Artificial Neural Network Accuracy Optimization Using Transfer Function Methods on Various Human Gait Walking Environments

Ragil Indrawati - Politeknik Negeri Semarang, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia
Farika Putri - Politeknik Negeri Semarang, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia
Eni Safriana - Politeknik Negeri Semarang, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia
Wahyu Isti Nugroho - Politeknik Negeri Semarang, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia
Hartanto Prawibowo - Universitas Diponegoro, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia
Mochammad Ariyanto - Universitas Diponegoro, Prof. Sudarto Road Tembalang, Semarang 50275, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.2.2159

Abstract


A bionic leg with ergonomic functionality can increase the user’s independence. However, an ergonomic bionic leg can be challenged to be developed. One of its challenges is related to functionality, where the bionic leg motor can be rugged to adapt to the user. One of the solutions for the bionic leg challenge is the application of a motor driver controlled by the user’s muscle signal. EMG signal can be utilized as the user’s signal source. The EMG signal is then fed back into the motor device. EMG signals obtained during a natural walking environment can result in smooth and natural movement. This study classifies EMG signals into 8 classes: a controlled walking environment (treadmill walking with various speeds) and a natural walking environment (ground walking, upstairs and downstairs walking). This research aims to optimize the ANN method using transfer function variations. The best method will be used to train EMG-driven motors for future studies related to bionic legs. The best ANN parameter in this research using Levenberg-Marquardt backpropagation as a training algorithm with transfer function pairing of the exponential function: Hyperbolic tangent sigmoid transfer function and SoftMax transfer function with 98.8% accuracy and 0.036 MSE value. The best method from the experiment and ANN classification can be used as a training method for a bionic leg in future research.


Keywords


artificial neural network; EMG; gait analysis; bionic leg.

Full Text:

PDF

References


R. Huang, H. Cheng, H. Guo, X. Lin, Q. Chen, and F. Sun, “Learning Cooperative Primitives with physical Human-Robot Interaction for a HUman-powered Lower EXoskeleton,” in 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, pp. 5355–5360. doi: 10.1109/IROS.2016.7759787.

K. Li, J. Zhang, L. Wang, M. Zhang, J. Li, and S. Bao, “A review of the key technologies for sEMG-based human-robot interaction systems,” Biomed. Signal Process. Control, vol. 62, p. 102074, Sep. 2020, doi: 10.1016/j.bspc.2020.102074.

P. Kim, J. Lee, and C. S. Shin, “Classification of Walking Environments Using Deep Learning Approach Based on Surface EMG Sensors Only,” 2021.

C. Morbidoni, A. Cucchiarelli, S. Fioretti, and F. Di Nardo, “A deep learning approach to EMG-based classification of gait phases during level ground walking,” Electron., vol. 8, no. 8, 2019, doi: 10.3390/electronics8080894.

F. Di Nardo, A. Nocera, A. Cucchiarelli, S. Fioretti, and C. Morbidoni, “Machine Learning for Detection of Muscular Activity from Surface EMG Signals,” pp. 1–17, 2022.

C. Nutakki et al., “Classification and Kinetic Analysis of Healthy Gait using Multiple Accelerometer Sensors,” Procedia Comput. Sci., vol. 171, no. 2019, pp. 395–402, 2020, doi: 10.1016/j.procs.2020.04.041.

I. H. Lopez-Nava, L. M. Valentín-Coronado, M. Garcia-Constantino, and J. Favela, “Gait activity classification on unbalanced data from inertial sensors using shallow and deep learning,” Sensors (Switzerland), vol. 20, no. 17, pp. 1–21, 2020, doi: 10.3390/s20174756.

M. A. R. Ahad et al., “Wearable sensor-based gait analysis for age and gender estimation,” Sensors (Switzerland), vol. 20, no. 8, pp. 1–24, 2020, doi: 10.3390/s20082424.

J. Wojtusch and O. Von Stryk, “HuMoD - A versatile and open database for the investigation, modeling and simulation of human motion dynamics on actuation level,” IEEE-RAS Int. Conf. Humanoid Robot., vol. 2015-December, no. November 2015, pp. 74–79, 2015, doi: 10.1109/HUMANOIDS.2015.7363534.

J. Ziegler, H. Gattringer, and A. Mueller, “Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines,” in 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), IEEE, Aug. 2018, pp. 978–983. doi: 10.1109/BIOROB.2018.8487750.

R. Ismail, “Muscle Power Signal Acquisition Monitoring Using Surface EMG,” J. Biomed. Res. Environ. Sci., vol. 3, no. 5, pp. 663–667, 2022, doi: 10.37871/jbres1493.

F. T. Putri, W. Caesarendra, G. Kr, and A. Glowacz, “Human Walking Gait Classification Utilizing an Artificial Neural Network for the Ergonomics Study of Lower Limb Prosthetics,” pp. 647–665, 2023.

G. Panahandeh, N. Mohammadiha, A. Leijon, and P. Handel, “Continuous hidden markov model for pedestrian activity classification and gait analysis,” IEEE Trans. Instrum. Meas., vol. 62, no. 5, pp. 1073–1083, 2013, doi: 10.1109/TIM.2012.2236792.

K. Zhang, W. Zhang, W. Xiao, H. Liu, C. W. De Silva, and C. Fu, “Sequential Decision Fusion for Environmental Classification in Assistive Walking,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 27, no. 9, pp. 1780–1790, 2019, doi: 10.1109/TNSRE.2019.2935765.

F. Di Nardo, C. Morbidoni, A. Cucchiarelli, and S. Fioretti, “Influence of EMG-signal processing and experimental set-up on prediction of gait events by neural network,” Biomed. Signal Process. Control, vol. 63, p. 102232, 2021, doi: https://doi.org/10.1016/j.bspc.2020.102232.

C. Fricke, J. Alizadeh, N. Zakhary, T. B. Woost, M. Bogdan, and J. Classen, “Evaluation of Three Machine Learning Algorithms for the Automatic Classification of EMG Patterns in Gait Disorders,” Front. Neurol., vol. 12, no. May, pp. 1–11, 2021, doi: 10.3389/fneur.2021.666458.

N. Nazmi, M. A. Abdul Rahman, S.-I. Yamamoto, and S. A. Ahmad, “Walking gait event detection based on electromyography signals using artificial neural network,” Biomed. Signal Process. Control, vol. 47, pp. 334–343, Jan. 2019, doi: 10.1016/j.bspc.2018.08.030.

C. Morbidoni et al., “Gait Phase Classification from Surface EMG Signals Using Neural Networks,” in XV Mediterranean Conference on Medical and Biological Engineering and Computing -- MEDICON 2019, J. Henriques, N. Neves, and P. de Carvalho, Eds., Cham: Springer International Publishing, 2020, pp. 75–82.

N. Nazmi et al., “Analysis of EMG Signals during Stance and Swing Phases for Controlling Magnetorheological Brake applications,” Open Eng., vol. 11, no. 1, pp. 112–119, 2020, doi: 10.1515/eng-2021-0009.

T. Ahmed and M. K. Islam, “EMG Signal Classification for Detecting Neuromuscular Disorders,” J. Phys. Conf. Ser., vol. 1921, no. 1, 2021, doi: 10.1088/1742-6596/1921/1/012043.

F. Q. Nuttall, “Body Mass Index,” Nutr. Today, vol. 50, no. 3, pp. 117–128, May 2015, doi: 10.1097/NT.0000000000000092.

R. I. J. J. P. W. A. D. Darmanto R. Novriansyah and A. P. Bayuseno, “Reconstruction of the artificial knee joint using a reverse engineering approach based on computer-aided design,” J. Med. Eng. & Technol., vol. 46, no. 2, pp. 136–147, 2022, doi: 10.1080/03091902.2022.2026502.

R. Ismail et al., “Design, Manufacturing and Characterization of Biodegradable Bone Screw from PLA Prepared by Fused Deposition Modelling (FDM) 3D Printing Technique,” J. Adv. Res. Fluid Mech. Therm. Sci., vol. 103, no. 2, pp. 205–215, 2023, doi: 10.37934/arfmts.103.2.205215.

A. F. Istiqomah et al., “Design and Analysis of The Energy Storage and Return (ESAR) Foot Prosthesis Using Finite Element Method,” J. Biomed. Sci. Bioeng., vol. 1, no. 2, pp. 59–64, 2022, doi: 10.14710/jbiomes.2021.v1i2.59-64.

L. Kistriyani, M. Khafidh, D. Suryawan, and R. Ismail, “Physical characteristic of polymer formulations for prosthetic foot materials: Comparison of natural rubber and ethylene vinyl acetate,” 2023, p. 050003. doi: 10.1063/5.0109385.

A. Rainoldi, G. Melchiorri, and I. Caruso, “A method for positioning electrodes during surface EMG recordings in lower limb muscles,” J. Neurosci. Methods, vol. 134, no. 1, pp. 37–43, Mar. 2004, doi: 10.1016/j.jneumeth.2003.10.014.

V. Christou et al., “Automatic Hemiplegia Type Detection (Right or Left) Using the Levenberg-Marquardt Backpropagation Method,” Inf., vol. 13, no. 2, 2022, doi: 10.3390/info13020101.

Y. Zhou et al., “EMG Signal Processing for Hand Motion Pattern Recognition Using Machine Learning Algorithms,” Arch. Orthop., vol. 1, no. 1, pp. 17–26, 2020, doi: 10.33696/orthopaedics.1.005.

J. Narayan, S. Jhunjhunwala, S. Mishra, and S. K. Dwivedy, “A comparative performance analysis of backpropagation training optimizers to estimate clinical gait mechanics,” in Predictive Modeling in Biomedical Data Mining and Analysis, Elsevier, 2022, pp. 83–104. doi: 10.1016/B978-0-323-99864-2.00012-3.

A. Alharbi, K. Equbal, S. Ahmad, H. U. Rahman, and H. Alyami, “Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method,” J. Healthc. Eng., vol. 2021, 2021, doi: 10.1155/2021/5541255.

A. Kumar and S. S. Sodhi, “Is Exponential Activation Function Always Better Than the Non-Exponential Activation Function,” vol. 21, no. 8, pp. 4713–4731, 2022.

O. Adeleke, S. A. Akinlabi, T. C. Jen, and I. Dunmade, “Application of artificial neural networks for predicting the physical composition of municipal solid waste: An assessment of the impact of seasonal variation,” Waste Manag. Res., vol. 39, no. 8, pp. 1058–1068, 2021, doi: 10.1177/0734242X21991642.

A. Jierula, S. Wang, T. M. Oh, and P. Wang, “Study on accuracy metrics for evaluating the predictions of damage locations in deep piles using artificial neural networks with acoustic emission data,” Appl. Sci., vol. 11, no. 5, pp. 1–21, 2021, doi: 10.3390/app11052314.