IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"Multimodal Freezing of Gait Detection: Analyzing the Benefits and Limitations of Physiological Data","authors":"Po-Kai Yang;Benjamin Filtjens;Pieter Ginis;Maaike Goris;Alice Nieuwboer;Moran Gilat;Peter Slaets;Bart Vanrumste","doi":"10.1109/TNSRE.2025.3545110","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3545110","url":null,"abstract":"Freezing of gait (FOG) is a debilitating symptom of Parkinson’s disease (PD), characterized by an absence or reduction in forward movement of the legs despite the intention to walk. Detecting FOG during free-living conditions presents significant challenges, particularly when using only inertial measurement unit (IMU) data, as it must be distinguished from voluntary stopping events that also feature reduced forward movement. Influences from stress and anxiety, measurable through galvanic skin response (GSR) and electrocardiogram (ECG), may assist in distinguishing FOG from normal gait and stopping. However, no study has investigated the fusion of IMU, GSR, and ECG for FOG detection. Therefore, this study introduced two methods: a two-step approach that first identified reduced forward movement segments using a Transformer-based model with IMU data, followed by an XGBoost model classifying these segments as FOG or stopping using IMU, GSR, and ECG features; and an end-to-end approach employing a multi-stage temporal convolutional network to directly classify FOG and stopping segments from IMU, GSR, and ECG data. Results showed that the two-step approach with all data modalities achieved an average F1 score of 0.728 and F1@50 of 0.725, while the end-to-end approach scored 0.771 and 0.759, respectively. However, no significant difference was found compared to using only IMU data in both approaches (p-values: 0.466 to 0.887). In conclusion, adding physiological data did not provide a statistically significant benefit in distinguishing between FOG and stopping. The limitations may be specific to GSR and ECG data, and may not generalize to other physiological modalities.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"956-965"},"PeriodicalIF":4.8,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902623","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalizing Muscle Tendon Parameters of Cerebral Palsy Patient’s Digital Model","authors":"Tinghan Xu;Yuanhao Liang;Lin Feng;Li Liu;Eric Yeung;Rong He;Michael To;Yong Hu","doi":"10.1109/TNSRE.2025.3544551","DOIUrl":"10.1109/TNSRE.2025.3544551","url":null,"abstract":"As computer science progresses, neuromusculoskeletal models are increasingly applied in clinical settings, particularly when studying abnormal characteristics in patients with cerebral palsy. Digital neuromusculoskeletal models enable researchers and clinicians to gain a deeper understanding of movement mechanisms, providing additional insights for diagnosis and treatment. While biomechanical simulation platforms like OpenSim offer standardized neuromusculoskeletal models for simulation, relying on generic healthy models to simulate movements in cerebral palsy patients can lead to inaccuracies. Therefore, personalized muscle-tendon parameters are essential for cerebral palsy patient models. In this study, we collected ultrasound video data of the semitendinosus muscle from two patients with cerebral palsy during the passive knee extension process. We proposed a muscle-tendon parameter personalization method and developed the individualized OpenSim models for the patients using this data. We validated the personalized models’ output fiber length and pennation angle through a series of hip flexion movement tests. The experimental results demonstrate that using the personalized muscle model for cerebral palsy patients produces muscle fiber length and pennation angle more closely aligned with ultrasound-measured values. After personalization, the RMSE between model output and ultrasound measurement of muscle fiber length and pennation angle decreased by 96.80% and 61.80%, respectively, averaged across both subjects. This study introduces a method for determining muscle-tendon parameters in cerebral palsy patients’ digital neuromusculoskeletal models, providing researchers and clinicians with more precise biomechanical information. These insights can better inform the treatment of cerebral palsy patients, ultimately enhancing therapeutic outcomes.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1079-1087"},"PeriodicalIF":4.8,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10900608","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Signal Characteristics, Motor Cortex Engagement, and Classification Performance of Combined Action Observation, Motor Imagery and SSMVEP (CAMS) BCI","authors":"Aravind Ravi;Paul Wolfe;James Tung;Ning Jiang","doi":"10.1109/TNSRE.2025.3544479","DOIUrl":"10.1109/TNSRE.2025.3544479","url":null,"abstract":"Motor imagery (MI)-based Brain-Computer Interfaces (BCIs) have shown promise in engaging the motor cortex for recovery. However, individual responses to MI-based BCIs are highly variable and relatively weak. Conversely, combined action observation (AO) and motor imagery (MI) paradigms have demonstrated stronger responses compared to AO or MI alone, along with enhanced cortical excitability. In this study, a novel BCI called Combined AO, MI, and Steady-State Motion Visual Evoked Potential (SSMVEP) (CAMS) was proposed. CAMS was designed based on gait observation and imagination. Twenty-five healthy volunteers participated in the study with CAMS serving as the intervention and SSMVEP checkerboard as the control condition. We hypothesized the CAMS intervention can induce observable increases in the negativity of the movement-related cortical potential (MRCP) associated with ankle dorsiflexion. MRCP components, including Bereitschaftspotential, were measured pre- and post-intervention. Additionally, the signal characteristics of the visual and motor responses were quantified. Finally, a two-class visual BCI classification performance was assessed. A consistent increase in negativity was observed across all MRCP components in signals over the primary motor cortex, compared to the control condition. CAMS visual BCI achieved a median accuracy of 83.8%. These findings demonstrate the ability of CAMS BCI to enhance cortical excitability in relation to movement preparation and execution. The CAMS stimulus not only evokes SSMVEP-like activity and sensorimotor rhythm but also enhances the MRCP. These findings contribute to the understanding of CAMS paradigm in enhancing cortical excitability, consistent and reliable classification performance holding promise for motor rehabilitation outcomes and future BCI design considerations.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1004-1013"},"PeriodicalIF":4.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10898016","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143556757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of 3D Stimuli With Frequency Ranges, Patterns, and Shapes on SSVEP-BCI Performance in Virtual Reality","authors":"Zihao Wei;Yanfei Lin;Jiayi Chen;Shuo Pan;Xiaorong Gao","doi":"10.1109/TNSRE.2025.3544308","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3544308","url":null,"abstract":"Traditional steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) systems offer stability and simplicity in evoking brain responses, but their practical utility is limited by immovable screens for visual stimuli. Virtual Reality (VR) technology provides a more natural and immersive environment to evoke SSVEP signals. However, the design methods for visual stimuli in VR environments remain to be explored, especially under the stereoscopic vision conditions. This study investigated the effects of 3D stimuli with frequency ranges, patterns, and shapes on the performance and user experiences of VR-SSVEP. There were four patterns including three-dimensional (3D) flicker, two-dimensional (2D) flicker, 3D checkerboard, and 3D quick response (QR) code with four shapes comprising cube, sphere, cylinder, and cone at low (9-15Hz), medium (18-24Hz), and high frequencies (30-36Hz). Both offline and online experiments were conducted to analyze the effects of different parameter combinations on SSVEP-BCI performance, and a questionnaire was exploited to evaluate user experiences. Compared to high frequency range, the low and medium frequency ranges had better performance and lower user experiences. 3D checkerboard and 3D QR code patterns showed significantly better user experiences than 3D and 2D flickers for all frequency ranges. With a high level of classification performance, 3D checkerboard and 3D QR code patterns in medium frequency range could synthetically enhance the system performance and user experiences. These results could provide significant value for SSVEP-BCI application in VR environments.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"890-899"},"PeriodicalIF":4.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10898078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143496527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simultaneous and Proportional Control Based on an Enhanced Musculoskeletal Model","authors":"Lizhi Pan;Diyi Liu;Ruyi Wang;Jinhua Li","doi":"10.1109/TNSRE.2025.3543912","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543912","url":null,"abstract":"Recently, the musculoskeletal model (MM) has been widely studied for decoding movement intent from electromyography (EMG) signals. However, the decoding performance of the MM is impaired for the coordinated movements of multiple degrees of freedom (DoFs) due to the crosstalk between signals of multiple muscles. To address this problem, this study proposed an enhanced MM for 3-DoF motion prediction by taking the “divide and conquer” (DC) strategy and integrating the non-negative matrix factorization (NMF) algorithm, which is named as DC-NMF-MM. The control signals of wrist flexion/extension and MCP flexion/extension were obtained from four independent muscles, and the control signals of wrist pronation/supination were obtained from eight-channel surface EMG signals. Eight non-disabled subjects were recruited for offline and online experiment. For offline experiment, another two MMs were established and taken as the control groups for validation of the proposed DC-NMF-MM, including the MM totally taking the NMF algorithm (T-NMF-MM) and that partly taking the NMF algorithm (P-NMF-MM) for predicting the wrist pronation/supination only. The Pearson’s correlation coefficient and the normalized root mean square error were employed to compare the prediction performance of three models. The results showed that the proposed method performs better than the other two models. Moreover, artificial neural network and linear regression model were established to compare with the proposed model and the results showed that DC-NMF-MM is more accurate in predicting joint Angle. For online experiment, a general 3-DOF musculoskeletal model based on DC-NMF-MM was established and the completion time, the number of overshoots, and the path efficiency were taken as evaluation indexes. The results further demonstrated the feasibility of the proposed method to achieve 3-DoF motion control. The proposed enhanced MM provides a prerequisite for the realization of clinical hand myoelectric control.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"847-857"},"PeriodicalIF":4.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10896736","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143496504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy of Transcranial Magnetic Stimulation in Post-Stroke Motor Recovery: Impact of Impairment Severity","authors":"Guiyuan Cai;Cailing Zhang;Jiayue Xu;Junbo Jiang;Gengbin Chen;Jialin Chen;Quan Liu;Guangqing Xu;Yue Lan","doi":"10.1109/TNSRE.2025.3543859","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543859","url":null,"abstract":"Stroke is a leading cause of impairment, with 70% of survivors experiencing upper limb motor deficits. While transcranial magnetic stimulation (TMS) is widely used in rehabilitation, the impact of impairment severity on treatment outcomes remains unclear. This study evaluated TMS effectiveness in post-stroke motor impairment and explored its neural mechanisms. Fifty-five stroke patients were divided into TMS (n =27) and control (n =28) groups. The TMS group received two weeks of intermittent theta-burst stimulation (iTBS), while controls received sham stimulation. Patients were stratified into mild/moderate (Fugl-Meyer Assessment [FMA] <inline-formula> <tex-math>$ge 30$ </tex-math></inline-formula>) and severe (FMA <30) impairment subgroups. Motor function and electroencephalography (EEG) metrics were assessed before and after treatment. Overall FMA improvement showed no difference between groups, but the TMS-mild/moderate impairment group demonstrated significantly greater improvement compared to others. This group exhibited higher global and local alpha band power and global alpha efficiency. FMA improvement positively correlated with local alpha power changes. TMS of ipsilesional M1 improves motor function in mild/moderate impairments but shows limited efficacy in severe cases. EEG suggests TMS promotes recovery by modulating alpha activity and enhancing network efficiency. These findings support stratified treatment approaches and highlight the need for alternative interventions in severe impairment.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"881-889"},"PeriodicalIF":4.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10896702","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143496465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"mGNN-bw: Multi-Scale Graph Neural Network Based on Biased Random Walk Path Aggregation for ASD Diagnosis","authors":"Wenqiu Pan;Guang Ling;Feng Liu","doi":"10.1109/TNSRE.2025.3543177","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543177","url":null,"abstract":"In recent years, computationally assisted diagnosis for classifying autism spectrum disorder (ASD) and typically developing (TD) individuals based on neuroimaging data, such as functional magnetic resonance imaging (fMRI), has garnered significant attention. Studies have shown that long-range functional connectivity patterns in ASD patients exhibit significant abnormalities, and individual brain networks display considerable heterogeneity. However, current graph neural networks (GNNs) used in ASD research have failed to adequately capture long-range connectivity and have overlooked individual differences. To address these limitations, this study proposes a novel multi-scale graph neural network based on biased random walks (mGNN-bw). The model introduces a co-optimization strategy between sub-models and the main model, leveraging node pooling scores from sub-models to guide biased random walks, effectively capturing long-range connectivity. By constructing high-order brain networks through path encoding and aggregation, and integrating them with low-order brain networks based on Pearson correlation, the model achieves a robust multi-scale feature representation. Experimental results on the publicly available ABIDE I dataset demonstrate the superior performance of our approach, achieving accuracy rates of 74.8% and 73.2% using CC200 and AAL atlases, respectively, outperforming existing methods. Additionally, the model identifies key ASD-associated brain regions, including the frontal lobe, insula, cingulate, and calcarine, supported by existing research. The proposed method significantly contributes to the clinical diagnosis of ASD.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"900-910"},"PeriodicalIF":4.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10896757","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Changes in Kinematic and Spatiotemporal Gait Parameters With a Biarticular Lower Limb Exosuit for Adolescents With Crouch Gait During Level Walking and Stair Climbing","authors":"Chiara Basla;Philippe Dürrenberger;Peter Wolf;Robert Riener;Hubertus J. A. van Hedel","doi":"10.1109/TNSRE.2025.3543606","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543606","url":null,"abstract":"Crouch gait is a prevalent walking abnormality among children with cerebral palsy, characterized by excessive knee and hip flexion during walking. This condition often limits children’s engagement in physical activities and daily life. Current exoskeleton solutions targeting the knee joint in this population are either tethered or bulky, hindering practical integration into daily routines. In this cross-sectional study, we evaluated the impact of a biarticular cable-driven exosuit, originally designed for adults, on the gait pattern of adolescents with crouch gait. Participants completed level walking and stair climbing trials under three conditions: without the exosuit (noMyo), with the exosuit inactive (MyoOff), and with the exosuit active (MyoOn). Kinematic and spatiotemporal gait metrics were analyzed using 3D motion capture. Five male adolescents with mild to moderate crouch participated. Results revealed significant improvements in mean knee and hip extension during the assisted phase (5 to 50% of the gait) with MyoOn compared to noMyo, increasing by 6 (range: 0 - 12) and 12 (range: 4 - 24) degrees, respectively, during level walking. During stair climbing, knee and hip extension improved in the stance phase of the trailing leg in the MyoOn condition compared to MyoOff. Only the hip angles improved in the MyoOn condition compared to noMyo. Spatiotemporal metrics showed no improvement. Stride length shortened significantly in both MyoOn and MyoOff. These findings demonstrate the exosuit’s potential to address extension deficits in crouch gait, although its weight may limit improvements in spatiotemporal gait characteristics. Developing a lighter, child-specific version could expand accessibility to a broader pediatric population.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"966-974"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892316","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Control to Suppress Epileptic Seizures in the Amygdala: In Silico Investigation Using a Network of Izhikevich Neurons","authors":"Gabriel da Silva Lima;Vinícius Rosa Cota;Wallace Moreira Bessa","doi":"10.1109/TNSRE.2025.3543756","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543756","url":null,"abstract":"Closed-loop electricalstimulation of brain structures is one of the most promising techniques to suppress epileptic seizures in drug-resistant refractory patients who are also ineligible to ablative neurosurgery. In this work, an intelligent controller is presented to block the aberrant activity of a network of Izhikevich neurons of three different types, used here to model the electrical activity of the basolateral amygdala during ictogenesis, i.e. its transition from asynchronous to hypersynchronous state. A Lyapunov-based nonlinear scheme is used as the main framework for the proposed controller. To avoid the issue of accessing each neuron individually, local field potentials are used to gain insight into the overall state of the Izhikevich network. Artificial neural networks are integrated into the control scheme to manage unknown dynamics and disturbances caused by brain electrical activity that are not accounted for in the model. Four different cases of ictogenesis induction were tested. The results show the efficacy of the proposed control strategy to suppress epileptic seizures and suggest its capability to address both patient-specific and patient-to-patient variability.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"868-880"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892294","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the Benefit of FMG and EMG Sensor Fusion for Gesture Recognition Using Cross-Subject Validation","authors":"Maurice Rohr;Jad Haidamous;Niklas Schäfer;Stephan Schaumann;Bastian Latsch;Mario Kupnik;Christoph Hoog Antink","doi":"10.1109/TNSRE.2025.3543649","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3543649","url":null,"abstract":"Hand gestures are a natural form of human communication, making gesture recognition a sensible approach for intuitive human-computer interaction. Wearable sensors on the forearm can be used to detect the muscle contractions that generate these gestures, but classification approaches relying on a single measured modality lack accuracy and robustness. In this work, we analyze sensor fusion of force myography (FMG) and electromyography (EMG) for gesture recognition. We employ piezoelectric FMG sensors based on ferroelectrets and a commercial EMG system in a user study with 13 participants to measure 66 distinct hand movements with 10ms labelling precision. Three classification tasks, namely flexion and extension, single finger, and all finger movement classification, are performed using common handcrafted features as input to machine learning classifiers. Subsequently, the evaluation covers the effectiveness of the sensor fusion using correlation analysis, classification performance based on leave-one-subject-out-cross-validation and 5x2cv-t-tests, and its effects of involuntary movements on classification. We find that sensor fusion leads to significant improvement (42% higher average recognition accuracy) on all three tasks and that both sensor modalities contain complementary information. Furthermore, we confirm this finding using reduced FMG and EMG sensor sets. This study reinforces the results of prior research about the effectiveness of sensor fusion by performing meticulous statistical analyses, thereby paving the way for multi-sensor gesture recognition in assistance systems.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"935-944"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892285","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535527","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}