PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Joint torque estimation is an essential aspect of the control architecture in assistive devices for rehabilitation and aiding movement impairments. Healthy adult torque trajectories serve as a baseline for controllers to determine the level of assistance required by patients, evaluate impaired motion, understand biomechanics, and design treatment plans. Currently, methods of torque estimation include inverse dynamics using gold standard motion capture systems, generic mathematical models based on joint torque-angle relationships, neuromusculoskeletal modelling using surface electromyography, and neural networks. As such, this review provides a focused overview of the recent and existing neural networks tailored for upper and lower limb joint torque estimation. Dataset preparation, data preprocessing, and evaluation metrics are presented along with a detailed description of the developed networks, which are classified by model architecture. It includes artificial neural networks (ANNs), convolution neural networks (CNNs), long short-term memory (LSTM) networks, and hybrid and alternate architectures such as wavelet or explainable convolution (XCM). The performance, benefits, and limitations of the models are discussed, highlighting CNNs and LSTMs as the current optimal models for time series prediction of joint torque. This is due to their ability to capture spatial and temporal dependencies in the data. Additionally, joint kinematics such as angles, angular velocities, and accelerations are considered optimal input parameters due to their ease of measurement using wearable sensors and integration with wearable assistive technology.

• Altai, Z., Boukhennoufa, I., Zhai, X., Phillips, A., Moran, J., & Liew, B. X. W. (2023). Performance of multiple neural networks in predicting lower limb joint moments using wearable sensors. Frontiers in Bioengineering and Biotechnology, 11, Article 1215770. https://doi.org/10.3389/fbioe.2023.1215770
  
  Ardestani, M. M., Zhang, X., Wang, L., Lian, Q., Liu, Y., He, J., Li, D., & Jin, Z. (2014). Human lower extremity joint moment prediction: A wavelet neural network approach. Expert Systems with Applications, 41(9), 4422–4433. https://doi.org/10.1016/j.eswa.2013.11.003
  
  Chandrapal, M., Chen, X., Wang, W., Stanke, B., & Pape, N. L. (2011). Investigating improvements to neural network based EMG to joint torque estimation. Paladyn, 2(4), 185–192. https://doi.org/10.2478/s13230-012-0007-2
  
  Cho, K., Merrienboer, B. V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv. https://doi.org/10.48550/arXiv.1406.1078
  
  Crenna, F., Rossi, G. B., & Berardengo, M. (2021). Filtering biomechanical signals in movement analysis. Sensors, 21(13), Article 4580. https://doi.org/10.3390/s21134580
  
  Delp, S. L., Anderson, F. C., Arnold, A. S., Loan, P., Habib, A., John, C. T., Guendelman, E., & Thelen, D. G. (2007). OpenSim: Open-source software to create and analyze dynamic simulations of movement. IEEE Transactions on Bio-Medical Engineering, 54(11), 1940–1950. https://doi.org/10.1109/TBME.2007.901024
  
  Dinovitzer, H., Shushtari, M., & Arami, A. (2023). Accurate real-time joint torque estimation for dynamic prediction of human locomotion. IEEE Transactions on Biomedical Engineering, 70(8), 2289-2297. https://doi.org/10.1109/TBME.2023.3240879
  
  Farina, D., & Enoka, R. M. (2023). Evolution of surface electromyography: From muscle electrophysiology towards neural recording and interfacing. Journal of Electromyography and Kinesiology, 71, Article 102796. https://doi.org/10.1016/j.jelekin.2023.102796
  
  Hajian, G., Morin, E., & Etemad, A. (2021, November 1-5). Convolutional neural network approach for elbow torque estimation during quasi-dynamic and dynamic contractions. [Paper presentation]. 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Mexico City, Mexico. https://doi.org/10.1109/EMBC46164.2021.9630287
  
  Höglund, G., Grip, H., & Öhberg, F. (2021). The importance of inertial measurement unit placement in assessing upper limb motion. Medical Engineering & Physics, 92, 1–9. https://doi.org/10.1016/j.medengphy.2021.03.010
  
  Huang, Y., Chen, K., Zhang, X., Wang, K., & Ota, J. (2020). Joint torque estimation for the human arm from sEMG using backpropagation neural networks and autoencoders. Biomedical Signal Processing and Control, 62, Article 102051. https://doi.org/10.1016/j.bspc.2020.102051
  
  Kruk, E. V. D., Strutton, P., Koizia, L. J., Fertleman, M., Reilly, P., & Bull, A. M. J. (2022). Why do older adults stand-up differently to young adults? Investigation of compensatory movement strategies in sit-to-walk. Npj Aging, 8(1), Article 13. https://doi.org/10.1038/s41514-022-00094-x
  
  Lam, S. K., & Vujaklija, I. (2021). Joint torque prediction via hybrid neuromusculoskeletal modelling during gait using statistical ground reaction estimates: An exploratory study. Sensors, 21(19), Article 6597. https://doi.org/10.3390/s21196597
  
  Li, Y., Chen, W., Yang, H., Li, J., & Zheng, N. (2020). Joint torque closed-loop estimation using NARX neural network based on sEMG signals. IEEE Access, 8, 213636–213646. https://doi.org/10.1109/ACCESS.2020.3039983
  
  Lim, H., Kim, B., & Park, S. (2019). Prediction of lower limb kinetics and kinematics during walking by a single IMU on the lower back using machine learning. Sensors, 20(1), Article 130. https://doi.org/10.3390/s20010130
  
  Liu, X., Zhou, Z., Mai, J., & Wang, Q. (2019). Real-time mode recognition based assistive torque control of bionic knee exoskeleton for sit-to-stand and stand-to-sit transitions. Robotics and Autonomous Systems, 119, 209–220. https://doi.org/10.1016/j.robot.2019.06.008
  
  Liu, Y., Shih, S. M., Tian, S. L., Zhong, Y. J., & Li, L. (2009). Lower extremity joint torque predicted by using artificial neural network during vertical jump. Journal of Biomechanics, 42(7), 906–911. https://doi.org/10.1016/j.jbiomech.2009.01.033
  
  McCabe, M. V., Citters, D. W. V., & Chapman, R. M. (2023). Hip joint angles and moments during stair ascent using neural networks and wearable sensors. Bioengineering, 10(7), Article 784. https://doi.org/10.3390/bioengineering10070784
  
  Molinaro, D. D., Kang, I., Camargo, J., & Young, A. J. (2020, November 29-December 1). Biological hip torque estimation using a robotic hip exoskeleton. [Paper presentation]. 8th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob), New York, USA. https://doi.org/10.1109/biorob49111.2020.9224334
  
  Moreira, L., Figueiredo, J., Vilas-Boas, J. P., & Santos, C. P. (2021). Kinematics, Speed, and anthropometry-based ankle joint torque estimation: A deep learning regression approach. Machines, 9(8), Article 154. https://doi.org/10.3390/machines9080154
  
  Mundt, M., Johnson, W. R., Potthast, W., Markert, B., Mian, A., & Alderson, J. (2021). A comparison of three neural network approaches for estimating joint angles and moments from inertial measurement units. Sensors, 21(13), Article 4535. https://doi.org/10.3390/s21134535
  
  Mundt, M., Koeppe, A., David, S., Witter, T., Bamer, F., Potthast, W., & Markert, B. (2020). Estimation of gait mechanics based on simulated and measured IMU data using an artificial neural network. Frontiers in Bioengineering and Biotechnology, 8, Article 41. https://doi.org/10.3389/fbioe.2020.00041
  
  Naidu, G., Zuva, T., & Sibanda, E. M. (2023). A review of evaluation metrics in machine learning algorithms. In R. Silhavy & P. Silhavy (Eds.), Artificial Intelligence Application in Networks and Systems (pp. 15–25). Springer International Publishing. https://doi.org/10.1007/978-3-031-35314-7_2
  
  Ozates, M. E., Karabulut, D., Salami, F., Wolf, S. I., & Arslan, Y. Z. (2023). Machine learning-based prediction of joint moments based on kinematics in patients with cerebral palsy. Journal of Biomechanics, 155, Article 111668. https://doi.org/10.1016/j.jbiomech.2023.111668
  
  Peng, L., Hou, Z. G., & Wang, W. (2015, August 25-29). A dynamic EMG-torque model of elbow based on neural networks. [Paper presentation]. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy. https://doi.org/10.1109/EMBC.2015.7318986
  
  Perera, C. K., Gopalai, A. A., Gouwanda, D., Ahmad, S. A., & Salim, M. S. B. (2023). Sit-to-walk strategy classification in healthy adults using hip and knee joint angles at gait initiation. Scientific Reports, 13(1), Article 16640. https://doi.org/10.1038/s41598-023-43148-0
  
  Pizzolato, C., Lloyd, D. G., Sartori, M., Ceseracciu, E., Besier, T. F., Fregly, B. J., & Reggiani, M. (2015). CEINMS: A toolbox to investigate the influence of different neural control solutions on the prediction of muscle excitation and joint moments during dynamic motor tasks. Journal of Biomechanics, 48(14), 3929–3936. https://doi.org/10.1016/j.jbiomech.2015.09.021
  
  Schmidt, K., Duarte, J. E., Grimmer, M., Sancho-Puchades, A., Wei, H., Easthope, C. S., & Riener, R. (2017). The myosuit: Bi-articular anti-gravity exosuit that reduces hip extensor activity in sitting transfers. Frontiers in Neurorobotics, 11, Article 57. https://doi.org/10.3389/fnbot.2017.00057
  
  Schulte, R. V., Zondag, M., Buurke, J. H., & Prinsen, E. C. (2022). Multi-day EMG-based knee joint torque estimation using hybrid neuromusculoskeletal modelling and convolutional neural networks. Frontiers in Robotics and AI, 9, Article 869476. https://doi.org/10.3389/frobt.2022.869476
  
  Seth, A., Hicks, J. L., Uchida, T. K., Habib, A., Dembia, C. L., Dunne, J. J., Ong, C. F., DeMers, M. S., Rajagopal, A., Millard, M., Hamner, S. R., Arnold, E. M., Yong, J. R., Lakshmikanth, S. K., Sherman, M. A., Ku, J. P., & Delp, S. L. (2018). OpenSim: Simulating musculoskeletal dynamics and neuromuscular control to study human and animal movement. PLOS Computational Biology, 14(7), Article e1006223. https://doi.org/10.1371/journal.pcbi.1006223
  
  Siu, H. C., Sloboda, J., McKindles, R. J., & Stirling, L. A. (2021). A neural network estimation of ankle torques from electromyography and accelerometry. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 1624–1633. https://doi.org/10.1109/TNSRE.2021.3104761
  
  Su, C., Chen, S., Jiang, H., & Chen, Y. (2020). Ankle joint torque prediction based on surface electromyographic and angular velocity signals. IEEE Access, 8, 217681–217687. https://doi.org/10.1109/ACCESS.2020.3040820
  
  Taye, M. M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11(3), Article 52. https://doi.org/10.3390/computation11030052
  
  Truong, M. T. N., Ali, A. E. A., Owaki, D., & Hayashibe, M. (2023). EMG-Based estimation of lower limb joint angles and moments using long short-term memory network. Sensors, 23(6), Article 3331. https://doi.org/10.3390/s23063331
  
  Wang, L., & Buchanan, T. S. (2002). Prediction of joint moments using a neural network model of muscle activations from EMG signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 10(1), 30–37. https://doi.org/10.1109/TNSRE.2002.1021584
  
  Wang, M., Chen, Z., Zhan, H., Zhang, J., Wu, X., Jiang, D., & Guo, Q. (2023). Lower limb joint torque prediction using long short-term memory network and gaussian process regression. Sensors, 23(23), Article 9576. https://doi.org/10.3390/s23239576
  
  Winter, D. A. (2009). Biomechanics and Motor Control of Human Movement (4th ed.). Wiley. https://doi.org/10.1002/9780470549148.ch5
  
  Xia, K., Huang, J., & Wang, H. (2020). LSTM-CNN architecture for human activity recognition. IEEE Access, 8, 56855–56866. https://doi.org/10.1109/ACCESS.2020.2982225
  
  Yu, Y., Chen, C., Zhao, J., Sheng, X., & Zhu, X. (2022). Surface electromyography image-driven torque estimation of multi-dof wrist movements. IEEE Transactions on Industrial Electronics, 69(1), 795–804. https://doi.org/10.1109/TIE.2021.3050367
  
  Zhang, L., Soselia, D., Wang, R., & Gutierrez-Farewik, E. M. (2022). Lower-limb joint torque prediction using LSTM neural networks and transfer learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, 600–609. https://doi.org/10.1109/TNSRE.2022.3156786
  
  Zhang, L., Soselia, D., Wang, R., & Gutierrez-Farewik, E. M. (2023). Estimation of Joint Torque by EMG-Driven Neuromusculoskeletal Models and LSTM Networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering: A Publication of the IEEE Engineering in Medicine and Biology Society, 31, 3722–3731. https://doi.org/10.1109/TNSRE.2023.3315373
  
  Zhang, Q., Fragnito, N., Bao, X., & Sharma, N. (2022). A deep learning method to predict ankle joint moment during walking at different speeds with ultrasound imaging: A framework for assistive devices control. Wearable Technologies, 3, Article e20. https://doi.org/10.1017/wtc.2022.18