Rapid Estimation of Elbow Joint Moment and Triceps Force During Triceps Dumbbell Kickback

Yıl 2025, ERKEN GÖRÜNÜM, 1 - 1

Mohammed Mansour , Kasım Serbest , Mustafa Çağrı Kutlu

https://doi.org/10.2339/politeknik.1681703

Öz

Introduction: Understanding the biomechanics of the upper limb is of considerable interest in both clinical and engineering domains. Estimating elbow joint moments and triceps force plays a pivotal role in modelling musculoskeletal function. However, the use of electromyography (EMG) data is often constrained by challenges such as signal noise and calibration complexity. The objective of this study is to determine the elbow joint moment and triceps force during a Rest Pause Triceps Dumbbell Kickback exercise. Methods: This investigation utilized kinematic assessments from a cohort of 14 participants with diverse anthropometric profiles. A range of machine learning and deep learning models were employed to predict joint torque and triceps muscle force, including deep neural networks (DNN), long short-term memory networks (LSTM), convolutional neural networks (CNN), decision trees (DT), linear regression (LR), support vector machines (SVM), and random forests (RF). Model performance was systematically evaluated using multiple statistical metrics: Mean Squared Residuals (MSR), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the Correlation Coefficient (R). Results: The analytical outcomes demonstrated that the LSTM model yielded the highest predictive accuracy, achieving a correlation coefficient of R = 0.98374 when six input features (time, mass, forearm mass, upper arm mass, elbow angle, and height) were used. In descending order of R values, the performance of the remaining models was as follows: RF (0.92793), CNN (0.92106), DT (0.88812), DNN (0.75769), SVM (0.70011), and LR (0.44690). These findings underscore the potential of LSTM in capturing the temporal dynamics essential for biomechanical prediction. Conclusion: The findings from this study provide new insights into data-driven biomechanics and suggest that LSTM-based models may offer a promising alternative to EMG-based approaches. Accurate prediction of joint moments has significant implications for the real-time control of assistive technologies, particularly active orthoses in the future.

Anahtar Kelimeler

biomechanical modeling , motion analysis , RPTK , upper limb , deep learning.

Kaynakça

• [1] Shkedy Rabani A, Mizrachi S, Sawicki GS, Riemer R, “Parametric equations to study and predict lower-limb joint kinematics and kinetics during human walking and slow running on slopes”, PloS one; 17(8): e0269061, (2022).
• [2] Yamagata M, Tateuchi H, Asayama A, Ichihashi N., “Influence of lower-limb muscle inactivation on medial and lateral knee contact forces during walking”, Medical Engineering & Physics 108: 103889, (2022).
• [3] Banks JJ, Umberger BR, Caldwell GE, “EMG optimization in Open- Sim: A model for estimating lower back kinetics in gait”, Medical Engineering & Physics 103: 103790, (2022).
• [4] Loss, J., & Candotti, C., “Comparative study between two elbow flexion exercises using the estimated resultant muscle force”, Brazilian Journal of Physical Therapy, FapUNIFESP (SciELO), (2008).
• [5] Tanaka, H., Hayashi, T., Inui, H., Muto, T., Ninomiya, H., Nakamura, Y., … Nobuhara, K., “Estimation of Shoulder Behavior From the Viewpoint of Minimized Shoulder Joint Load Among Adolescent Baseball Pitchers”, The American Journal of Sports Medicine. SAGE Publications., (2018).
• [6] Zarfam, P., & Mofid, M., “On the assessment of modal nonlinear pushover analysis for steel frames with semi-rigid connections”, Structural Engineering and Mechanics, 32 (3), 383, (2009).
• [7] Mundt M, Koeppe A, David S, et al, “Estimation of gait mechanics based on simulated and measured IMU data using an artificial neural network”, Frontiers in bioengineering and biotechnology, 8: 41, (2020).
• [8] Zell P, Rosenhahn B, “Learning inverse dynamics for human locomotion analysis”, Neural Computing and Applications, 32(15): 11729–11743, (2020).
• [9] Aydoğan, İ., & Aydın, E. A., “Wearable Electromyogram Design for Finger Movements Based Real-Time Human-Machine Interfaces”, Politeknik Dergisi, 26(2), 973-981, (2023).
• [10] Ardestani MM, Zhang X,Wang L, et al, “Human lower extremity joint moment prediction: A wavelet neural network approach”, Expert Systems with Applications 41(9): 4422–4433, (2014).
• [11] Choi J, Yeoh W L, Matsuura, S, Loh, P Y, & Muraki S, “Effects of mechanical assistance on muscle activity and motor performance during isometric elbow flexion”, Journal of Electromyography and Kinesiology, 50, 102380, (2020).
• [12] Rakshit, R, Xiang, Y, & Yang, J, “Dynamic-joint-strength-based two-dimensional symmetric maximum weight-lifting simulation: Model development and validation”, Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 234(7), 660-673, (2020).
• [13] Ebrahimi, A, Martin, J A, Schmitz, D G, & Thelen, D G, “Shear wave tensiometry reveals an age-related deficit in triceps surae work at slow and fast walking speeds”, Frontiers in Sports and Active Living, 2, 69, (2020).
• [14] Granatosky, M C, & Ross, C F, “Differences in muscle mechanics underlie divergent optimality criteria between feeding and locomotor systems”, Journal of Anatomy, 237(6), 1072-1086, (2020).
• [15] Lu, W, Gao, L, Zhang, Q, & Li, Z, “A hybrid deep learning framework for estimation of elbow flexion force via electromyography”, In Journal of Physics: Conference Series (Vol. 1883, No. 1, p. 012164). IOP Publishing, (2021).
• [16] Huang, Y, Chen, K, Zhang, X, Wang, K, & Ota, J, “Motion estimation of elbow joint from sEMG using continuous wavelet transform and back propagation neural networks”, Biomedical Signal Processing and Control, 68, 102657, (2021).
• [17] Baltzopoulos, V, “Inverse dynamics, joint reaction forces and loading in the musculoskeletal system: guidelines for correct mechanical terms and recommendations for accurate reporting of results”, Sports Biomechanics, 23(3), 287-300, (2024).
• [18] Larsen, S, Gomo, O, & van den Tillaar, R, “A biomechanical analysis of wide, medium, and narrow grip width effects on kinematics, horizontal kinetics, and muscle activity on the sticking region in recreationally trained males during 1-RM bench pressing”, Frontiers in sports and active living, 2, 637066, (2021).
• [19] Wang, H, Xie, Z, Lu, L, Li, L, & Xu, X., “A computer-vision method to estimate joint angles and L5/S1 moments during lifting tasks through a single camera”. Journal of biomechanics, 129, 110860, (2021).
• [20] Truong, M T N., Ali, A E A, Owaki, D, & Hayashibe, M, “EMG-based estimation of lower limb joint angles and moments using long short-term memory network”, Sensors, 23(6), 3331, (2023).
• [21] Hambly, M J, De Sousa, A C C, Lloyd, D G, & Pizzolato, C, “EMG-Informed Neuromusculoskeletal Modelling Estimates Muscle Forces and Joint Moments During Electrical Stimulation”, In 2023 International Conference on Rehabilitation Robotics (ICORR) (pp. 1-6). IEEE, (2023).
• [22] Zhang, X, Li, Y, & Sun, R, “Assistance force-line of exosuit affects ankle multidimensional motion: a theoretical and experimental study”, Journal of Neuro Engineering and Rehabilitation, 21(1), 87, (2024).
• [23] Faridmehr, I., & Nehdi, M. L., “Predicting axial load capacity of CFST columns using machine learning Structural Concrete, Wiley, (2022).
• [24] Varma, V. S., Rao, R. Y., Vundavilli, P. R., Pandit, M. K., & Budarapu, P. R., “A Machine Learning-Based Approach for the Design of Lower Limb Exoskeleton”, International Journal of Computational Methods. World Scientific Pub Co Pte Ltd, (2022).
• [25] Sakamoto, S.-. ichi ., Hutabarat, Y., Owaki, D., & Hayashibe, M., “Ground Reaction Force and Moment Estimation through EMG Sensing Using Long Short-Term Memory Network during Posture Coordination”, Cyborg and Bionic Systems. American Association for the Advancement of Science (AAAS).
• [26] Ullauri, J B, Peternel, L, Ugurlu, B, Yamada, Y, & Morimoto, J, “On the EMG-based torque estimation for humans coupled with a force-controlled elbow exoskeleton”, In 2015 International Conference on Advanced Robotics (ICAR) (pp. 302-307). IEEE, (2015).
• [27] Mundt, M., Koeppe, A., David, S., Witter, T., Bamer, F., Potthast, W., & Markert, B., “Estimation of gait mechanics based on simulated and measured IMU data using an artificial neural network”, Frontiers in bioengineering and biotechnology, 8, 41, (2020).
• [28] Hu, B, Tao, H, Lu, H, Zhao, X, Yang, J, & Yu, H, “An Improved EMG‐Driven Neuromusculoskeletal Model for Elbow Joint Muscle Torque Estimation”, Applied Bionics and Biomechanics, 2021(1), 1985741, (2021).
• [29] Taneja, K., He, X., He, Q., Zhao, X., Lin, Y. A., Loh, K. J., & Chen, J. S., “A feature-encoded physics-informed parameter identification neural network for musculoskeletal systems”, Journal of biomechanical engineering, 144(12), 121006, (2022).
• [30] Lu, W, Gao, L, Cao, H, & Li, Z, “sEMG-upper limb interaction force estimation framework based on residual network and bidirectional long short-term memory network”, Applied Sciences, 12(17), 8652, (2022).
• [31] Luh, J J, Chang, G C, Cheng, C K, Lai, J S, & Kuo, T S, “Isokinetic elbow joint torques estimation from surface EMG and joint kinematic data: using an artificial neural network model”, Journal of electromyography and kinesiology, 9(3), 173-183, (1999).
• [32] Shirzadi, M, Marateb, H R, Rojas-Martínez, M, Mansourian, M, Botter, A, Vieira dos Anjos, F, ... & Mañanas, M A, “A real-time and convex model for the estimation of muscle force from surface electromyographic signals in the upper and lower limbs”, Frontiers in physiology, 14, 1098225, (2023).
• [33] Sepulveda, F, Wells, D M, & Vaughan, C L, “A neural network representation of electromyography and joint dynamics in human gait”, Journal of biomechanics, 26(2), 101-109, (1993).
• [34] Johnson, R T, Lakeland, D, & Finley, J M, “Using Bayesian inference to estimate plausible muscle forces in musculoskeletal models”, Journal of neuroengineering and rehabilitation, 19(1), 34, (2022).
• [35] Hashemi, J, Morin, E, Mousavi, P, & Hashtrudi-Zaad, K, “Enhanced dynamic EMG-force estimation through calibration and PCI modeling.” IEEE Transactions on Neural Systems and Rehabilitation Engineering, 23(1), 41-50, (2014).
• [36] Uhlrich, S D, Falisse, A, Kidziński, Ł, Muccini, J, Ko, M, Chaudhari, A S, & Delp, S L, “OpenCap: 3D human movement dynamics from smartphone videos”, bioRxiv 1, 1 (2022), 1–48, (2022).
• [37] Winter, D. A., “Biomechanics and motor control of human movement”, John wiley & sons, (2009).
• [38] Walker, A., “New Australopithecus femora from East Rudolf, Kenya”, Journal of Human Evolution, 2(6), 545-555, (1973).
• [39] Chandler, R. F., Clauser, C. E., McConville, J. T., Reynolds, H. M., & Young, J. W., “Investigation of inertial properties of the human body”, (Vol. 53). Wright-Patterson Air Force Base, OH, USA: Aerospace Medical Research Laboratory, (1975).
• [40] Sugisaki, N., Wakahara, T., Miyamoto, N., Murata, K., Kanehisa, H., Kawakami, Y., & Fukunaga, T, “Influence of muscle anatomical cross-sectional area on the moment arm length of the triceps brachii muscle at the elbow joint”, Journal of biomechanics, 43(14), 2844-2847, (2010).
• [41] Trentin E, “Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction”, Pattern Recognition Letters 66: 71–80, (2015).
• [42] Senvar O, Sennaroglu B, “Comparing performances of clements, box-cox, Johnson methods with weibull distributions for assessing process capability”, Journal of Industrial Engineering and Management 9(3): 634–656, (2016).
• [43] Singh D, Singh B, “Investigating the impact of data normalization on classification performance”, Applied Soft Computing, 97: 105524, (2020).
• [44] Karapinar Senturk Z, Sevgul Bakay M, “Machine Learning- Based Hand Gesture Recognition via EMG Data”, (2021).
• [45] Alpaydin E, “Introduction to machine learning”, MIT press, (2020).
• [46] Akour I, Alshurideh M, Al Kurdi B, Al Ali A, Salloum S, “Using machine learning algorithms to predict people’s intention to use mobile learning platforms during the COVID-19 pandemic: machine learning approach”, JMIR Medical Education, 7(1): e24032, (2021).
• [47] Quiroz JC, Feng YZ, Cheng ZY, et al, “Development and validation of a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data”, JMIR Medical Informatics, 9(2): e24572, (2021).
• [48] Najafabadi MM, Villanustre F, Khoshgoftaar TM, Seliya N, Wald R, Muharemagic E, “Deep learning applications and challenges in big data analytics”, Journal of big data, 2(1): 1–21, (2015).
• [49] Miyato T,Maeda Si, Koyama M, Ishii S, “Virtual adversarial training: a regularization method for supervised and semi-supervised learning”, IEEE transactions on pattern analysis and machine intelligence, 41(8): 1979–1993, (2018).
• [50] Chen Y,Wang X, Zhang B, “An unsupervised deep learning approach for scenario forecasts” In: IEEE. 1–7, (2018).
• [51] Eren, M., Toktaş, İ., & Özkan, M. T., “Modeling of stress concentration factor using artificial neural networks for a flat tension bar with opposite v-shaped notches” Politeknik Dergisi, 26(3), 1199-1205, (2023).
• [52] Hanani, A. A., Mansour, M., & Badrasawi, M., “Prediction of medical students’ mental health in palestine during covid-19 using deep and machine learning”, Palestinian Medical and Pharmaceutical Journal, 9(4), 4, (2024).
• [53] Boser BE, Guyon IM, Vapnik VN, “A training algorithm for optimal margin classifiers”, In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152), (1992).
• [54] Wen L, Cao Y, “Influencing factors analysis and forecasting of residential energy-related CO2 emissions utilizing optimized support vector machine”, Journal of Cleaner Production, 250: 119492, (2020).
• [55] Zhang Z, Li Y, Li L, Li Z, Liu S, “Multiple linear regression for high efficiency video intra coding”, In: IEEE, 1832–1836, (2019).
• [56] Kumar SA et al, “Efficiency of decision trees in predicting student’s academic performance”, (2011).
• [57] Das R, “A comparison of multiple classification methods for diagnosis of Parkinson disease” Expert Systems with Applications, 37(2): 1568–1572, (2010).
• [58] Saber M, El Rharras A, Saadane R, Aroussi HK, Wahbi M, “Artificial neural networks, support vector machine and energy detection for spectrum sensing based on real signals”, International Journal of Communication Networks and Information Security 11(1): 52–60, (2019).
• [59] Mansour, M, Serbest, K, Kutlu, M, & Cilli, M, “Estimation of lower limb joint moments based on the inverse dynamics approach: a comparison of machine learning algorithms for rapid estimation”, Medical & Biological Engineering & Computing, 61(12), 3253-3276, (2023).
• [60] Ekinci, E, Garip, Z, & Serbest, K, “Electromyography based hand movement classification and feature extraction using machine learning algorithms”, Politeknik Dergisi, 26(4), 1621-1633, (2023).