在的治疗机制。本研究中使用的脑电图指标侧重于运动产生的功能参与：颞叶区域（抑制非运动活动）和中央额叶区域（从抑制中释放运动区域）的α功率。结果显示，通过 Fugl-Meyer 评估（FMA）衡量的训练后益处在 3 种 tDCS 干预（运动前、初级运动、假）中相似。脑电图似乎对训练更敏感，前运动 tDCS 组的反应明显。训练三个月后，只有前运动 tDCS 组保持了 FMA 的进步，这些进步与脑电图指数相关。同样，这种模式也是前运动 tDCS 所特有的。由于抑制门控模型表明脑电图指数反映了个体的精神运动效率，因此我们还发现基线脑电图指数可以预测 FMA 的保持情况。我们的研究结果证明了前运动tDCS与MT联合治疗的优越性，并确定了颞叶和中央额叶区域的功能性振荡α波段活动可能是治疗机制的基础。个人的脑电图空间模式可有效预测上肢保持效果。

{"title":"Theory-Driven EEG Indexes for Tracking Motor Recovery and Predicting the Effects of Hybridizing tDCS With Mirror Therapy in Stroke Patients","authors":"Chia-Lun Liu;Ken-Hsien Su;Yi-Shiung Horng;Chia-Ling Chen;Shou-Hsien Huang;Ching-Yi Wu","doi":"10.1109/TNSRE.2024.3493926","DOIUrl":"10.1109/TNSRE.2024.3493926","url":null,"abstract":"Stroke remains a leading cause of adult disability, underscoring why research continues to focus on advancing new treatment methods and neurophysiological indexes. While these studies may be effective, many lack a clear theoretical framework. The current study first determined the optimal combination effects of mirror therapy (MT) with transcranial direct current stimulation (tDCS) on the premotor or primary motor cortex on its short-term and sustained clinical outcomes. We then introduced electroencephalogram (EEG) indexes derived from the gating-by-inhibition model to explore the underlying therapeutic mechanisms. The EEG indexes used in this study focused on the functional involvement for motor generation: alpha power at temporal regions (inhibiting non-motor activity) and central-frontal regions (releasing motor regions from inhibition). Results showed that post-training benefits, measured by Fugl-Meyer Assessment (FMA), were similar across 3 tDCS interventions (premotor, primary motor, sham). EEG seemed more sensitive to the training, with notable responses in the premotor tDCS group. Three months after training, only the premotor tDCS group maintained the gains in FMA, with these improvements correlated with the EEG indexes. Again, this pattern was specific to premotor tDCS. Since the gating-by-inhibition model suggests that EEG index reflects an individual’s psychomotor efficiency, we also found that the baseline EEG index could predict FMA retention. Our findings demonstrate the superiority of combined premotor tDCS with MT and identify functionally oscillatory alpha-band activity in the temporal and central-frontal regions as potentially underlying the therapeutic mechanism. An individual’s spatial pattern of EEG may be effective in predicting upper extremity retention effect.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4042-4051"},"PeriodicalIF":4.8,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10747549","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142604336","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}

引用次数: 0

Automatic Reconstruction of Deep Brain Stimulation Lead Trajectories From CT Images Using Tracking and Morphological Analysis 利用跟踪和形态分析从 CT 图像自动重建脑深部刺激导线轨迹

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-07 DOI: 10.1109/TNSRE.2024.3493862

Wanxuan Sang;Zhiwen Xiao;Tiangang Long;Changqing Jiang;Luming Li

Deep brain stimulation (DBS) is an effective treatment for neurological disorders, and accurately reconstructing the DBS lead trajectories is crucial for MRI compatibility assessment and surgical planning. This paper presents a novel fully automated framework for reconstructing DBS lead trajectories from postoperative CT images. The leads were first segmented by thresholding, but would be fused together somewhere. Mean curvature analysis of multi-layer CT number isosurfaces was introduced to effectively address lead fusion, due to the different topological characteristics of the isosurfaces in and out of the fusion regions. The position of electrode contacts was determined through morphological analysis to get the starting point and the initial direction for trajectory tracking. The next trajectory point was derived by calculating the weighted average coordinates of the candidate points, using the distance from the current estimated trajectory and the CT number as weights. This method has demonstrated high accuracy and efficiency, successfully and automatically reconstructing complex bilateral trajectories for 13 patient cases in less than 10 minutes with errors less than 1 mm. This work overcomes the limitations of existing semi-automatic techniques that require extensive manual intervention. It paves the way for optimizing DBS lead trajectory to reduce tissue heating and image artifacts, which will contribute to neuroimaging studies and improve clinical outcomes. Code for our proposed algorithm is publicly available on Github.

深部脑刺激（DBS）是治疗神经系统疾病的有效方法，而准确重建 DBS 导联轨迹对于磁共振成像兼容性评估和手术规划至关重要。本文介绍了一种从术后 CT 图像重建 DBS 导联轨迹的新型全自动框架。首先通过阈值法对导联线进行分割，然后在某处将导联线融合在一起。由于融合区域内外的等值面具有不同的拓扑特征，因此引入了多层 CT 数字等值面的平均曲率分析，以有效解决导联融合问题。通过形态分析确定电极接触的位置，从而获得轨迹跟踪的起点和初始方向。通过计算候选点的加权平均坐标，以与当前估计轨迹的距离和 CT 编号作为权重，得出下一个轨迹点。该方法准确度高、效率高，在不到 10 分钟的时间内成功自动重建了 13 例患者的复杂双侧轨迹，误差小于 1 毫米。这项工作克服了现有半自动技术需要大量人工干预的局限性。它为优化 DBS 导联轨迹以减少组织发热和图像伪影铺平了道路，这将有助于神经成像研究和改善临床结果。我们提出的算法代码可在 Github 上公开获取。

{"title":"Automatic Reconstruction of Deep Brain Stimulation Lead Trajectories From CT Images Using Tracking and Morphological Analysis","authors":"Wanxuan Sang;Zhiwen Xiao;Tiangang Long;Changqing Jiang;Luming Li","doi":"10.1109/TNSRE.2024.3493862","DOIUrl":"10.1109/TNSRE.2024.3493862","url":null,"abstract":"Deep brain stimulation (DBS) is an effective treatment for neurological disorders, and accurately reconstructing the DBS lead trajectories is crucial for MRI compatibility assessment and surgical planning. This paper presents a novel fully automated framework for reconstructing DBS lead trajectories from postoperative CT images. The leads were first segmented by thresholding, but would be fused together somewhere. Mean curvature analysis of multi-layer CT number isosurfaces was introduced to effectively address lead fusion, due to the different topological characteristics of the isosurfaces in and out of the fusion regions. The position of electrode contacts was determined through morphological analysis to get the starting point and the initial direction for trajectory tracking. The next trajectory point was derived by calculating the weighted average coordinates of the candidate points, using the distance from the current estimated trajectory and the CT number as weights. This method has demonstrated high accuracy and efficiency, successfully and automatically reconstructing complex bilateral trajectories for 13 patient cases in less than 10 minutes with errors less than 1 mm. This work overcomes the limitations of existing semi-automatic techniques that require extensive manual intervention. It paves the way for optimizing DBS lead trajectory to reduce tissue heating and image artifacts, which will contribute to neuroimaging studies and improve clinical outcomes. Code for our proposed algorithm is publicly available on Github.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4014-4021"},"PeriodicalIF":4.8,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10746541","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142604275","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}

引用次数: 0

Multi-scale coupling between LFP and EMG in mice by low- intensity pulsed ultrasound stimulation with different number of tone-burst. 通过不同音爆次数的低强度脉冲超声刺激小鼠 LFP 和 EMG 之间的多尺度耦合。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-06 DOI: 10.1109/TNSRE.2024.3492158

Ziqiang Jin, Xiaoling Chen, Zechuan Du, Yi Yuan, Xiaoli Li, Ping Xie

Low-intensity pulsed ultrasound stimulation (LIPUS) as a non-invasive, high-spatial resolution and high penetration depth brain modulation technology has been used for modulating neuromuscular function. However, the modulation of neural electrical signal changes in the neuromuscular system by LIPUS remains to be explored. In this study, we stimulated the mouse brain motor cortex by LIPUS with different number of tone burst (NTB) and recorded the local field potential (LFP) signals of the target region and electromyography (EMG) of tail muscle. Multi-Scale Transfer Entropy (MSTE) analysis method was used to explore the multi-scale synchronization characteristics and functional cortico-muscular coupling (FCMC) strength changes of mice LFP-EMG before and after LIPUS under different NTBs. The results show that the MSTE of LFP-EMG before and after LIPUS stimulation was higher than that of EMG-LFP. After adding multi-scale, MSTE has a significant relationship with time scales. When NTB = 200, the scale of extremum is the largest. There was a fitting intersection between LFP-EMG and EMG-LFP scale 7-21 before and after stimulation. After scale averaging, the LFP-EMG after stimulation was lower than that before stimulation, and the EMG-LFP after stimulation was higher than that before stimulation.Conclusion: There is a significant correlation between NTB and time scale before and after LIPUS,as well as upward and downward. Consequently,This study used FCMC methods to study different NTBs and multi-scale relationships, provides new variables from LIPUS parameters and analysis, and provides new reference for clinical applications of LIPUS.

低强度脉冲超声刺激（LIPUS）作为一种无创、高空间分辨率和高穿透深度的脑调制技术，已被用于调节神经肌肉功能。然而，LIPUS 对神经肌肉系统中神经电信号变化的调制仍有待探索。本研究用不同数量的音爆（NTB）刺激小鼠大脑运动皮层，记录靶区局部场电位（LFP）信号和尾肌肌电图（EMG）。采用多尺度传递熵（MSTE）分析方法探讨了不同NTB下LIPUS前后小鼠LFP-EMG的多尺度同步特征和皮质-肌肉功能耦合（FCMC）强度变化。结果表明，LIPUS 刺激前后 LFP-EMG 的 MSTE 均高于 EMG-LFP。加入多尺度后，MSTE 与时间尺度有显著关系。当 NTB = 200 时，极值尺度最大。在刺激前后，LFP-EMG 与 EMG-LFP 第 7-21 刻度之间存在拟合交集。刻度平均后，刺激后的 LFP-EMG 低于刺激前，刺激后的 EMG-LFP 高于刺激前：结论：NTB 与 LIPUS 前后的时间尺度以及向上和向下的时间尺度之间存在明显的相关性。因此，本研究采用FCMC方法研究了不同的NTB和多尺度关系，提供了LIPUS参数和分析的新变量，为LIPUS的临床应用提供了新的参考。

{"title":"Multi-scale coupling between LFP and EMG in mice by low- intensity pulsed ultrasound stimulation with different number of tone-burst.","authors":"Ziqiang Jin, Xiaoling Chen, Zechuan Du, Yi Yuan, Xiaoli Li, Ping Xie","doi":"10.1109/TNSRE.2024.3492158","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3492158","url":null,"abstract":"Low-intensity pulsed ultrasound stimulation (LIPUS) as a non-invasive, high-spatial resolution and high penetration depth brain modulation technology has been used for modulating neuromuscular function. However, the modulation of neural electrical signal changes in the neuromuscular system by LIPUS remains to be explored. In this study, we stimulated the mouse brain motor cortex by LIPUS with different number of tone burst (NTB) and recorded the local field potential (LFP) signals of the target region and electromyography (EMG) of tail muscle. Multi-Scale Transfer Entropy (MSTE) analysis method was used to explore the multi-scale synchronization characteristics and functional cortico-muscular coupling (FCMC) strength changes of mice LFP-EMG before and after LIPUS under different NTBs. The results show that the MSTE of LFP-EMG before and after LIPUS stimulation was higher than that of EMG-LFP. After adding multi-scale, MSTE has a significant relationship with time scales. When NTB = 200, the scale of extremum is the largest. There was a fitting intersection between LFP-EMG and EMG-LFP scale 7-21 before and after stimulation. After scale averaging, the LFP-EMG after stimulation was lower than that before stimulation, and the EMG-LFP after stimulation was higher than that before stimulation.Conclusion: There is a significant correlation between NTB and time scale before and after LIPUS,as well as upward and downward. Consequently,This study used FCMC methods to study different NTBs and multi-scale relationships, provides new variables from LIPUS parameters and analysis, and provides new reference for clinical applications of LIPUS.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590784","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}

引用次数: 0

Reconstructing Multi-Stroke Characters from Brain Signals toward Generalizable Handwriting Brain-Computer Interfaces. 从大脑信号重构多笔画字符，实现通用手写脑机接口。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-06 DOI: 10.1109/TNSRE.2024.3492191

Xiaomeng Yang, Xinzhu Xiong, Xufei Li, Qi Lian, Junming Zhu, Jianmin Zhang, Yu Qi, Yueming Wang

Handwriting Brain-Computer Interfaces (BCIs) provides a promising communication avenue for individuals with paralysis. While English-based handwriting BCIs have achieved rapid typewriting with 26 lowercase letters (mostly containing one stroke each), it is difficult to extend to complex characters, especially those with multiple strokes and large character sets. The Chinese characters, including over 3500 commonly used characters with 10.3 strokes per character on average, represent a highly complex writing system. This paper proposes a Chinese handwriting BCI system, which reconstructs multi-stroke handwriting trajectories from brain signals. Through the recording of cortical neural signals from the motor cortex, we reveal distinct neural representations for stroke-writing and pen-lift phases. Leveraging this finding, we propose a stroke-aware approach to decode stroke-writing trajectories and pen-lift movements individually, which can reconstruct recognizable characters (accuracy of 86% with 400 characters). Our approach demonstrates high stability over 5 months, shedding light on generalized and adaptable handwriting BCIs.

手写脑机接口（BCIs）为瘫痪患者提供了一条前景广阔的交流途径。虽然基于英语的手写生物识别（BCI）已经实现了 26 个小写字母的快速打字（大部分每个字母只有一个笔画），但很难扩展到复杂的字符，尤其是那些多笔画和大字符集的字符。汉字包括 3500 多个常用字，平均每字 10.3 笔，是一个高度复杂的书写系统。本文提出了一种汉字手写生物识别（BCI）系统，可通过大脑信号重建多笔画手写轨迹。通过记录运动皮层的神经信号，我们揭示了笔画书写和提笔阶段的不同神经表征。利用这一发现，我们提出了一种笔划感知方法，可单独解码笔划书写轨迹和提笔动作，从而重建可识别的字符（400 个字符的准确率为 86%）。我们的方法在5个月内表现出高度稳定性，为通用和适应性强的手写BCI提供了启示。

{"title":"Reconstructing Multi-Stroke Characters from Brain Signals toward Generalizable Handwriting Brain-Computer Interfaces.","authors":"Xiaomeng Yang, Xinzhu Xiong, Xufei Li, Qi Lian, Junming Zhu, Jianmin Zhang, Yu Qi, Yueming Wang","doi":"10.1109/TNSRE.2024.3492191","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3492191","url":null,"abstract":"Handwriting Brain-Computer Interfaces (BCIs) provides a promising communication avenue for individuals with paralysis. While English-based handwriting BCIs have achieved rapid typewriting with 26 lowercase letters (mostly containing one stroke each), it is difficult to extend to complex characters, especially those with multiple strokes and large character sets. The Chinese characters, including over 3500 commonly used characters with 10.3 strokes per character on average, represent a highly complex writing system. This paper proposes a Chinese handwriting BCI system, which reconstructs multi-stroke handwriting trajectories from brain signals. Through the recording of cortical neural signals from the motor cortex, we reveal distinct neural representations for stroke-writing and pen-lift phases. Leveraging this finding, we propose a stroke-aware approach to decode stroke-writing trajectories and pen-lift movements individually, which can reconstruct recognizable characters (accuracy of 86% with 400 characters). Our approach demonstrates high stability over 5 months, shedding light on generalized and adaptable handwriting BCIs.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590786","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}

引用次数: 0

Spatiotemporal Dynamics of Periodic and Aperiodic Brain Activity Under Peripheral Nerve Stimulation With Acupuncture 针刺周围神经刺激下周期性和非周期性脑活动的时空动态变化

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-05 DOI: 10.1109/TNSRE.2024.3492014

Haitao Yu;Fan Li;Jialin Liu;Chen Liu;Guiping Li;Jiang Wang

Brain activities are a mixture of periodic and aperiodic components, manifesting in the power spectral density (PSD) as rhythmic oscillations with spectral peaks and broadband fluctuations. Periodic oscillatory properties of brain response to external stimulation are widely studied, while aperiodic component responses remain unclear. Here, we investigate spatiotemporal dynamics of periodic and aperiodic brain activity under peripheral nerve stimulation with acupuncture by parameterization of power spectra of EEG signals. Regarding periodic brain activity, spectral peak in delta band emerges in frontal and central brain regions indicates a typical phenomenon of neural entrainment, which is formed by coupling periodic brain activity to external rhythmic acupuncture stimulation. In addition, the statistical results show that alpha periodic power is an important indicator for characterizing the modulatory effects of acupuncture on periodic brain activity. As for aperiodic brain activity, broadband EEG spectral trend analysis demonstrates a steeper aperiodic slope in left parietal lobe and a stronger negative correlation with the aperiodic offset under acupuncture compared with resting state, with the absolute value of correlation coefficient increasing from 0.27 to 0.50. Based on the two parameters that can best characterize the acupuncture effect, alpha periodic power and aperiodic slope, the accurate decoding of acupuncture manipulation is realized with AUC = 0.87. This work shows the modulatory effect of peripheral nerve stimulation with acupuncture on the brain activity by characterizing the periodic and aperiodic spectrum features of EEG, providing new insights into the comprehensive understanding of the response processes of human brain to acupuncture stimulation.

大脑活动是周期性和非周期性成分的混合体，在功率谱密度（PSD）中表现为具有谱峰和宽带波动的节律性振荡。大脑对外界刺激反应的周期性振荡特性已被广泛研究，而非周期性成分的反应仍不清楚。在此，我们通过对脑电图信号功率谱的参数化，研究了针刺周围神经刺激下周期性和非周期性大脑活动的时空动态。在周期性脑活动方面，额叶和中枢脑区出现了δ波段频谱峰，表明周期性脑活动与外部节律性针刺刺激耦合形成了典型的神经夹带现象。此外，统计结果表明，α周期功率是表征针灸对周期性脑活动调节作用的重要指标。至于非周期性脑活动，宽带脑电图频谱趋势分析表明，与静息状态相比，针刺时左顶叶的非周期性斜率更陡，与非周期性偏移的负相关性更强，相关系数的绝对值从 0.27 增加到 0.50。基于α周期功率和非周期性斜率这两个最能表征针刺效应的参数，实现了对针刺操作的精确解码，AUC = 0.87。这项工作通过表征脑电图的周期性和非周期性频谱特征，显示了针灸刺激周围神经对大脑活动的调节作用，为全面了解人脑对针灸刺激的反应过程提供了新的见解。

{"title":"Spatiotemporal Dynamics of Periodic and Aperiodic Brain Activity Under Peripheral Nerve Stimulation With Acupuncture","authors":"Haitao Yu;Fan Li;Jialin Liu;Chen Liu;Guiping Li;Jiang Wang","doi":"10.1109/TNSRE.2024.3492014","DOIUrl":"10.1109/TNSRE.2024.3492014","url":null,"abstract":"Brain activities are a mixture of periodic and aperiodic components, manifesting in the power spectral density (PSD) as rhythmic oscillations with spectral peaks and broadband fluctuations. Periodic oscillatory properties of brain response to external stimulation are widely studied, while aperiodic component responses remain unclear. Here, we investigate spatiotemporal dynamics of periodic and aperiodic brain activity under peripheral nerve stimulation with acupuncture by parameterization of power spectra of EEG signals. Regarding periodic brain activity, spectral peak in delta band emerges in frontal and central brain regions indicates a typical phenomenon of neural entrainment, which is formed by coupling periodic brain activity to external rhythmic acupuncture stimulation. In addition, the statistical results show that alpha periodic power is an important indicator for characterizing the modulatory effects of acupuncture on periodic brain activity. As for aperiodic brain activity, broadband EEG spectral trend analysis demonstrates a steeper aperiodic slope in left parietal lobe and a stronger negative correlation with the aperiodic offset under acupuncture compared with resting state, with the absolute value of correlation coefficient increasing from 0.27 to 0.50. Based on the two parameters that can best characterize the acupuncture effect, alpha periodic power and aperiodic slope, the accurate decoding of acupuncture manipulation is realized with AUC = 0.87. This work shows the modulatory effect of peripheral nerve stimulation with acupuncture on the brain activity by characterizing the periodic and aperiodic spectrum features of EEG, providing new insights into the comprehensive understanding of the response processes of human brain to acupuncture stimulation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3993-4003"},"PeriodicalIF":4.8,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10744423","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142583121","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}

引用次数: 0

HDE-Array: Development and Validation of a New Dry Electrode Array Design to Acquire HD-sEMG for Hand Position Estimation HDE-Array：开发和验证新型干电极阵列设计，以获取用于估算手部位置的 HD-sEMG。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-04 DOI: 10.1109/TNSRE.2024.3490796

Giovanni Rolandino;Chiara Zangrandi;Taian Vieira;Giacinto Luigi Cerone;Brian Andrews;James J. FitzGerald

This paper aims to introduce HDE-Array (High-Density Electrode Array), a novel dry electrode array for acquiring High-Density surface electromyography (HD-sEMG) for hand position estimation through RPC-Net (Recursive Prosthetic Control Network), a neural network defined in a previous study. We aim to demonstrate the hypothesis that the position estimates returned by RPC-Net using HD-sEMG signals acquired with HDE-Array are as accurate as those obtained from signals acquired with gel electrodes. We compared the results, in terms of precision of hand position estimation by RPC-Net, using signals acquired by traditional gel electrodes and by HDE-Array. As additional validation, we performed a variance analysis to confirm that the presence of only two rows of electrodes does not result in an excessive loss of information, and we characterized the electrode-skin impedance to assess the effects of the voltage divider effect and power line interference. Performance tests indicated that RPC-Net, used with HDE-Array, achieved comparable or superior results to those observed when used with the gel electrode setup. The dry electrodes demonstrated effective performance even with a simplified setup, highlighting potential cost and usability benefits. These results suggest improvements in the accessibility and user-friendliness of upper-limb rehabilitation devices and underscore the potential of HDE-Array and RPC-Net to revolutionize control for medical and non-medical applications.

本文旨在介绍 HDE-Array（高密度电极阵列），这是一种新型干式电极阵列，用于获取高密度表面肌电图（HD-sEMG），并通过 RPC-Net（递归假体控制网络）进行手部位置估计。我们的目的是证明一个假设，即使用 HDE-Array 获得的 HD-sEMG 信号通过 RPC-Net 返回的位置估计值与使用凝胶电极获得的信号一样准确。我们比较了 RPC-Net 使用传统凝胶电极和 HDE-Array 采集的信号进行手部位置估计的精度。作为额外的验证，我们还进行了方差分析，以确认只有两排电极不会导致过多的信息丢失，我们还对电极-皮肤阻抗进行了描述，以评估分压器效应和电源线干扰的影响。性能测试表明，RPC-Net 与 HDE-Array 配合使用，取得了与凝胶电极装置相当甚至更好的效果。干电极即使在简化设置的情况下也能显示出有效的性能，凸显了潜在的成本和可用性优势。这些结果表明，上肢康复设备的易用性和用户友好性得到了改善，并强调了 HDE-Array 和 RPC-Net 在革新医疗和非医疗应用控制方面的潜力。

{"title":"HDE-Array: Development and Validation of a New Dry Electrode Array Design to Acquire HD-sEMG for Hand Position Estimation","authors":"Giovanni Rolandino;Chiara Zangrandi;Taian Vieira;Giacinto Luigi Cerone;Brian Andrews;James J. FitzGerald","doi":"10.1109/TNSRE.2024.3490796","DOIUrl":"10.1109/TNSRE.2024.3490796","url":null,"abstract":"This paper aims to introduce HDE-Array (High-Density Electrode Array), a novel dry electrode array for acquiring High-Density surface electromyography (HD-sEMG) for hand position estimation through RPC-Net (Recursive Prosthetic Control Network), a neural network defined in a previous study. We aim to demonstrate the hypothesis that the position estimates returned by RPC-Net using HD-sEMG signals acquired with HDE-Array are as accurate as those obtained from signals acquired with gel electrodes. We compared the results, in terms of precision of hand position estimation by RPC-Net, using signals acquired by traditional gel electrodes and by HDE-Array. As additional validation, we performed a variance analysis to confirm that the presence of only two rows of electrodes does not result in an excessive loss of information, and we characterized the electrode-skin impedance to assess the effects of the voltage divider effect and power line interference. Performance tests indicated that RPC-Net, used with HDE-Array, achieved comparable or superior results to those observed when used with the gel electrode setup. The dry electrodes demonstrated effective performance even with a simplified setup, highlighting potential cost and usability benefits. These results suggest improvements in the accessibility and user-friendliness of upper-limb rehabilitation devices and underscore the potential of HDE-Array and RPC-Net to revolutionize control for medical and non-medical applications.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4004-4013"},"PeriodicalIF":4.8,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741560","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142576056","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}

引用次数: 0

AFSleepNet: Attention-Based Multi-View Feature Fusion Framework for Pediatric Sleep Staging AFSleepNet：基于注意力的多视角特征融合框架，用于儿科睡眠分期。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-04 DOI: 10.1109/TNSRE.2024.3490757

Yunfeng Zhu;Yunxiao Wu;Zhiya Wang;Ligang Zhou;Chen Chen;Zhifei Xu;Wei Chen

The widespread prevalence of sleep problems in children highlights the importance of timely and accurate sleep staging in the diagnosis and treatment of pediatric sleep disorders. However, most existing sleep staging methods rely on one-dimensional raw polysomnograms or two-dimensional spectrograms, which omit critical details due to single-view processing. This shortcoming is particularly apparent in pediatric sleep staging, where the lack of a specialized network fails to meet the needs of precision medicine. Therefore, we introduce AFSleepNet, a novel attention-based multi-view feature fusion network tailored for pediatric sleep analysis. The model utilizes multimodal data (EEG, EOG, EMG), combining one-dimensional convolutional neural networks to extract time-invariant features and bidirectional-long-short-term memory to learn the transition rules among sleep stages, as well as employing short-time Fourier transform to generate two-dimensional spectral maps. This network employs a fusion method with self-attention mechanism and innovative pre-training strategy. This strategy can maintain the feature extraction capabilities of AFSleepNet from different views, enhancing the robustness of the multi-view model while effectively preventing model overfitting, thereby achieving efficient and accurate automatic sleep stage analysis. A “leave-one-subject-out” cross-validation on CHAT and clinical datasets demonstrated the excellent performance of AFSleepNet, with mean accuracies of 87.5% and 88.1%, respectively. Superiority over existing methods improves the accuracy and reliability of pediatric sleep staging.

儿童睡眠问题普遍存在，这凸显了及时准确的睡眠分期对诊断和治疗儿童睡眠障碍的重要性。然而，大多数现有的睡眠分期方法都依赖于一维原始多导睡眠图或二维频谱图，由于单视角处理，忽略了关键细节。这一缺陷在儿科睡眠分期中尤为明显，由于缺乏专业网络，无法满足精准医疗的需求。因此，我们引入了 AFSleepNet，这是一种为儿科睡眠分析量身定制的基于注意力的新型多视角特征融合网络。该模型利用多模态数据（EEG、EOG、EMG），结合一维卷积神经网络提取时变特征，并利用双向长短期记忆学习睡眠阶段之间的转换规则，同时利用短时傅里叶变换生成二维频谱图。该网络采用了具有自我注意机制的融合方法和创新的预训练策略。这种策略可以保持 AFSleepNet 从不同视角提取特征的能力，增强多视角模型的鲁棒性，同时有效防止模型过拟合，从而实现高效、准确的自动睡眠阶段分析。在CHAT和临床数据集上进行的 "leave-one-subject-out "交叉验证证明了AFSleepNet的卓越性能，平均准确率分别为87.5%和88.1%。与现有方法相比，AFSleepNet 的优越性提高了儿科睡眠分期的准确性和可靠性。

{"title":"AFSleepNet: Attention-Based Multi-View Feature Fusion Framework for Pediatric Sleep Staging","authors":"Yunfeng Zhu;Yunxiao Wu;Zhiya Wang;Ligang Zhou;Chen Chen;Zhifei Xu;Wei Chen","doi":"10.1109/TNSRE.2024.3490757","DOIUrl":"10.1109/TNSRE.2024.3490757","url":null,"abstract":"The widespread prevalence of sleep problems in children highlights the importance of timely and accurate sleep staging in the diagnosis and treatment of pediatric sleep disorders. However, most existing sleep staging methods rely on one-dimensional raw polysomnograms or two-dimensional spectrograms, which omit critical details due to single-view processing. This shortcoming is particularly apparent in pediatric sleep staging, where the lack of a specialized network fails to meet the needs of precision medicine. Therefore, we introduce AFSleepNet, a novel attention-based multi-view feature fusion network tailored for pediatric sleep analysis. The model utilizes multimodal data (EEG, EOG, EMG), combining one-dimensional convolutional neural networks to extract time-invariant features and bidirectional-long-short-term memory to learn the transition rules among sleep stages, as well as employing short-time Fourier transform to generate two-dimensional spectral maps. This network employs a fusion method with self-attention mechanism and innovative pre-training strategy. This strategy can maintain the feature extraction capabilities of AFSleepNet from different views, enhancing the robustness of the multi-view model while effectively preventing model overfitting, thereby achieving efficient and accurate automatic sleep stage analysis. A “leave-one-subject-out” cross-validation on CHAT and clinical datasets demonstrated the excellent performance of AFSleepNet, with mean accuracies of 87.5% and 88.1%, respectively. Superiority over existing methods improves the accuracy and reliability of pediatric sleep staging.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"4022-4032"},"PeriodicalIF":4.8,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741586","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142576052","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}

引用次数: 0

Comparing Powered Wheelchair Driving Characteristics of Real Driving and Two Types of Simulated Driving 比较电动轮椅在实际驾驶和两种模拟驾驶中的特点。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-11-04 DOI: 10.1109/TNSRE.2024.3481277

Myeonghwan Bang;Min A Kim;Myung Joon Lim;Hyoung Seop Kim

We aimed to gather evidence on the feasibility of using simulator-based driving assessments for prescribing powered mobility devices (PMDs). Therefore, we compared the driving characteristics of real driving and two types of simulated driving. Thirty participants with difficulty walking more than 100 meters independently were enrolled. We developed a full-cabin and desktop simulator and created driving scenarios that closely resembled a real driving route in a park. They participated in three separate driving sessions, each using a powered wheelchair, full-cabin simulator, and desktop simulator. The driving characteristics, such as driving distance, mean speed, and standard deviation (SD) of speed, were obtained and analyzed to assess differences and correlations. Statistically significant differences were found in the driving distance and the SD of speed, respectively. However, for the mean speed, there was no statistically significant difference among the three types of driving. The intraclass correlation coefficient (ICC) for the driving distance was 0.154, which was not statistically significant. However, for mean speed, the ICC was 0.752, indicating a strong correlation. The ICC for the SD of speed was 0.562, indicating a moderate correlation. We demonstrated that the two types of simulators have characteristics that are similar to real-world driving characteristics. The mean speed showed the highest similarity, and the SD of the speed showed a moderate degree of similarity. These results highlight the significant potential of employing simulator-based driving to evaluate the use of PMDs.

我们的目的是收集证据，证明在开具助行器具处方时使用模拟驾驶评估的可行性。因此，我们比较了真实驾驶和两种模拟驾驶的驾驶特性。我们招募了 30 名独立行走 100 米以上有困难的参与者。我们开发了全舱和桌面模拟器，并创建了与公园中真实驾驶路线非常相似的驾驶场景。他们分别使用电动轮椅、全座舱模拟器和桌面模拟器进行了三次驾驶训练。对驾驶距离、平均速度和速度标准偏差（SD）等驾驶特征进行了采集和分析，以评估差异和相关性。结果发现，驾驶距离和速度标准偏差在统计学上存在明显差异。然而，在平均速度方面，三种驾驶方式之间没有统计学意义上的显著差异。驾驶距离的类内相关系数（ICC）为 0.154，无统计学意义。然而，平均速度的 ICC 为 0.752，表明相关性很强。速度标差的 ICC 为 0.562，表明相关性适中。我们证明，这两种模拟器的特性与真实世界的驾驶特性相似。平均速度显示出最高的相似性，速度的 SD 显示出中等程度的相似性。这些结果凸显了采用模拟器驾驶来评估 PMD 使用情况的巨大潜力。

{"title":"Comparing Powered Wheelchair Driving Characteristics of Real Driving and Two Types of Simulated Driving","authors":"Myeonghwan Bang;Min A Kim;Myung Joon Lim;Hyoung Seop Kim","doi":"10.1109/TNSRE.2024.3481277","DOIUrl":"10.1109/TNSRE.2024.3481277","url":null,"abstract":"We aimed to gather evidence on the feasibility of using simulator-based driving assessments for prescribing powered mobility devices (PMDs). Therefore, we compared the driving characteristics of real driving and two types of simulated driving. Thirty participants with difficulty walking more than 100 meters independently were enrolled. We developed a full-cabin and desktop simulator and created driving scenarios that closely resembled a real driving route in a park. They participated in three separate driving sessions, each using a powered wheelchair, full-cabin simulator, and desktop simulator. The driving characteristics, such as driving distance, mean speed, and standard deviation (SD) of speed, were obtained and analyzed to assess differences and correlations. Statistically significant differences were found in the driving distance and the SD of speed, respectively. However, for the mean speed, there was no statistically significant difference among the three types of driving. The intraclass correlation coefficient (ICC) for the driving distance was 0.154, which was not statistically significant. However, for mean speed, the ICC was 0.752, indicating a strong correlation. The ICC for the SD of speed was 0.562, indicating a moderate correlation. We demonstrated that the two types of simulators have characteristics that are similar to real-world driving characteristics. The mean speed showed the highest similarity, and the SD of the speed showed a moderate degree of similarity. These results highlight the significant potential of employing simulator-based driving to evaluate the use of PMDs.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3987-3992"},"PeriodicalIF":4.8,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10742429","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142576053","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}

引用次数: 0

Lower Limb Torque Prediction for Sit-To-Walk Strategies Using Long Short-Term Memory Neural Networks 利用长短期记忆神经网络预测坐着行走策略的下肢扭矩

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-10-30 DOI: 10.1109/TNSRE.2024.3488052

Chamalka Kenneth Perera;Alpha. A. Gopalai;Darwin Gouwanda;Siti. A. Ahmad;Pei-Lee Teh

Joint torque prediction is crucial when investigating biomechanics, evaluating treatments, and designing powered assistive devices. Controllers in assistive technology require reference torque trajectories to set the level of assistance for a patient during rehabilitation or when aiding essential daily tasks such as sit-to-walk (STW). STW itself can be generalized into strategies based on individual needs and movement patterns. In this study, three long short-term memory (LSTM) neural networks were empirically trained for hip and knee torque prediction considering these STW strategies and subject anthropometry. The hip and knee are the drivers of STW, while the network architectures were selected for recognizing temporal and spatial relationships. Performance of the LSTMs were compared and evaluated against the STW strategies to accurately generate strategy-specific and user-oriented torque. As such, train and test STW data were obtained from 65 subjects across three age groups: young, middle-aged, and older adults (19-73 years). Model inputs were hip and knee angles with horizontal center of mass velocity, while windowing allowed the LSTMs to dynamically adapt to real-time changes in STW transitions. The encoder-decoder LSTM showcased optimal performance with robust recognition of temporal features. It produced significantly (

${P}lt 0.05$

) low hip and knee root mean square error (

$0.24~pm ~0.07$

and

$0.15~pm ~0.02$

Nm/kg), strong Spearman’s correlation (

$93.43~pm ~2.86$

and

$84.83~pm ~2.96$

%) and good intraclass correlation coefficients (greater than 0.75), demonstrating model reliability. Hence, this network predicts strategy and user oriented reference torques for personalized controllers in assistive devices, with more natural application of assistance.

在研究生物力学、评估治疗方法和设计动力辅助设备时，关节扭矩预测至关重要。辅助技术中的控制器需要参考扭矩轨迹来设定病人在康复或辅助坐着行走（STW）等基本日常任务时的辅助水平。坐姿行走本身可以根据个人需求和运动模式归纳为不同的策略。在本研究中，考虑到这些 STW 策略和受试者的人体测量，对三个长短期记忆（LSTM）神经网络进行了经验性训练，以预测髋关节和膝关节的扭矩。髋关节和膝关节是 STW 的驱动力，而网络架构则是为识别时间和空间关系而选择的。针对 STW 策略对 LSTM 的性能进行了比较和评估，以准确生成特定策略和面向用户的扭矩。因此，训练和测试 STW 数据来自三个年龄组的 65 名受试者：年轻人、中年人和老年人（19-73 岁）。模型输入为具有水平质心速度的髋关节和膝关节角度，而窗口允许 LSTM 动态适应 STW 过渡的实时变化。编码器-解码器 LSTM 凭借对时间特征的强大识别能力展现了最佳性能。它能明显（P

{"title":"Lower Limb Torque Prediction for Sit-To-Walk Strategies Using Long Short-Term Memory Neural Networks","authors":"Chamalka Kenneth Perera;Alpha. A. Gopalai;Darwin Gouwanda;Siti. A. Ahmad;Pei-Lee Teh","doi":"10.1109/TNSRE.2024.3488052","DOIUrl":"10.1109/TNSRE.2024.3488052","url":null,"abstract":"Joint torque prediction is crucial when investigating biomechanics, evaluating treatments, and designing powered assistive devices. Controllers in assistive technology require reference torque trajectories to set the level of assistance for a patient during rehabilitation or when aiding essential daily tasks such as sit-to-walk (STW). STW itself can be generalized into strategies based on individual needs and movement patterns. In this study, three long short-term memory (LSTM) neural networks were empirically trained for hip and knee torque prediction considering these STW strategies and subject anthropometry. The hip and knee are the drivers of STW, while the network architectures were selected for recognizing temporal and spatial relationships. Performance of the LSTMs were compared and evaluated against the STW strategies to accurately generate strategy-specific and user-oriented torque. As such, train and test STW data were obtained from 65 subjects across three age groups: young, middle-aged, and older adults (19-73 years). Model inputs were hip and knee angles with horizontal center of mass velocity, while windowing allowed the LSTMs to dynamically adapt to real-time changes in STW transitions. The encoder-decoder LSTM showcased optimal performance with robust recognition of temporal features. It produced significantly (\u0000<inline-formula> <tex-math>${P}lt 0.05$ </tex-math></inline-formula>\u0000) low hip and knee root mean square error (\u0000<inline-formula> <tex-math>$0.24~pm ~0.07$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$0.15~pm ~0.02$ </tex-math></inline-formula>\u0000 Nm/kg), strong Spearman’s correlation (\u0000<inline-formula> <tex-math>$93.43~pm ~2.86$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$84.83~pm ~2.96$ </tex-math></inline-formula>\u0000%) and good intraclass correlation coefficients (greater than 0.75), demonstrating model reliability. Hence, this network predicts strategy and user oriented reference torques for personalized controllers in assistive devices, with more natural application of assistance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3977-3986"},"PeriodicalIF":4.8,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10739358","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142545264","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}

引用次数: 0

A Novel Multi-Feature Fusion Network With Spatial Partitioning Strategy and Cross-Attention for Armband-Based Gesture Recognition 采用空间分割策略和交叉注意力的新型多特征融合网络，用于基于臂章的手势识别。

IF 4.8 2区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Pub Date : 2024-10-28 DOI: 10.1109/TNSRE.2024.3487216

Fo Hu;Mengyuan Qian;Kailun He;Wen-An Zhang;Xusheng Yang

Effectively integrating the time-space-frequency information of multi-modal signals from armband sensor, including surface electromyogram (sEMG) and accelerometer data, is critical for accurate gesture recognition. Existing approaches often neglect the abundant spatial relationships inherent in multi-channel sEMG signals obtained via armband sensors and face challenges in harnessing the correlations across multiple feature domains. To address this issue, we propose a novel multi-feature fusion network with spatial partitioning strategy and cross-attention (MFN-SPSCA) to improve the accuracy and robustness of gesture recognition. Specifically, a spatiotemporal graph convolution module with a spatial partitioning strategy is designed to capture potential spatial feature of multi-channel sEMG signals. Additionally, we design a cross-attention fusion module to learn and prioritize the importance and correlation of multi-feature domain. Extensive experiment demonstrate that the MFN-SPSCA method outperforms other state-of-the-art methods on self-collected dataset and the Ninapro DB5 dataset. Our work addresses the challenge of recognizing gestures from the multi-modal data collected by armband sensor, emphasizing the importance of integrating time-space-frequency information. Codes are available at https://github.com/ZJUTofBrainIntelligence/MFN-SPSCA.

有效整合来自臂带传感器的多模态信号（包括表面肌电图（sEMG）和加速度计数据）的时空频率信息对于准确识别手势至关重要。现有方法往往忽视了通过臂带传感器获取的多通道 sEMG 信号中固有的丰富空间关系，在利用多个特征域的相关性方面面临挑战。为解决这一问题，我们提出了一种具有空间分区策略和交叉注意力的新型多特征融合网络（MFN-SPSCA），以提高手势识别的准确性和鲁棒性。具体来说，我们设计了一个具有空间分割策略的时空图卷积模块，以捕捉多通道 sEMG 信号的潜在空间特征。此外，我们还设计了一个交叉注意力融合模块，以学习和优先处理多特征域的重要性和相关性。大量实验证明，MFN-SPSCA 方法在自收集数据集和 Ninapro DB5 数据集上的表现优于其他先进方法。我们的工作解决了从臂章传感器收集的多模态数据中识别手势的难题，强调了整合时-空-频信息的重要性。代码见 https://github.com/ZJUTofBrainIntelligence/MFN-SPSCA。

{"title":"A Novel Multi-Feature Fusion Network With Spatial Partitioning Strategy and Cross-Attention for Armband-Based Gesture Recognition","authors":"Fo Hu;Mengyuan Qian;Kailun He;Wen-An Zhang;Xusheng Yang","doi":"10.1109/TNSRE.2024.3487216","DOIUrl":"10.1109/TNSRE.2024.3487216","url":null,"abstract":"Effectively integrating the time-space-frequency information of multi-modal signals from armband sensor, including surface electromyogram (sEMG) and accelerometer data, is critical for accurate gesture recognition. Existing approaches often neglect the abundant spatial relationships inherent in multi-channel sEMG signals obtained via armband sensors and face challenges in harnessing the correlations across multiple feature domains. To address this issue, we propose a novel multi-feature fusion network with spatial partitioning strategy and cross-attention (MFN-SPSCA) to improve the accuracy and robustness of gesture recognition. Specifically, a spatiotemporal graph convolution module with a spatial partitioning strategy is designed to capture potential spatial feature of multi-channel sEMG signals. Additionally, we design a cross-attention fusion module to learn and prioritize the importance and correlation of multi-feature domain. Extensive experiment demonstrate that the MFN-SPSCA method outperforms other state-of-the-art methods on self-collected dataset and the Ninapro DB5 dataset. Our work addresses the challenge of recognizing gestures from the multi-modal data collected by armband sensor, emphasizing the importance of integrating time-space-frequency information. Codes are available at \u0000<uri>https://github.com/ZJUTofBrainIntelligence/MFN-SPSCA</uri>\u0000.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3878-3890"},"PeriodicalIF":4.8,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10737142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142521817","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}

引用次数: 0