Query：
学者姓名：李玉榕
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Traditional muscle strength training instruments often rely on torque-based feedback to guide exercises, which can introduce delays in system response and result in discomfort due to hysteresis effects. Surface electromyography (sEMG) signals were used as control inputs to overcome the lag in torque-based muscle strength training instruments. The sEMG is generated 20-80 ms before movement, which is called "muscle electromechanical delay." If the torque can be effectively predicted during this period, the lag effect can be significantly reduced, thus improving the effectiveness and comfort of training. We, therefore, proposed a multistep ahead (MSA) model based on the nonlinear autoregressive network with exogenous inputs (NARX) dynamic recurrent neural network. It predicted torques using sEMG, and allowed natural control of the instrument. The results showed that the normalized root-mean-square error (NRMSE) was lower than 0.1167, and the Pearson correlation coefficients (rho) exceeded 0.9444, even when the ahead steps achieved 35. The intrasubject and the intersubject validation demonstrated significantly lower NRMSE ( p <0.05) and higher rho ( p < 0.05) of the MSA model, compared with some state-of-theart recursive models and typical models without autoregression items. It proves that the MSA can accurately predict the motion. Meanwhile, the introduction of the sEMG signal as a control source significantly reduced the root-mean-square jerk (RMSJ) of the torque, demonstrating smoother motion. The experimental results revealed that the one-step-ahead model achieved an average response time of 3.73 ms, which is markedly lower than the muscle electromechanical delay. The response time increased by an average of approximately 0.068 ms per additional ahead step. In conclusion, the proposed EMG-driven muscle strength training instrument enables natural muscle strength training.
Keyword ：
Brain modeling Brain modeling Computational modeling Computational modeling Electromyography Electromyography Instruments Instruments Limbs Limbs Muscles Muscles Muscle strength training instrument Muscle strength training instrument neural network neural network nonlinear autoregressive network with exogenous inputs (NARX) nonlinear autoregressive network with exogenous inputs (NARX) Predictive models Predictive models Sensors Sensors surface electromyography (sEMG) surface electromyography (sEMG) Torque Torque torque prediction torque prediction Training Training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Yurong , Lin, Xiaofeng , Liu, Qiang et al. Natural Control of Muscle Strength Training Instrument Based on EMG-Driven Multistep Ahead Models [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| MLA | Li, Yurong et al. "Natural Control of Muscle Strength Training Instrument Based on EMG-Driven Multistep Ahead Models" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 74 (2025) . |
| APA | Li, Yurong , Lin, Xiaofeng , Liu, Qiang , Zheng, Nan , Tan, Jiyu , Zhan, Miaoqin . Natural Control of Muscle Strength Training Instrument Based on EMG-Driven Multistep Ahead Models . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Background: Electrocardiogram (ECG) is crucial in diagnosing and preventing heart diseases. However, its efficacy is compromised by the interference of the external environment, leading to potential misdiagnoses. Thus, it is crucial to remove the noise in ECGs. Recently, deep-learning based ECGs denoising approaches have achieved impressive performance, however, they only considered the time-domain information of ECGs. Methods: In this work, we propose a Frequency Information Enhanced Half Instance Normalization Network (FIEHINet) which integrates knowledge of both time and frequency domains into a deep-learning model for ECG signal denoising. Two branches are employed to extract time and frequency features for noise eliminating, respectively. Then the ECG signals are reconstructed based on the fused features. Furthermore, masked signal training is introduced to improve the generalization ability. Results: In order to evaluate the proposed method, ECGs used are chosen from five different databases. The proposed method for ECG signal denoising achieved Sum of Squared Distances scores of 3.95 +/- 7.04, 2.04 +/- 3.20, and 0.998 +/- 1.579 for three kinds of noise intensities. Meanwhile, the classification experimental results of the processed dataset with the proposed method are 3.8 % higher in F1 score than the original dataset. Conclusion: A model for removing mixed noises is successfully developed and tested. Significance: This study presents an ECG denoising technique based on Half Instance Normalization, time- -frequency information, and masked signal training, which can improve ECG interpretation and potentially reduce misdiagnoses in clinical practice.
Keyword ：
Denoising Denoising Electrocardiograms Electrocardiograms Frequency Information Enhanced (FIE) Frequency Information Enhanced (FIE) Half Instance Normalization (HIN) Half Instance Normalization (HIN) Neural Network Neural Network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gao, Ning , Li, Yurong , Zheng, Nan et al. Frequency information enhanced half instance normalization network for denoising electrocardiograms [J]. | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2025 , 102 . |
| MLA | Gao, Ning et al. "Frequency information enhanced half instance normalization network for denoising electrocardiograms" . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL 102 (2025) . |
| APA | Gao, Ning , Li, Yurong , Zheng, Nan , Shi, Wuxiang , Cai, Dan , Huang, Xiaoying et al. Frequency information enhanced half instance normalization network for denoising electrocardiograms . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2025 , 102 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
目的 基于OpenSim软件开发建立1个包含双接触点、3个自由度膝关节的个性化肌肉骨骼模型,估测膝关节负荷,为临床膝骨关节炎(KOA)患者的精准化诊断及个体化康复方案的制订提供可靠依据.方法 利用由斯坦福大学授权公开、加州拉霍亚市Scripps诊所希利矫形研究与教育中心发布的"膝关节体内负荷预测挑战赛"公开数据集,纳入4例接受全膝关节置换术(TKA)并植入压力检测仪器的受试者,以OpenSim模型库中的通用模型gait2392为基础升级搭建,新模型包含28个关节和43个自由度,并调整膝关节结构,使其具有屈曲-伸展、内收-外展、内旋-外旋3个方向自由度,增添了单臂4个关节、7个自由度能够扭矩驱动的上肢结构,并将股骨与胫骨间由单接触点调整为双接触点.通过模型缩放、逆向运动学分析、逆向动力学分析、残差缩减处理、肌肉控制和肌肉分析等,综合考虑步态中外部力和体内肌力的贡献,计算胫股关节内侧、外侧接触力.采用Matlab 2018b进行统计学分析,计算模型估计结果与植入假体测量结果的Pearson相关系数、均方根误差以及标准差,验证本研究建立的肌骨模型的有效性.结果 4名受试者共获得21次完整步态试验数据,受试者JW、DM、PS、SC步态周期平均时长分别为(1.18±0.03)、(1.18±0.08)、(1.09±0.02)、(1.14±0.04)s;内侧、外侧、总接触力估计值与测量值的相关系数平均值分别为(0.921±0.079)、(0.817±0.084)、(0.930±0.066),均方根误差的平均值分别为(0.336±0.146)、(0.332±0.043)、(0.442±0.160)BW;内侧、外侧接触力峰值的估计值与测量值均方根误差的平均值分别为(0.43±0.25)、(0.34±0.24)BW,峰值出现时间误差的平均值分别为(44.09±34.66)、(67.52±61.19)ms.结论 利用所建立的双接触点、3个自由度的膝关节全身OpenSim肌肉骨骼模型能够生成肌肉驱动的步态模拟,得到可靠的胫股关节接触力,为精准监测胫股关节负荷、临床康复方案的制订和持续改进假体设计等提供重要依据.
Keyword ：
OpenSim OpenSim 内侧、外侧接触力 内侧、外侧接触力 肌肉骨骼模型 肌肉骨骼模型 胫股关节 胫股关节 行走步态 行走步态
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王晓玲 , 简家伟 , 谢秋蓉 et al. 基于OpenSim肌骨建模估算胫股关节接触力 [J]. | 康复学报 , 2025 , 35 (1) : 59-68 . |
| MLA | 王晓玲 et al. "基于OpenSim肌骨建模估算胫股关节接触力" . | 康复学报 35 . 1 (2025) : 59-68 . |
| APA | 王晓玲 , 简家伟 , 谢秋蓉 , 连章汇 , 郭春明 , 郭洁梅 et al. 基于OpenSim肌骨建模估算胫股关节接触力 . | 康复学报 , 2025 , 35 (1) , 59-68 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this paper, a novel dynamic multiobjective optimization algorithm (DMOA) with a cascaded fuzzy system (CFS) is developed, which aims to promote objective knowledge transfer from an innovative perspective of comprehensive information characterization. This development seeks to overcome the bottleneck of negative transfer in evolutionary transfer optimization (ETO)-based algorithms. Specifically, previous Pareto solutions, center- and knee-points of multi-subpopulation are adaptively selected to establish the source domain, which are then assigned soft labels through the designed CFS, based on a thorough evaluation of both convergence and diversity. A target domain is constructed by centroid feed-forward of multi-subpopulation, enabling further estimations on learning samples with the assistance of the kernel mean matching (KMM) method. By doing so, the property of non-independently identically distributed data is considered to enhance efficient knowledge transfer. Extensive evaluation results demonstrate the reliability and superiority of the proposed CFS-DMOA in solving dynamic multiobjective optimization problems (DMOPs), showing significant competitiveness in terms of mitigating negative transfer as compared to other state-of-the-art ETO-based DMOAs. Moreover, the effectiveness of the soft labels provided by CFS in breaking the “either/or” limitation of hard labels is validated, facilitating a more flexible and comprehensive characterization of historical information, thereby promoting objective and effective knowledge transfer IEEE
Keyword ：
cascaded fuzzy system cascaded fuzzy system dynamic multiobjective optimization algorithm (DMOA) dynamic multiobjective optimization algorithm (DMOA) Evolutionary transfer optimization (ETO) Evolutionary transfer optimization (ETO) Fuzzy systems Fuzzy systems Heuristic algorithms Heuristic algorithms information characterization information characterization Knowledge transfer Knowledge transfer negative transfer negative transfer Optimization Optimization Prediction algorithms Prediction algorithms Sociology Sociology Statistics Statistics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, H. , Wang, Z. , Zeng, N. et al. Promoting Objective Knowledge Transfer: A Cascaded Fuzzy System for Solving Dynamic Multiobjective Optimization Problems [J]. | IEEE Transactions on Fuzzy Systems , 2024 , 32 (11) : 1-15 . |
| MLA | Li, H. et al. "Promoting Objective Knowledge Transfer: A Cascaded Fuzzy System for Solving Dynamic Multiobjective Optimization Problems" . | IEEE Transactions on Fuzzy Systems 32 . 11 (2024) : 1-15 . |
| APA | Li, H. , Wang, Z. , Zeng, N. , Wu, P. , Li, Y. . Promoting Objective Knowledge Transfer: A Cascaded Fuzzy System for Solving Dynamic Multiobjective Optimization Problems . | IEEE Transactions on Fuzzy Systems , 2024 , 32 (11) , 1-15 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
心电信号广泛应用于心脏疾病的医学检测中，可穿戴动态心电监测设备可以实现对心律失常的风险识别并预警. 相比于静息心电信号，动态心电信号在采集过程中会受到更大运动伪迹的干扰，这些干扰会覆盖心电信号的关键信息，限制其临床应用. 本文兼顾心电信号局部和全局特征，利用其周期性，研究了一种将心电信号低频PT波和高频QRS波群分开处理的两步式自适应阈值滤波算法，适用于单通道心电信号中的运动伪迹滤除. 第一步先通过多分辨率阈值初步抑制心电信号低频部分中的运动伪迹；第二步，对受运动伪迹影响而不平衡的QRS波进行自适应阈 值修复，通过对QRS波形调节，减少心电信号中高频部分运动伪迹，同时设置自适应阈值对心电信号P波、T波对应的小波系数进行处理，超出自适应阈值范围的小波系数通过波形缩放进行调整，进一步抑制低频运动伪迹. 研究通过不同心电数据库评估算法的性能 . 在输入信噪比从-10 ~10 dB时，心电信号信噪比提升了10.912 2 dB和 4.391 2 dB，滤波后心电信号与纯净心电信号的相关系数分别为 0.687 6和 0.978 3，提取的运动伪迹与原运动伪迹相关系数分别为0.953 0和0.852 9. 实验结果表明，算法在不同噪声水平下，利用自适应阈值的优点，能有效复原受运动伪迹污染的心电信号波形特征，最大限度保留心电信号的临床信息，可作为可穿戴心电设备滤除运动伪迹的有效工具.
Keyword ：
信号处理 信号处理 小波变换 小波变换 心电信号 心电信号 自适应阈值 自适应阈值 运动伪迹 运动伪迹
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 吕建行 , 李玉榕 , 陈建国 et al. 两步式自适应阈值法滤除心电信号中运动伪迹 [J]. | 电子学报 , 2024 . |
| MLA | 吕建行 et al. "两步式自适应阈值法滤除心电信号中运动伪迹" . | 电子学报 (2024) . |
| APA | 吕建行 , 李玉榕 , 陈建国 , 高宁 . 两步式自适应阈值法滤除心电信号中运动伪迹 . | 电子学报 , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
ObjectiveThe objective of this study was to investigate the activity and connectivity of cerebral and cerebellar cortices underlying the sensory trick (ST) effects in patients with cervical dystonia (CD), using electroencephalography (EEG).MethodsWe recruited 15 CD patients who exhibited clinically effective ST and 15 healthy controls (HCs) who mimicked the ST maneuver. EEG signals and multiple-channel electromyography (EMG) were recorded simultaneously during resting and acting stages. EEG source analysis and functional connectivity were performed. To account for the effects of sensory processing, we calculated relative power changes as the difference in power spectral density between resting and the maneuver execution.ResultsST induced a decrease in low gamma (30-50 Hz) spectral power in the primary sensory and cerebellar cortices, which remained lower than in HCs during the maintenance period. Compared with HCs, patients exhibited consistently strengthened connectivity within the sensorimotor network during the maintenance period, particularly in the primary sensory-sensorimotor cerebellum connection.InterpretationThe application of ST resulted in altered cortical excitability and functional connectivity regulated by gamma oscillation in CD patients, suggesting that this effect cannot be solely attributed to motor components. The cerebellum may play important roles in mediating the ST effects.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cai, Nai-Qing , Shi, Wu-Xiang , Chen, Ru-Kai et al. Cerebral-Cerebellar Cortical Activity and Connectivity Underlying Sensory Trick in Cervical Dystonia [J]. | ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY , 2024 , 11 (10) : 2633-2644 . |
| MLA | Cai, Nai-Qing et al. "Cerebral-Cerebellar Cortical Activity and Connectivity Underlying Sensory Trick in Cervical Dystonia" . | ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY 11 . 10 (2024) : 2633-2644 . |
| APA | Cai, Nai-Qing , Shi, Wu-Xiang , Chen, Ru-Kai , Chen, Bo-Li , Li, Yu-Rong , Wang, Ning . Cerebral-Cerebellar Cortical Activity and Connectivity Underlying Sensory Trick in Cervical Dystonia . | ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY , 2024 , 11 (10) , 2633-2644 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Brain -computer interface (BCI) is an emerging technology which provides a road to control communication and external devices. Electroencephalogram (EEG) -based motor imagery (MI) tasks recognition has important research significance for stroke, disability and others in BCI fields. However, enhancing the classification performance for decoding MI -related EEG signals presents a significant challenge, primarily due to the variability across different subjects and the presence of irrelevant channels. To address this issue, a novel hybrid structure is developed in this study to classify the MI tasks via deep separable convolution network (DSCNN) and bidirectional long short-term memory (BLSTM). First, the collected time -series EEG signals are initially processed into a matrix grid. Subsequently, data segments formed using a sliding window strategy are inputted into proposed DSCNN model for feature extraction (FE) across various dimensions. And, the spatial -temporal features extracted are then fed into the BLSTM network, which further refines vital time -series features to identify five distinct types of MI -related tasks. Ultimately, the evaluation results of our method demonstrate that the developed model achieves a 98.09% accuracy rate on the EEGMMIDB physiological datasets over a 4 -second period for MI tasks by adopting full channels, outperforming other existing studies. Besides, the results of the five evaluation indexes of Recall, Precision, Test-auc, and F1 -score also achieve 97.76%, 97.98%, 98.63% and 97.86%, respectively. Moreover, a Gradient -class Activation Mapping (GRAD -CAM) visualization technique is adopted to select the vital EEG channels and reduce the irrelevant information. As a result, we also obtained a satisfying outcome of 94.52% accuracy with 36 channels selected using the Grad -CAM approach. Our study not only provides an optimal trade-off between recognition rate and number of channels with half the number of channels reduced, but also it can also advances practical application research in the field of BCI rehabilitation medicine, effectively.
Keyword ：
Data analysis Data analysis Data Processing Data Processing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Jixiang , Wang, Zhaoxuan , Li, Yurong . Recognition of EEG-based movement intention combined with channel selection adopting deep learning methods [J]. | JOURNAL OF INSTRUMENTATION , 2024 , 19 (5) . |
| MLA | Li, Jixiang et al. "Recognition of EEG-based movement intention combined with channel selection adopting deep learning methods" . | JOURNAL OF INSTRUMENTATION 19 . 5 (2024) . |
| APA | Li, Jixiang , Wang, Zhaoxuan , Li, Yurong . Recognition of EEG-based movement intention combined with channel selection adopting deep learning methods . | JOURNAL OF INSTRUMENTATION , 2024 , 19 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
ECG (ElectroCardioGram) signals are widely used in the medical detection of heart disease, and wearable dynamic ECG monitoring devices enable the detection and early warning of cardiac arrhythmias. Compared to resting ECG signals, dynamic ECG signals are more susceptible to interference from motion artifacts during the data acquisition process. These motion artifacts can obscure critical information within the ECG signal, limiting its clinical utility. In this paper, taking into account the local and global characteristics of the ECG signal and using its periodicity, a two-stage adaptive threshold filtering algorithm is investigated to process the low-frequency PT wave and the high-frequency QRS wave group separately, which is suitable for motion artifact filtering in single-channel ECG signal. In the first step, motion artifacts in the low-frequency part of the ECG signal are suppressed by a multi-resolution threshold. In the second step, the imbalanced QRS wave affected by motion artifacts is repaired by adaptive threshold, adjusting the QRS waveform to reduce motion artifacts in the high-frequency portion of the ECG signal, while setting adaptive thresholds to process the wavelet coefficients corresponding to the P-wave and T-wave of the ECG signal. Wavelet coefficients beyond the adaptive threshold range are adjusted via waveform scaling to further suppress the low-frequency motion artifacts. In this paper, the performance of the algorithm is evaluated using different ECG databases. When the input SNR changes from -10~10 dB, the SNR of the ECG signal increases by 10.912 2 dB and 4.391 2 dB, respectively, and the correlation coefficients between the filtered ECG signal and the pure ECG signal are 0.687 6 and 0.978 3, respectively, the correlation coefficients between the extracted motion artifacts and the original motion artifacts are 0.953 0 and 0.852 9, respectively. The experimental results show that under different noise levels, the proposed algorithm can effectively recover the ECG waveform characteristics contaminated by motion artifacts by exploiting the advantages of adaptive threshold, and retain the clinical information of ECG signals to the maximum extent, and can be used as an effective tool for filtering motion artifacts in wearable ECG devices. © 2024 Chinese Institute of Electronics. All rights reserved.
Keyword ：
adaptive threshold adaptive threshold electrocardiogram electrocardiogram motion artifact motion artifact signal processing signal processing wavelet transform wavelet transform
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lü, J.-H. , Li, Y.-R. , Chen, J.-G. et al. ECG Motion Artifact Filtering Based on Two-Stage Adaptive Threshold Rules; [两步式自适应阈值法滤除心电信号中运动伪迹] [J]. | Acta Electronica Sinica , 2024 , 52 (10) : 3493-3506 . |
| MLA | Lü, J.-H. et al. "ECG Motion Artifact Filtering Based on Two-Stage Adaptive Threshold Rules; [两步式自适应阈值法滤除心电信号中运动伪迹]" . | Acta Electronica Sinica 52 . 10 (2024) : 3493-3506 . |
| APA | Lü, J.-H. , Li, Y.-R. , Chen, J.-G. , Gao, N. . ECG Motion Artifact Filtering Based on Two-Stage Adaptive Threshold Rules; [两步式自适应阈值法滤除心电信号中运动伪迹] . | Acta Electronica Sinica , 2024 , 52 (10) , 3493-3506 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The primary aim of this study is to construct a state-space model that reduces the complexity of the human sensorimotor control system and explore motion control theory based on manifolds. Low-dimensional neural and muscle manifolds, representing the population activity of the brain and muscles, quantify the sensorimotor function of the human cortex, revealing hidden information about how the brain controls movement. This study used EEG and EMG signals from 25 participants during a card grabbing task. Preferential subspace recognition (PSID) algorithm was used to construct a state space model of subjects to study the neural computational strategies for sensorimotor control in the preparation and execution phases of motion, as well as the differences between brain and muscle population activity. The results show that from the preparation stage to the execution stage, the population activity of cortical muscles follows the orthogonal neural computation strategy in the subspace. The degree of trajectory entanglement between neural manifolds and muscle manifolds is greater than that during exercise preparation. Moreover, neural manifolds are less entangled than muscle manifolds and show a more stable state in structure. These results show that the adopted approach effectively reveals the orthogonal neural mechanisms of brain control during movement, highlighting the differences in control output and feedback input in sensorimotor control. This offers a new perspective on how the brain controls complex movements. © 2024 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Tan, J. , Li, Y. , Li, J. et al. Modeling and Analyzing the Manifolds of Cortical-Muscle During Card-Grabbing by Preferential Subspace Identification [未知]. |
| MLA | Tan, J. et al. "Modeling and Analyzing the Manifolds of Cortical-Muscle During Card-Grabbing by Preferential Subspace Identification" [未知]. |
| APA | Tan, J. , Li, Y. , Li, J. , Zheng, N. . Modeling and Analyzing the Manifolds of Cortical-Muscle During Card-Grabbing by Preferential Subspace Identification [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Human Kinesiology analysis is essential for understanding biomechanical loads in rehabilitation, injury prevention, and diagnosis. However, traditional marker-based motion capture systems are suboptimal due to high equipment and time costs, as well as the need for specialized expertise. Although OpenSim can perform detailed kinematic analyses using musculoskeletal models, integrating these analyses seamlessly with sparse human key points derived from computer vision remains challenging. Additionally, the current triangulation methods based on direct linear transformation (DLT) have limitations in accuracy and generalization ability. While learnable triangulation methods can extract complex features from images and significantly improve the accuracy of identifying and locating human nodes, they still lack limb length constraints and require calibration for each inference. In order to solve the above problems, in this work, we apply a triangulation method combining graph convolutional network with joint context constraints and camera pose distribution to human kinematics analysis, which fully considers the bone length constraints and joint connection relations, and improves the reasoning ability of the model under different camera parameter datasets. In addition, we fine-tuned the backbone network using relevant data with foot markers to suit the needs of kinesiology analysis. Finally, the output key points of the triangulation network is sent into the deep learning network to obtain the corresponding anatomical markers, and the results in the visual field are better combined with the musculoskeletal model provided by OpenSim, and more accurate kinematic parameters are obtained. © 2024 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, C. , Li, Y. , Ye, W. et al. Human Kinematics Analysis by Markerless Vision Based on OpenSim [未知]. |
| MLA | Zhang, C. et al. "Human Kinematics Analysis by Markerless Vision Based on OpenSim" [未知]. |
| APA | Zhang, C. , Li, Y. , Ye, W. , Huang, G. . Human Kinematics Analysis by Markerless Vision Based on OpenSim [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
