Neural Computing and Applications

, Volume 30, Issue 6, pp 1701–1713 | Cite as

Human knee joint walking pattern generation using computational intelligence techniques

  • João P. Ferreira
  • Alexandra Vieira
  • Paulo Ferreira
  • Manuel Crisóstomo
  • A. Paulo Coimbra


Computational intelligence techniques (CITs) can be used to generate the human knee joint angle walking pattern in the sagittal plane, useful in medical rehabilitation as a specific reference of normal pattern depending on the subject’s age, mass, height and stride duration. In this paper, the knee joint angle reference curves in the sagittal plane were generated by using three different CITs: artificial neural network, extreme learning machine (ELM) and multi-output support vector regression. The gait pattern of a woman is different of the gait pattern of a man, and consequently, their knee joint angle curves are also different. Thus, it was necessary to train and test each of the three CITs for each gender. The data used by the CIT were obtained from volunteers with healthy gait and with different characteristics (gender, age, height and weight). The volunteers’ knee joint angle curves were collected by a system mainly constituted by a treadmill, two web cameras and passive marks positioned at volunteers’ joints. These gait analyses were made for five different walking speeds. It was observed that the best curves for each gender were generated using the ELM. Therefore, the ELM can be used to generate the normal knee joint angle curves expected for any person with specific characteristics (age, mass, height, stride duration), and physicians can use these specific normal curves for comparison purposes instead of using the standard knee joint angle curves of the literature which do not take into consideration the specific characteristics of the joint angle source.


ANN ELM MSVR Knee Gait Healthy 



This work has been supported by Fundação para a Ciência e a Tecnologia (FCT) and project “ProjB -Diagnosis and Assisted Mobility - Centro-07-ST24-FEDER-002028” with FEDER funding, programs QREN and COMPETE. The authors also acknowledge FCT and COMPETE 2020 program for the financial support to the project “Automatic Adaptation of an Humanoid Robot Gait to Different Floor-Robot Friction Coefficients” (PTDC/EEI-AUT/5141/2014).

Compliance with ethical standards

Conflict of interest

Authors declare that they have no conflict of interest.


  1. 1.
    Caldas R, Mundt M, Potthast W, Buarque de Lima Neto F, Markert B (2017) A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms. Gait Posture 57(February):204–210CrossRefGoogle Scholar
  2. 2.
    Pirker W, Katzenschlager R (2017) Gait disorders in adults and the elderly: a clinical guide. Wien Klin Wochenschr 129(3–4):81–95CrossRefGoogle Scholar
  3. 3.
    Muro-de-la-Herran A, García-Zapirain B, Méndez-Zorrilla A (2014) Gait analysis methods: an overview of wearable and non-wearable systems, highlighting clinical applications. Sensors (Switzerland) 14(2):3362–3394CrossRefGoogle Scholar
  4. 4.
    Horst F, Mildner M, Schöllhorn WI (2017) One-year persistence of individual gait patterns identified in a follow-up study—a call for individualised diagnose and therapy. Gait Posture 58(September):476–480CrossRefGoogle Scholar
  5. 5.
    Luu TP, Low KH, Qu X, Lim HB, Hoon KH (2014) An individual-specific gait pattern prediction model based on generalized regression neural networks. Gait Posture 39(1):443–448CrossRefGoogle Scholar
  6. 6.
    Yun Y, Kim H-C, Shin SY, Lee J, Deshpande AD, Kim C (2014) Statistical method for prediction of gait kinematics with Gaussian process regression. J Biomech 47(1):186–192CrossRefGoogle Scholar
  7. 7.
    Nair BM, Kendricks KD (2016) Deep network for analyzing gait patterns in low resolution video towards threat identification. Electron Imaging 2016(11):1–8CrossRefGoogle Scholar
  8. 8.
    Zeng W, Liu F, Wang Q, Wang Y, Ma L, Zhang Y (2016) Parkinson’s disease classification using gait analysis via deterministic learning. Neurosci Lett 633:268–278CrossRefGoogle Scholar
  9. 9.
    Pushpa Rani GAM (2010) Children abnormal GAIT classification using extreme learning machine. Glob J Comput Sci Technol 10(13):66–72Google Scholar
  10. 10.
    Kong W, Saad MH, Hannan MA, Hussain A (2014) Human gait state classification using artificial neural network. In: 2014 IEEE symposium on computational intelligence for multimedia, signal and vision processing (CIMSIVP), 9–12 December 2014. Google Scholar
  11. 11.
    Triloka J, Senanayake SMNA, Lai D (2017) Neural computing for walking gait pattern identification based on multi-sensor data fusion of lower limb muscles. Neural Comput Applic 28(Suppl 1):65. CrossRefGoogle Scholar
  12. 12.
    Semwal VB, Mondal K, Nandi GC (2015) Robust and accurate feature selection for humanoid push recovery and classification: deep learning approach. Neural Comput Appl 28(3):565–574CrossRefGoogle Scholar
  13. 13.
    Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501CrossRefGoogle Scholar
  14. 14.
    Ferreira PA, Ferreira JP, Crisóstomo M, Coimbra AP (2016) Low cost vision system for human gait acquisition and characterization. IEEE Int. Conf Ind Eng Eng Manag 2016:291–295Google Scholar
  15. 15.
    Bohannon RW (1997) Comfortable and maximum walking speed of adults aged 20–79 years: reference values and determinants. Age Ageing 26(1):15–19CrossRefGoogle Scholar
  16. 16.
    Hagan MT, Demuth HB, Beale MH (1996) Neural network design. PWS Publishing Company, New YorkGoogle Scholar
  17. 17.
    Oberg T, Karsznia A, Oberg K (1994) Joint angle parameters in gait: reference data for normal subjects, 10–79 years of age. J Rehabil Res Dev 31(3):199–213Google Scholar
  18. 18.
    Kaczmarczyk K, Wit A, Krawczyk M, Zaborski J (2011) Artificial neural networks ANN applied for gait classification and physiotherapy monitoring in post stroke patients. In: Suzuki K (ed) Artificial neural networks—methodological advances and biomedical applications, Chap 16. ISBN 978-953-307-243-2
  19. 19.
    Erzin Y, Turkoz D (2016) Use of neural networks for the prediction of the CBR value of some Aegean sands. Neural Comput Appl 27(5):1415–1426CrossRefGoogle Scholar
  20. 20.
  21. 21.
    Finker R, Campo I, Echanobe J, Martínez V (2014) An intelligent embedded system for real-time adaptive extreme learning machine. In: 2014 IEEE symposium on intelligent embedded systems (IES), 9–12 December 2014. Google Scholar
  22. 22.
    Huang Y (2009) Advances in artificial neural networks—methodological development and application. Algorithms 2(3):973–1007MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Hornik K, Stinchcomb M, White H (1989) Multilayer feedforward Networks are universal approximators. Neural Netw 2(5):359–366. CrossRefzbMATHGoogle Scholar
  24. 24.
    Huang G, Huang G-B, Song S, You K (2015) Trends in extreme learning machines: a review. Neural Networks 61:32–48CrossRefzbMATHGoogle Scholar
  25. 25.
    Yanwei H, Dengguo W (2011) Nonlinear internal model control with inverse model based on extreme learning machine. In: Proceedings of the international conference on electric information and control engineering (ICEICE '11). pp 2391–2395Google Scholar
  26. 26.
    Lin S, Liu X, Fang J, Xu Z (2014) Is extreme learning machine feasible? a theoretical assessment (Part II). IEEE Trans Neural Netw Learn Sys, pp 21–34.
  27. 27.
    Maliha A, Yusof R, Shapiai MI (2016) Extreme learning machine for structured output spaces. Neural Comput Applic. Google Scholar
  28. 28.
    Huang G-B, Ding X, Zhou H (2010) Optimization method based extreme learning machine for classification. Neurocomputing 74(1–3):155–163CrossRefGoogle Scholar
  29. 29.
    Pérez-Cruz F, Camps-Valls G, Soria-Olivas E, Pérez-Ruixo JJ, Figueiras-Vidal AR, Artés-Rodríguez A (2002) Multi-dimensional function approximation and regression estimation. In: Dorronsoro JR (ed) Artificial neural networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin. Google Scholar
  30. 30.
    Xu Y, Lv X, Xi W (2012) A weighted multi-output support vector regression and its application. J Comput Inf Syst 8(9):3807–3814Google Scholar
  31. 31.
    Shetty S, Rao YS (2016) SVM based machine learning approach to identify Parkinson’s disease using gait analysis. In: Inventive Computation Technologies (ICICT), international conference, vol 2. IEEEGoogle Scholar
  32. 32.
    Ferreira JP, Crisostomo MM, Coimbra AP (2009) SVR versus neural-fuzzy network controllers for the sagittal balance of a biped robot. IEEE Trans Neural Netw 20(12):1885–1897CrossRefGoogle Scholar
  33. 33.
    Tuia D, Verrelst J, Alonso L, Perez-Cruz F, Camps-Valls G (2011) Multioutput support vector regression for remote sensing biophysical parameter estimation. IEEE Geosci Remote Sens Lett 8(4):804–808CrossRefGoogle Scholar
  34. 34.
    Ribeiro B, Lopes N (2013) Extreme learning classifier with deep concepts. Lecture Notes on Computer Science (including Subseries Lecture Notes Artificial Intelligence Lecture Notes on Bioinformatics), vol 8258 LNCS, no. PART 1, pp 182–189Google Scholar
  35. 35.
    Gomes A, Araújo N, Meneghesso L, Ricardo A, Leite M (2005) System for kinematical analysis of the human gait based on videogrammetry Metodologia Modelo biomecânico. Fisioter e Pesqui 11:3–10Google Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  1. 1.Institute Superior of Engineering of CoimbraCoimbraPortugal
  2. 2.Department of Electrical and Computer Engineering, Institute of Systems and RoboticsUniversity of CoimbraCoimbraPortugal

Personalised recommendations