Abstract
To improve human–machine cooperation and enhance the accuracy of gait recognition in wearable lower limb exoskeletons, an enhancement method of gait recognition based on adaptive feature selection and an optimized machine learning algorithm was proposed. In this study, surface electromyography (sEMG) signals of rectus femoris, medialis femoris, lateralis femoris, semitendinosus, and biceps femoris were recorded during level-ground walking. Then, time-domain (TD), frequency domain (FD), time-frequency domain (T-FD), and nonlinear features were extracted. The integrated values of electromyography, variance, root-mean-square, and wavelength were selected as the time-domain features, and the mean power frequency and median frequency were selected as the frequency domain features. Wavelet packet energy was selected as the time-frequency domain feature. Nonlinear features, including approximate entropy, sample entropy, and fuzzy entropy of sEMG were extracted. To reduce feature dimension and improve the calculation efficiency, adaptive feature selection was performed by particle swarm optimization combined with sigmoid function. Then, the feature matrix was determined as the input for a random forest classifier to recognize different gait phases. An adaptive optimization mechanism based on Bayesian optimization was applied to random forest. Compared with random forest, the overall performance of the optimized model was improved. Its accuracy was increased by 3.57%. The feature selection and adaptive optimization mechanisms in gait recognition not only enhance the accuracy of random forest algorithms applied to sEMG for gait prediction but also facilitate the flexibility and consistency required for lower limb exoskeleton gait control.
Issue Section:
Research Papers
References
1.
Baud
, R.
, Manzoori
, A. R.
, Ijspeert
, A.
, and Bouri
, M.
, 2021
, “Review of Control Strategies for Lower-Limb Exoskeletons to Assist Gait
,” J. NeuroEng. Rehabil.
, 18
(1
), p. 119
.10.1186/s12984-021-00906-32.
Zhang
, H. H.
, Kadrolkar
, A.
, and Sup
, F. C.
, 2016
, “Design and Preliminary Evaluation of a Passive Spine Exoskeleton
,” ASME. J. Med. Devices
, 10
(1
), p. 011002
.10.1115/1.40317983.
Chen
, J.
, Sun
, Y.
, and Sun
, S.
, 2021
, “Muscle Synergy of Lower Limb Motion in Subjects With and Without Knee Pathology
,” Diagnostics
, 11
(8
), p. 1318
.10.3390/diagnostics110813184.
Song
, C. J.
, 2018
, “Research on Intention Recognition and Gait Planning of Exoskeleton Robot Based on Myoelectric Signals
,” Master's thesis, Harbin Institute of Technology
, Harbin, Heilongjiang
.5.
Gu
, X. L.
, Song
, T. C.
, Chen
, W. T.
, and Mao
, J. Y.
, 2022
, “Identification of Six Upper Limb Action EMG Signals Based on MATLAB
,” Mech. Eng.
, 5
, pp. 17
–19
.6.
Kang
, T.
, 2021
, “Human Motion Intention Recognition Based on Surface Electromyography
,” Master's thesis, University of Electronic Science and Technology of China
, Chengdu, Sichuan
.7.
Ai
, Q. S.
, Zhang
, Y. N.
, Qi
, W. L.
, Liu
, Q.
, and Chen
, K.
, 2017
, “Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals
,” Symmetry
, 9
(8
), p. 147
.10.3390/sym90801478.
Xi
, X. G.
, Tang
, M. Y.
, Miran
, S. M.
, and Luo
, Z. Z.
, 2017
, “Evaluation of Feature Extraction and Recognition for Activity Monitoring and Fall Detection Based on Wearable sEMG Sensors
,” Sensors
, 17
(6
), p. 1229
.10.3390/s170612299.
Huang
, P.
, Li
, Y. P.
, Lv
, X. Y.
, Chen
, W.
, and Liu
, S. X.
, 2020
, “Recognition of Common Non-Normal Walking Actions Based on Relief-F Feature Selection and Relief-Bagging-SVM
,” Sensors
, 20
(5
), p. 1447
.10.3390/s2005144710.
Favieiro
, G. W.
, and Balbinot
, A.
, 2019
, “Paraconsistent Random Forest: An Alternative Approach for Dealing With Uncertain Data
,” IEEE Access
, 7
, pp. 147914
–147927
.10.1109/ACCESS.2019.294625611.
Verónica
, B. C.
, and Amparo
, A. B.
, 2019
, “Ensembles for Feature Selection: A Review and Future Trends
,” Inf. Fusion
, 52
, pp. 1
–12
.10.1016/j.inffus.2018.11.008.12.
Gopal
, P.
, Gesta
, A.
, and Mohebbi
, A.
, 2022
, “A Systematic Study on Electromyography-Based Hand Gesture Recognition for Assistive Robots Using Deep Learning and Machine Learning Models
,” Sensors
, 22
(10
), p. 3650
.10.3390/s2210365013.
Jose
, N.
, Raj
, R.
, Adithya
, P. K.
, and Sivanadan
, K. S.
, 2017
, “Classification of Forearm Movements From sEMG Time Domain Features Using Machine Learning Algorithms
,” 2017 IEEE Region 10 Conference (TENCON
), Penang, Malaysia
, Nov. 5–8, pp. 1624
–1628
.10.1109/TENCON.2017.822811814.
Song
, G.
, Wang
, Y. C.
, Wang
, M. M.
, and Li
, Y.
, 2018
, “Lower Limb Movement Intent Recognition Based on Grid Search Random Forest Algorithm
,” 3rd International Conference on Robotics, Control and Automation (ICRCA '18
), Association for Computing Machinery
, Chengdu, Peoples Republic of China, Aug. 11–13, pp. 225
–229
.10.1145/3265639.326564415.
Hussien
, A. G.
, Oliva
, D.
, Houssein
, E. H.
, Juan
, A. A.
, and Yu
, X.
, 2020
, “Binary Whale Optimization Algorithm for Dimensionality Reduction
,” Mathematics
, 8
(10
), p. 1821
.10.3390/math810182116.
Yi
, J. H.
, Deb
, S.
, Dong
, J.
, Alavi
, A. H.
, and Wang
, G. G.
, 2018
, “An Improved NSGA-III Algorithm With Adaptive Mutation Operator for Big Data Optimization Problems
,” Future Gener. Comput. Syst.
, 88
, pp. 571
–585
.10.1016/j.future.2018.06.00817.
Chowdhury
, R. H.
, Reaz
, M. B. I.
, Ali
, M. A. B. M.
, Bakar
, A. A. A.
, Chellappan
, K.
, and Chang
, T. G.
, 2013
, “Surface Electromyography Signal Processing and Classification Techniques
,” Sensors
, 13
(9
), pp. 12431
–12466
.10.3390/s13091243118.
Sanz
, H.
, Valim
, C.
, Vegas
, E.
, Oller
, J. M.
, and Reverter
, F.
, 2018
, “SVM-RFE: Selection and Visualization of the Most Relevant Features Through Non-Linear Kernels
,” BMC Bioinf.
, 19
(1
), p. 432
.10.1186/s12859-018-2451-419.
Priyadarshini
, J.
, Premalatha
, M.
, Čep
, R.
, Jayasudha
, M.
, and Kalita
, K.
, 2023
, “Analyzing Physics-Inspired Metaheuristic Algorithms in Feature Selection With K-Nearest-Neighbor
,” Appl. Sci.
, 13
(2
), p. 906
.10.3390/app1302090620.
Gadekallu
, T. R.
, Khare
, N.
, Bhattacharya
, S.
, Singh
, S.
, Maddikunta
, P. K. R.
, and Srivastava
, G.
, 2023
, “Deep Neural Networks to Predict Diabetic Retinopathy
,” J. Ambient Intell. Humanized Comput.
, 14
(5
), pp. 5407
–5420
.10.1007/s12652-020-01963-721.
Rao
, H. D.
, Shi
, X. Z.
, Ahoussou
, K. R.
, Feng
, J. J.
, Xia
, Y. C.
, Elhoseny
, M.
, Yuan
, X. H.
, and Gu
, L. C.
, 2019
, “Feature Selection Based on Artificial Bee Colony and Gradient Boosting Decision Tree
,” Appl. Soft Comput.
, 74
, pp. 634
–642
.10.1016/j.asoc.2018.10.03622.
Mirjalili
, S.
, and Lewis
, A.
, 2016
, “The Whale Optimization Algorithm
,” Adv. Eng. Software
, 95
, pp. 51
–67
.10.1016/j.advengsoft.2016.01.00823.
Guo
, Z.
, Yu
, H.
, and Yin
, Y. H.
, 2014
, “Developing a Mobile Lower Limb Robotic Exoskeleton for Gait Rehabilitation
,” ASME. J. Med. Devices
, 8
(4
), p. 044503
.10.1115/1.402690024.
Li
, Z.
, Guan
, X. R.
, Zou
, K. F.
, and Xu
, C.
, 2019
, “Estimation of Knee Movement From Surface EMG Using Random Forest With Principal Component Analysis
,” Electronics
, 9
(1
), p. 43
.10.3390/electronics901004325.
Yang
, C. X.
, Gao
, H. B.
, Shen
, J. H.
, Li
, Q. F.
, Shi
, W. Z.
, Dong
, D. X.
, and Chen
, Y.
, 2022
, “Ultrasonic Phased Array Pre-Threshold Noise Reduction Based on Wavelet Packet Decomposition
,” Sens. Technol.
, 35
(10
), pp. 1368
–1374
.10.3969/j.issn.1004-1699.2022.010.01026.
Wan
, D. Y.
, 2022
, “Revealing the Complexity of Resting-State fMRI Signals Based on Multiple Entropies
,” Master's thesis, University of Electronic Science and Technology of China
, Chengdu, Sichuan
.27.
Zhu
, Y. Q.
, and Wang
, W. G.
, 2022
, “Research on Multidimensional Feature Fusion and Classification Algorithms for EEG Signals
,” Comput. Eng. Appl.
, 58
(13
), pp. 146
–153
.10.3778/j.issn.1002-8331.2012-050528.
Eberhart
, R.
, and Kennedy
, J.
, 1995
, “A New Optimizer Using Particle Swarm Theory
,” Proceedings of the Sixth International Symposium on Micro Machine and Human Science
, Nagoya, Japan
, Oct. 4–6, pp. 39
–43
.10.1109/MHS.1995.49421529.
D'Angelo
, G.
, and Palmieri
, F.
, 2021
, “GGA: A Modified Genetic Algorithm With Gradient-Based Local Search for Solving Constrained Optimization Problems
,” Inf. Sci.
, 547
, pp. 136
–162
.10.1016/j.ins.2020.08.04030.
Farhadi
, Z.
, Bevrani
, H.
, Feizi-Derakhshi
, M.-R.
, Kim
, W.
, and Ijaz
, M. F.
, 2022
, “An Ensemble Framework to Improve the Accuracy of Prediction Using Clustered Random-Forest and Shrinkage Methods
,” Appl. Sci.
, 12
(20
), p. 10608
.10.3390/app12201060831.
Joy
, T. T.
, Rana
, S.
, Gupta
, S.
, and Venkatesh
, S.
, 2016
, “Hyperparameter Tuning for Big Data Using Bayesian Optimisation
,” 2016 23rd International Conference on Pattern Recognition (ICPR)
, Mexican Assoc Comp Vis Robot & Neural Comp, Cancun, Mexico
, Dec. 4–8, pp. 2574
–2579
.10.1109/ICPR.2016.790002332.
Meng
, L.
, Pang
, J.
, Wang
, Z. Y.
, Xu
, R.
, and Ming
, D.
, 2021
, “The Role of Surface Electromyography in Data Fusion With Inertial Sensors to Enhance Locomotion Recognition and Prediction
,” Sensors
, 21
(18
), p. 6291
.10.3390/s2118629133.
Tu
, J.
, Dai
, Z. X.
, Zhao
, X.
, and Huang
, Z. J.
, 2023
, “Lower Limb Motion Recognition Based on Surface Electromyography
,” Biomed. Signal Process. Control
, 81
, p. 104443
.10.1016/j.bspc.2022.10444334.
Wang
, J. Y.
, Dai
, Y. H.
, and Si
, X. X.
, 2021
, “Analysis and Recognition of Human Lower Limb Motions Based on Electromyography (EMG) Signals
,” Electronics
, 10
(20
), p. 2473
.10.3390/electronics1020247335.
Guo
, Z. M.
, Wang
, C.
, and Song
, C. N.
, 2020
, “A Real-Time Stable-Control Gait Switching Strategy for Lower-Limb Rehabilitation Exoskeleton
,” PLoS ONE
, 15
(8
), p. e0238247
.10.1371/journal.pone.023824736.
Zhang
, C. H.
, Yu
, Z. D.
, Wang
, X. Y.
, Chen
, Z. J.
, Deng
, C.
, and Xie
, S. Q.
, 2024
, “Exploration of Deep Learning-Driven Multimodal Information Fusion Frameworks and Their Application in Lower Limb Motion Recognition
,” Biomed. Signal Process. Control
, 96
(B
), p. 106551
.10.1016/j.bspc.2024.106551Copyright © 2025 by ASME
You do not currently have access to this content.
