Skip to main content

Advertisement

SpringerLink
Log in

Estimation of lower limb joint moments based on the inverse dynamics approach: a comparison of machine learning algorithms for rapid estimation

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

A Correction to this article was published on 15 September 2023

This article has been updated

Abstract

The aim of this study is to estimate the joint moments of the ankle, knee, and hip joints during walking. A sit-to-stand (STS) movement analysis was first performed on 20 participants with different anthropometric characteristics. Then, analysis of the dynamics of the STS motion was used to develop a biomechanical model. Decision tree (DT), linear regression (LR), support vector machine (SVM), random forest (RF), and three deep learning (DL) algorithms and deep neural network (DNN), long-short-term memory (LSTM), and convolutional neural network (CNN) are examined in this work to estimate three joint moments: ankle, knee, and hip. The results of the seven algorithms were evaluated using four statistical benchmarks: MSR, RMSE, correlation coefficient (R), and MAE to find the most accurate one. The results show that the most successful algorithms were LSTM in estimating knee, hip, and ankle joint moments using 19 and 7 inputs. The R value was 0.9990 using 19 inputs and 0.9972 using 7 inputs. The other algorithms have a correlation coefficient (R) success of 0.9902, 0.9770, 0.9884, 0.9577, 0.9786, and 0.9022 for RF, CNN, DT, DNN, SVM, and LR, respectively. The prediction of joint moments plays a crucial role in the design of the biomechanical system with the desired mechanical properties. Especially, the need has arisen to predict joint moments in a shorter time to utilize in real-time active prosthesis/orthosis controllers.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Change history

References

  1. Shkedy Rabani A, Mizrachi S, Sawicki GS, Riemer R (2022) 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

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Yamagata M, Tateuchi H, Asayama A, Ichihashi N (2022) Influence of lower-limb muscle inactivation on medial and lateral knee contact forces during walking. Med Eng Phys 108:103889

  3. Banks JJ, Umberger BR, Caldwell GE (2022) EMG optimization in Open- Sim: a model for estimating lower back kinetics in gait. Med Eng Phys 103:103790

    Article  PubMed  Google Scholar 

  4. Cilli M, Serbest K, Kayaoglu E (2021) The effect of body weight on joint torques in teenagers: investigation of sit-to-stand movement. Clinical Biomech 83:105288

    Article  Google Scholar 

  5. Hahn ME (2007) Feasibility of estimating isokinetic knee torque using a neural network model. J Biomech 40(5):1107–1114

    Article  PubMed  Google Scholar 

  6. Ardestani MM, Zhang X, Wang L et al (2014) Human lower extremity joint moment prediction: a wavelet neural network approach. Expert Syst App 41(9):4422–4433

    Article  Google Scholar 

  7. Xiong B, Zeng N, Li H et al (2019) Intelligent prediction of human lower extremity joint moment: an artificial neural network approach. IEEE Access 7:29973–29980

    Article  Google Scholar 

  8. Mundt M, Koeppe A, David S et al (2020) Estimation of gait mechanics based on simulated and measured IMU data using an artificial neural network. Frontiers in bioengineering and biotechnology 8:41

    Article  PubMed  PubMed Central  Google Scholar 

  9. Zhang Q, Clark WH, Franz JR, Sharma N (2022) Personalized fusion of ultrasound and electromyography-derived neuromuscular features increases prediction accuracy of ankle moment during plantarflexion. Biomed Signal Process Control 71:103100

    Article  Google Scholar 

  10. Zell P, Rosenhahn B (2020) Learning inverse dynamics for human locomotion analysis. Neural Comput App 32(15):11729–11743

  11. Burton IIWS, Myers CA, Rullkoetter PJ (2021) Machine learning for rapid estimation of lower extremity muscle and joint loading during activities of daily living. J Biomech 123:110439

    Article  PubMed  Google Scholar 

  12. Prentice AM, Jebb SA (2001) Beyond body mass index. Obes Rev 2(3):141–147

    Article  CAS  PubMed  Google Scholar 

  13. Mohajan D, Mohajan HK (2023) Body mass index (BMI) is a popular anthropometric tool to measure obesity among adults. J Innov Med Res 2(4):25–33

    Article  Google Scholar 

  14. Organization WH (2000) Obesity: preventing and managing the global epidemic

  15. Kuo YL, Tully EA, Galea MP (2010) Kinematics of sagittal spine and lower limb movement in healthy older adults during sit-to-stand from two seat heights. Spine 35(1):E1–E7

    Article  PubMed  Google Scholar 

  16. Kadaba MP, Ramakrishnan H, Wootten M (1990) Measurement of lower extremity kinematics during level walking. J Orthop Res 8(3):383–392

    Article  CAS  PubMed  Google Scholar 

  17. Zajac FE, Neptune RR, Kautz SA (2002) Biomechanics and muscle coordination of human walking: Part I: Introduction to concepts, power transfer, dynamics and simulations. Gait & Posture 16(3):215–232

    Article  Google Scholar 

  18. Yeadon MR (1990) The simulation of aerial movement—II. A mathematical inertia model of the human body. J Biomech 23(1):67–74

  19. Mansouri M, Reinbolt JA (2012) A platform for dynamic simulation and control of movement based on OpenSim and MATLAB. J Biomech 45(8):1517–1521

  20. Abtahi SMA, Jamshidi N, Ghaziasgar A (2018) The effect of knee-ankle- foot orthosis stiffness on the parameters of walking. Comput Methods Biomech Biomed Eng 21(3):201–207

    Article  Google Scholar 

  21. Trentin E (2015) Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction. Pattern Recogn Lett 66:71–80

    Article  Google Scholar 

  22. Senvar O, Sennaroglu B (2016) Comparing performances of Clements, Box-Cox, Johnson methods with Weibull distributions for assessing process capability. J Ind Eng Manag 9(3):634–656

  23. Singh D, Singh B (2020) Investigating the impact of data normalization on classification performance. Appl Soft Comput 97:105524

    Article  Google Scholar 

  24. Karapinar Senturk Z, Sevgul Bakay M (2021) Machine learning- based hand gesture recognition via EMG data

  25. Alpaydin E (2020) Introduction to machine learning. MIT press

  26. Akour I, Alshurideh M, Al Kurdi B, Al Ali A, Salloum S (2021) Using machine learning algorithms to predict people’s intention to use mobile learning platforms during the COVID-19 pandemic: machine learning approach. JMIR Med Educ 7(1):e24032

  27. Quiroz JC, Feng YZ, Cheng ZY et al (2021) Development and validation of a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data: retrospective study. JMIR Med Inf 9(2):e24572

    Article  Google Scholar 

  28. Najafabadi MM, Villanustre F, Khoshgoftaar TM, Seliya N, Wald R, Muharemagic E (2015) Deep learning applications and challenges in big data analytics. J Big Data 2(1):1–21

    Article  Google Scholar 

  29. Miyato T, Si Maeda, Koyama M, Ishii S (2018) Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans Pattern Anal Mach Intell 41(8):1979–1993

    Article  PubMed  Google Scholar 

  30. Chen Y,Wang X, Zhang B (2018) An unsupervised deep learning approach for scenario forecasts. In: IEEE. 1–7

  31. Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: 144–152

  32. Wen L, Cao Y (2020) Influencing factors analysis and forecasting of residential energy-related CO2 emissions utilizing optimized support vector machine. J Clean Prod 250:119492

    Article  CAS  Google Scholar 

  33. Zhang Z, Li Y, Li L, Li Z, Liu S (2019) Multiple linear regression for high efficiency video intra coding. In: IEEE. 1832–1836

  34. Das R (2010) A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Syst Appl 37(2):1568–1572

  35. Kumar SA et al (2011). Efficiency of decision trees in predicting student’s academic performance

  36. Saber M, El Rharras A, Saadane R, Aroussi HK, Wahbi M (2019) Artificial neural networks, support vector machine and energy detection for spectrum sensing based on real signals. Int J Commun Netw Inf Secur 11(1):52–60

    Google Scholar 

  37. Agrawal SK, Banala SK, Fattah A et al (2007) Assessment of motion of a swing leg and gait rehabilitation with a gravity balancing exoskeleton. IEEE Trans Neural Sys Rehabil Eng 15(3):410–420

    Article  Google Scholar 

  38. Mapaisansin P, Suriyaamarit D, Boonyong S (2020) The development of sit-to-stand in typically developing children aged 4 to 12 years: movement time, trunk and lower extremity joint angles, and joint moments. Gait & Posture 76:14–21

  39. Schmid S, Luder G, Mebes CM et al (2013) Neuromechanical gait adaptations in women with joint hypermobility-an exploratory study. Clin Biomech 28(9–10):1020–1025

    Article  Google Scholar 

  40. Mundt M, Thomsen W, Witter T et al (2020) Prediction of lower limb joint angles and moments during gait using artificial neural networks. Med Biol Eng Comput 58(1):211–225

Download references

Author information

Authors and Affiliations

  1. Mechatronics Engineering, Sakarya University of Applied Sciences, Serdivan, Sakarya, 54050, Turkey

    Mohammed Mansour, Kasim Serbest & Mustafa Kutlu

  2. Coaching Education, Sakarya University of Applied Sciences, Serdivan, Sakarya, 54050, Turkey

    Murat Cilli

Authors
  1. Mohammed Mansour
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kasim Serbest
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mustafa Kutlu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Murat Cilli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammed Mansour.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original online version of this article was revised: Graphical abstract image was incorrect.

Appendix. Figure results

Appendix. Figure results

Fig. 11
figure 11

LR

Full size image
Fig. 12
figure 12

RF

Full size image
Fig. 13
figure 13

DT

Full size image
Fig. 14
figure 14

DNN

Full size image
Fig. 15
figure 15

LSTM

Full size image
Fig. 16
figure 16

CNN

Full size image
Fig. 17
figure 17

SVM

Full size image
Fig. 18
figure 18

LR

Full size image
Fig. 19
figure 19

RF

Full size image
Fig. 20
figure 20

DT

Full size image
Fig. 21
figure 21

DNN

Full size image
Fig. 22
figure 22

LSTM

Full size image
Fig. 23
figure 23

CNN

Full size image
Fig. 24
figure 24

SVM

Full size image
Fig. 25
figure 25

LR

Full size image
Fig. 26
figure 26

RF

Full size image
Fig. 27
figure 27

DT

Full size image
Fig. 28
figure 28

DNN

Full size image
Fig. 29
figure 29

LSTM

Full size image
Fig. 30
figure 30

CNN

Full size image

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mansour, M., Serbest, K., Kutlu, M. et al. Estimation of lower limb joint moments based on the inverse dynamics approach: a comparison of machine learning algorithms for rapid estimation. Med Biol Eng Comput 61, 3253–3276 (2023). https://doi.org/10.1007/s11517-023-02890-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02890-3

Keywords

Search

Navigation