Adaptive Random Forest for Gait Prediction in Lower Limb Exoskeleton

Abstract:

To improve the human-machine cooperativity of a wearable lower limb exoskeleton, a gait recognition method based on surface electromyography (sEMG) was proposed. sEMG of rectus femoris, vastus medialis, vastus lateralis, semitendinosus and biceps femoris were acquired. Then, time domain, frequency domain, time-frequency domain and nonlinear features were extracted. The integrated value of electromyography, variance, root mean square and wavelength were selected as the time domain features and the frequency domain feature includes mean power frequency. 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. Classification accuracy of different feature matrices and different muscle groups were constructed and verified. The optimal multi-dimensional fusion feature matrix was determined. Introducing the Bayesian optimization algorithm, the Bayesian optimized Random Forest classification model was constructed to identify different gait phases. Comparing with Random Forest, the accuracy of the optimized Random Forest was improved by 5.89%. Applying Random Forest algorithm with Bayesian optimization to gait prediction based on sEMG, the followership and consistency of gait control in lower limb exoskeleton can be improved. This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 64)
• Pages: 55-67
• DOI: https://doi.org/10.4028/p-Q2hYbX
• Online since: April 2024
• Authors: Xu Dong Guo, Feng Qi Zhong*, Jian Ru Xiao, Zhen Hua Zhou, Wei Xu
• Keywords: Bayesian Optimization, Feature Fusion, Gait Prediction, Lower Limb Exoskeleton, Random Forest

References

[1] J.Y. Han, Y.H. Wang, D.Q. Wan, Research progress and development trend of lower limb exoskeleton rehabilitation robot, Journal of Shanghai Jiao Tong University (Medical Edition), 42(2022)241-246.

[2] C.J. Song, Research on intention recognition and gait planning of exoskeleton robot based on myoelectric signals, Harbin: Harbin Institute of Technology (2018).

[3] X.L. Gu, T.C. Song, W.T. Chen, et al, Identification of six upper limb action EMG signals based on MATLAB, Mechanical Engineer, 5(2022) 17-19.

[4] T. Kang, Human motion intention recognition based on surface electromyography, Chengdu: University of Electronic Science and Technology of China (2021).

[5] Q.S. Ai, Y.N. Zhang, W.L. Qi, et al, Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals, Symmetry, 9(2017)147.

DOI: 10.3390/sym9080147

[6] X.G. Xi, M.Y. Tang, S.M. Miran, et al, Evaluation of Feature Extraction and Recognition for Activity Monitoring and Fall Detection Based on Wearable sEMG Sensors, Sensors, 17(2017) 1229.

DOI: 10.3390/s17061229

[7] P. Huang, Y.P. Li, X.Y. Lv, et al, Recognition of Common Non-Normal Walking Actions Based on Relief-F Feature Selection and Relief-Bagging-SVM, Sensors, 25(2020)1447.

DOI: 10.3390/s20051447

[8] G.W. Favieiro, A. Balbinot, Paraconsistent Random Forest: An Alternative Approach for Dealing with Uncertain Data, IEEE Access, 7(2019)1479.

DOI: 10.1109/access.2019.2946256

[9] P. Gopal, A. Gesta, A. Mohebbi, A Systematic Study on Electromyography-Based Hand Gesture Recognition for Assistive Robots Using Deep Learning and Machine Learning Models, Sensors, 22(2022)3650.

DOI: 10.3390/s22103650

[10] N. Jose, R. Raj, P.K. Adithya, et al, Classification of Forearm Movements from sEMG Time Domain Features Using Machine Learning Algorithms, 2017 IEEE Region 10 Conference (TENCON), Penang, MALAYSIA: IEEE (2017)1624-1628.

DOI: 10.1109/tencon.2017.8228118

[11] G. Song, Y.C. Wang, M.M. Wang, et al, Lower Limb Movement Intent Recognition Based on Grid Search Random Forest Algorithm, 3rd International Conference on Robotics, Control and Automation (ICRCA '18), New York, NY, USA: Association for Computing Machinery (2018)225-229.

DOI: 10.1145/3265639.3265644

[12] Z. Li, X.R. Guan, K.F. Zou, et al, Estimation of Knee Movement from Surface EMG Using Random Forest with Principal Component Analysis, Electronics, 9(2020)43.

DOI: 10.3390/electronics9010043

[13] P. Zhang, J.X. Zhang, R.H. Liu, et al, Research on lower limb action recognition based on GA-RBF neural network and sEMG, Chinese Journal of Biomedical Engineering, 41(2022)41-47.

[14] H. Kumar, N. Ganapathy, S.D. Puthankattil, et al, Classification of Emotional States Using EEG Signals and Wavelet Packet Transform Features, Studies in health technology and informatics, 294(2022)943-944.

DOI: 10.3233/shti220632

[15] P.A. Karjalainen, F.R. Gao, T.X. Tian, et al, Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms, Computational Intelligence and Neuroscience (2021)1-14.

DOI: 10.1155/2021/6693206

[16] Y. Lu, H. Wang, F. Hu, et al, Effective recognition of human lower limb jump locomotion phases based on multi-sensor information fusion and machine learning, Medical & Biological Engineering & Computing, 59(2021)883–899.

DOI: 10.1007/s11517-021-02335-9

[17] W.T. Chen, J. Zhuang, W.X. Yu, et al, Measuring complexity using FuzzyEn, ApEn, and SampEn, Medical Engineering & Physics, 31(2009)61-68.

DOI: 10.1016/j.medengphy.2008.04.005

[18] Z. Farhadi, H. Bevrani, M.R. Feizi-Derakhshi, et al, An Ensemble Framework to Improve the Accuracy of Prediction Using Clustered Random-Forest and Shrinkage Method, Applied Sciences, 12(2022)10608.

DOI: 10.3390/app122010608

[19] T.T. Joy, S. Rana, S. Gupta, et al, Hyperparameter Tuning for Big Data using Bayesian Optimization. 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, MEXICO: Mexican Assoc Comp Vis Robot & Neural Comp (2016)2574-2579.

DOI: 10.1109/icpr.2016.7900023

[20] S.L. Bai, D.J. Ying, Systematic Anatomy, eight ed., People's Health Publishing House, Beijing, 2013.

[21] P. Jacqueline, M.B. Judith, S.Y. Jiang, Gait analysis: normal and pathological functions, first ed, Shanghai Science and Technology Press, Shanghai, 2017.

[22] P. Huang, J. Qi, L.F. Deng, et al, Surface electromyographic analysis of lower limb muscles in normal young adults with natural gait, Chinese Organization Engineering Research, 16(2012)3680-3684.

[23] G. Tang, Biomechanical simulation analysis of typical human sports, Shanghai: Shanghai Jiao Tong University (2011).

[24] C.C. Hang, Research on lower limb motion intention recognition based on sEMG signal, Wuhan: Wuhan University of Technology (2019).

[25] H.Y. Zhao, Z.B. Qiu, D.Y., Peng et al, Prediction of Joint Angles Based on Human Lower Limb Surface Electromyography, Sensors, 23(2023)5404.

DOI: 10.3390/s23125404

[26] S. Issa, A.R. Khaled, Lower Limb Movement Recognition Using EMG Signals, Intelligent Systems Design and Applications, 418(2022)336–345.

DOI: 10.1007/978-3-030-96308-8_31

[27] P.J. Qin, X. Shi, Evaluation of Feature Extraction and Classification for Lower Limb Motion Based on sEMG Signal, Entropy, 22(2020)852.

DOI: 10.3390/e22080852

[28] Z.M. Guo, C. Wang, C.N. Song, A real-time stable-control gait switching strategy for lower-limb rehabilitation exoskeleton, PLoS ONE, 15(2020) e0238247.

DOI: 10.1371/journal.pone.0238247

[29] P.N. Wei, J.H. Zhang, F.F. Tian, et al, A comparison of neural networks algorithms for EEG and sEMG features based gait phases recognition, Biomedical Signal Processing and Control, 68(2021)102587.

DOI: 10.1016/j.bspc.2021.102587