Paper Titles
Comparative Evaluation of the Effects of Yttrium Stabilized Zirconia Nanoparticles (YSZrO2- NP) and Porcelain Particles on Property Enhancement of Polymethylmethacrylate (PMMA) Denture Composites
p.21
Optimization of Silver Nanoparticle Synthesis Using S. Amaranthoides Leaf Extract via Response Surface Methodology for Enhanced Antibacterial Applications
p.43
Optimizing Dental Implant Viability with SLA and Anodizing Surface Treatments for Advanced Biological Adhesion, Enhanced Osseointegration, and Stress Resistance
p.63
MRI Measurements of the Cartilage Contact Pattern of the Glenohumeral Joint During Rotation with Abduction under Static Conditions In Vivo
p.79
Development of a Low Cost and Locally Sourced Functional Prosthetic Hand
p.89
Development of Personalized External Breast Prosthesis Prototype Using 3D Modeling in Unilateral Post-Mastectomy Patient
p.109
Motion Intention Recognition Method Based on GWO-AdaBoost-GRU for Lower Extremity Exoskeleton
p.119
Dynamic Biomechanical Consequences of Hallux Valgus: A Multimodal Investigation of Lower Limb Compensation Patterns
p.133
Modular Prototype of a Canine Prosthesis through the Simulation of a Transradial Amputation Case
p.153

Motion Intention Recognition Method Based on GWO-AdaBoost-GRU for Lower Extremity Exoskeleton

Article Preview

Abstract:

To meet the requirements of the lower limb exoskeleton robot working in coordination with the human body and improve the human-machine interaction performance, a lower limb motion intention recognition method based on the dual-stage joint optimization of the Gated Recurrent Unit (GRU) neural network by the Grey Wolf Optimization (GWO) and the Adaptive Boosting (AdaBoost) algorithm is proposed, and the GWO-AdaBoost-GRU intention recognition model is constructed. The Surface electromyography signals of six lower limb movements are collected and processed respectively by the CEEMDAN-WT joint denoising, activity segment extraction, and feature extraction, and the feature vector dataset is constructed as the model input. To comprehensively verify the performance of the GWO-AdaBoost-GRU model, it is compared with the GRU and GWO-GRU models, and an application verification is carried out by building a lower limb exoskeleton rehabilitation system. The experiments show that the average recognition accuracy of the GWO-AdaBoost-GRU model is 95.5%, which is 8.1% higher than that of the GRU model and 3.2% higher than that of the GWO-GRU model. Moreover, in the practical application of the lower limb rehabilitation institution, the GWO-AdaBoost-GRU intention recognition model has high accuracy, can accurately recognize the movement intentions of the subjects, and complete the designated rehabilitation movements in conjunction with the rehabilitation system, demonstrating excellent application performance.

You might also be interested in these eBooks
Journal of Biomimetics, Biomaterials and Biomedical Engineering Vol. 70 View Preview

Info:

Periodical:

Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 70)

Pages:

119-132

DOI:

https://doi.org/10.4028/p-7Djr4T

Citation:

Cite this paper

Online since:

January 2026

Authors:

Bing Yan Cui*, Lin Shang, Wen Jing Li, Wei Ying Wu, Shi Long Zhang

Keywords:

Adaptive Boosting Algorithm, Gated Recurrent Unit, Grey Wolf Optimization Algorithm, Intention Recognition, SEMG

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] Han Y, Wang X, Jia S, Lower limb exoskeleton robot technology , Nanjing Southeast University Press, China, 2019.

Google Scholar

[2] Meng L, Dong H, Huo J, et al. Soft exoskeleton robot facing to lower-imb rehabilitation: a narrative review, J. Chinese Journal of Scientific Instrument, 2021, 42(04): 206-217.

Google Scholar

[3] Tang L, Yang X, Wang R, et al. An Attention Mechanism-Based CNN-LSTM Framework for Lower Limb Knee Joint Angle Prediction, J. Journal of Data Acquisition & Processing, 2024, 39(4).

Google Scholar

[4] Corvini G, Conforto S. A Simulation Study to Assess the Factors of Influence on Mean and Median Frequency of sEMG Signals during Muscle Fatigue, J. Sensors, 2022, 22(17): 6360.

DOI: 10.3390/s22176360

Google Scholar

[5] Reaz M B I, Hussain M S, Mohd-Yasin F. Techniques of EMG signal analysis: detection, processing, classification and applications (Correction), J. Biological procedures online, 2006, 8: 163-163.

DOI: 10.1251/bpo124

Google Scholar

[6] Tu P, Li J, Wang H. Lower limb motion recognition with improved svm based on surface electromyography, J. Sensors, 2024, 24(10): 3097.

DOI: 10.3390/s24103097

Google Scholar

[7] Chowdhury R H, Reaz M B I, Ali M A B M, et al. Surface electromyography signal processing and classification techniques, J. Sensors, 2013, 13(9): 12431-12466.

DOI: 10.3390/s130912431

Google Scholar

[8] Gao F, Tian T, Yao T, et al. Human gait recognition based on multiple feature combination and parameter optimization algorithms, J. Comput Intell Neurosci.2021 Feb 27;2021:6693206.

Google Scholar

[9] Guo X D, Zhong F Q, Xiao J R, et al. Adaptive Random Forest for Gait Prediction in Lower Limb Exoskeleton, J. Journal of Biomimetics, Biomaterials and Biomedical Engineering, 2024, 64: 55-67.

DOI: 10.4028/p-q2hybx

Google Scholar

[10] Chen R, Chen Y Z, Guo W, et al. sEMG-based gesture recognition using GRU with strong robustness against forearm posture, C. //2021 IEEE International Conference on Real-time Computing and Robotics (RCAR). IEEE, 2021: 275-280.

DOI: 10.1109/rcar52367.2021.9517639

Google Scholar

[11] Chen W, Jiang Z, Guo H, et al. Fall detection based on key points of human-skeleton using openpose, J. Symmetry, 2020, 12(5): 744.

DOI: 10.3390/sym12050744

Google Scholar

[12] Lin C, Chen C, Cui Z, et al. A Bi-GRU-attention neural network to identify motor units from high-density surface electromyographic signals in real time, J. Frontiers in Neuroscience, 2024, 18: 1306054.

DOI: 10.3389/fnins.2024.1306054

Google Scholar

[13] Kumar R, Gupta A, Muthukrishnan S P, et al. sEMG-Driven Physics-Informed Gated Recurrent Networks for Modeling Upper Limb Multi-Joint Movement Dynamics, J. arXiv preprint arXiv:2408.16599, 2024.

Google Scholar

[14] Verma A R, Gupta B. A novel approach adaptive filtering method for electromyogram signal using Gray Wolf optimization algorithm, J. SN Applied Sciences, 2020, 2(1): 16.

DOI: 10.1007/s42452-019-1823-3

Google Scholar

[15] Cao Y, Miao Q, Liu J, et al. Advance and Prospects of AdaBoost Algorithm, J. Acta Automatica Sinica, 2013, 39(06): 745-758.

DOI: 10.3724/sp.j.1004.2013.00745

Google Scholar

[16] Liu Y, As'arry A, Hassan K M, et al. Review of Grey Wolf Optimization Algorithm: Variants and Applications, J. Neural Computing and Applications, 2024, 36(6): 2713-2735.

DOI: 10.1007/s00521-023-09202-8

Google Scholar

[17] Zhou Y. Research on Classification of Motor Imagery EEGSignals Based on Ensemble Convolutional Neural Network, D. Anhui University, 2021.

Google Scholar

[18] Arunkumar S, Jayakumar N. A comprehensive review on lower limb exoskeleton: from origin to future expectations, J. International Journal on Interactive Design and Manufacturing (IJIDeM), 2024: 1-24.

DOI: 10.1007/s12008-024-02076-7

Google Scholar

[19] Luo X. Research on Lower Limb Muscle Force during Human Walking, D. Jilin University, 2022.

Google Scholar

[20] Yousif A H ,Norasmadi R A ,Salleh B F A , et al.Evaluation of Lower Limb Muscles Fatigue and Force during Running 400-Meters Using Learning Machine, J. Journal of Biomimetics, Biomaterials and Biomedical Engineering, 2019, 462039-53.

DOI: 10.4028/www.scientific.net/jbbbe.43.39

Google Scholar

[21] Pusarla N ,Singh A ,Tripathi S .Decoding emotional patterns using NIG modeling of EEG signals in the CEEMDAN domain, J. International Journal of Information Technology, 2024: 1-12.

DOI: 10.1007/s41870-024-02001-x

Google Scholar

[22] Deng J, Cui B, Zhang X. Gesture Recognition Method Based on AFSA-SVM, J. Journal of North China University of Polytechnic (Natural Science Edition), 2023, 45(04): 91-98.

Google Scholar