Artificial Intelligence Approach in Biomechanical Analysis of Gait.

Document Type : Original research papers

Authors

1 Department of Sports Biomechanics, Central Tehran Branch, Islamic Azad University, Tehran

2 Department of Sports Biomechanics, Faculty of Physical Education and Sports Science, Islamic Azad University of Central Tehran Branch, Tehran, Iran.

3 Department of Sport Injuries and Corrective Exercises, Sports Medicine Research Center, Sport Sciences Research Institute, Tehran, Iran

4 Department of Sports Biomechanics, Sport Sciences Research Institute, Tehran, Iran.

Abstract

The objective of the current investigation was to conduct a biomechanical analysis of human gait based on the Unsupervised machine learning – Artificial Intelligence approach. Twenty-eight junior active males participated in the study. Following the placement of the markers, the participants were asked to complete the gait task in a 10-meter gateway where the dominant leg contact was placed on the third step and non- non-dominant leg on the fourth step. The task was executed in two separate attempts, first by the preferred speed of the participants and second with a steady speed of 100BPM. The Hierarchical approach consisting of Nearest Neighbor and the utilization of Z score was employed to discern uniform gait biomechanical patterns of the entire participant according to the values of joint angles and joint moments in both conditions - preferred and steady speeds by SPSS software version 26 (p<0.05). Considering a combination of both kinematics and kinetics parameters, in preferred speed, the hip and knee in the vertical direction for both dominant and non-dominant limbs are classified in one cluster, but in a steady speed, the hip in mediolateral direction and knee in the vertical direction for both dominant and non-dominant limbs are presented in one cluster. The kinematic and kinetic variables are useful in gate clustering to categorize gait patterns. These variables can be subdivided into homogeneous subgroups for a more detailed understanding of human locomotion.

Keywords

Main Subjects

References

  1. Khera P, Kumar N. Role of machine learning in gait analysis: a review. Journal of Medical Engineering & Technology. 2020;44(8):441-67.
  2. Molavian R, Salehi M, Alizadeh R. A Comparison of Kinematic Symmetry of Lower Limbs during Running at Different Speeds. Journal of Clinical Physiotherapy Research. 2021,6(4):e4, https://doi.org/10.22037/jcpr.v6i3.34467.
  3. Fatahi A, Molaviaan R. Comparison of Kinematics and kinetics Symmetry of Lower Limbs during running. Journal of Exercise Science and Medicine. 2020;12(2) : 217-225. doi: 10.32598/JESM.12.2.10.
  4. Phinyomark A, Petri G, Ibáñez-Marcelo E, Osis ST, Ferber R. Analysis of big data in gait biomechanics: Current trends and future directions. Journal of medical and biological engineering. 2018;38:244-60.
  5. Izhar CAA, Hussain Z, Maruzuki M, Sulaiman MS, Abd Rahim A. Gait cycle prediction model based on gait kinematic using machine learning technique for assistive rehabilitation device. IAES International Journal of Artificial Intelligence. 2021;10(3):752-763. DOI:10.11591/ijai.v10.i3.pp752-763.
  6. Farah JD, Baddour N, Lemaire ED, editors. Gait phase detection from thigh kinematics using machine learning techniques. 2017 IEEE International Symposium on Medical Measurements and Applications (MeMeA); 2017: IEEE.
  7. Dolatabadi E, Taati B, Mihailidis A. An automated classification of pathological gait using unobtrusive sensing technology. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2017;25(12):2336-46.
  8. Lai DT, Begg RK, Palaniswami M. Computational intelligence in gait research: a perspective on current applications and future challenges. IEEE Transactions on Information Technology in Biomedicine. 2009;13(5):687-702.
  9. Paulo J, Peixoto P, Amorim P. Trajectory-based gait pattern shift detection for assistive robotics applications. Intelligent Service Robotics. 2019;12:255-64.
  10. Kutilek P, Hozman J, editors. Prediction of lower extremities movement using characteristics of angle-angle diagrams and artificial intelligence. 2011 E-Health and Bioengineering Conference (EHB); 2011: IEEE.
  11. Farah JD, Baddour N, Lemaire ED. Design, development, and evaluation of a local sensor-based gait phase recognition system using a logistic model decision tree for orthosis-control. Journal of neuroengineering and rehabilitation. 2019;16(1):1-11.
  12. Begg R, Kamruzzaman J. Neural networks for detection and classification of walking pattern changes due to ageing. Australasian Physics & Engineering Sciences in Medicine. 2006;29:188-95.
  13. Lau H-Y, Tong K-Y, Zhu H. Support vector machine for classification of walking conditions using miniature kinematic sensors. Medical & biological engineering & computing. 2008;46:563-73.
  14. Faraji B, Khezri D. Ultra-Local Model Control of Parkinson's Patients Based on Machine Learning. Journal of Advanced Sport Technology. 2021;5(1):1-16.
  15. Souza AdMe, Stemmer MR. Extraction and classification of human body parameters for gait analysis. Journal of Control, Automation and Electrical Systems. 2018;29:586-604.
  16. Shim H-m, Lee S. Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience. Journal of Central South University. 2015;22(5):1801-8.
  17. Wei W, McElroy C, Dey S, editors. Human Action Understanding and Movement Error Identification for the Treatment of Patients with Parkinson's Disease. 2018 IEEE International Conference on Healthcare Informatics (ICHI); 2018: IEEE.
  18. Leightley D, McPhee JS, Yap MH. Automated analysis and quantification of human mobility using a depth sensor. IEEE journal of biomedical and health informatics. 2016;21(4):939-48.
  19. Van Gestel L, De Laet T, Di Lello E, Bruyninckx H, Molenaers G, Van Campenhout A, et al. Probabilistic gait classification in children with cerebral palsy: A Bayesian approach. Research in Developmental Disabilities. 2011;32(6):2542-52.
  20. Mu T, Pataky TC, Findlow AH, Aung MS, Goulermas JY. Automated nonlinear feature generation and classification of foot pressure lesions. IEEE Transactions on Information Technology in Biomedicine. 2009;14(2):418-24.
  21. Khezri D, Eslami M, Yousefpour R. Clustering healthy runner based on 3-D kinematics patterns of pelvic during running using hierarchical method. Journal of Applied Exercise Physiology. 2019;14(28):227-40.
  22. Yoo TK, Kim SK, Choi SB, Kim DY, Kim DW, editors. Interpretation of movement during stair ascent for predicting severity and prognosis of knee osteoarthritis in elderly women using support vector machine. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2013: IEEE.
  23. Xiong B, Zeng N, Li H, Yang Y, Li Y, Huang M, et al. Intelligent prediction of human lower extremity joint moment: An artificial neural network approach. IEEE Access. 2019;7:29973-80.
  24. Zeng W, Ismail SA, Pappas E. Classification of gait patterns in patients with unilateral anterior cruciate ligament deficiency based on phase space reconstruction, Euclidean distance and neural networks. Soft Computing. 2020;24(3):1851-68.
  25. Alaqtash M, Sarkodie-Gyan T, Yu H, Fuentes O, Brower R, Abdelgawad A, editors. Automatic classification of pathological gait patterns using ground reaction forces and machine learning algorithms. 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2011: IEEE.
  26. Devanne M, Wannous H, Daoudi M, Berretti S, Del Bimbo A, Pala P, editors. Learning shape variations of motion trajectories for gait analysis. 2016 23rd International Conference on Pattern Recognition (ICPR); 2016: IEEE.
  27. Costa Á, Iáñez E, Úbeda A, Hortal E, Del-Ama AJ, Gil-Agudo A, et al. Decoding the attentional demands of gait through EEG gamma band features. PLoS one. 2016;11(4):e0154136. https://doi.org/10.1371/journal.pone.0154136.
  28. Goh SK, Abbass HA, Tan KC, Al-Mamun A, Thakor N, Bezerianos A, et al. Spatio–spectral representation learning for electroencephalographic gait-pattern classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2018;26(9):1858-67.
  29. Paulo J, Peixoto P, Nunes UJ. ISR-AIWALKER: Robotic walker for intuitive and safe mobility assistance and gait analysis. IEEE Transactions on Human-Machine Systems. 2017;47(6):1110-22.
  30. Liu D-X, Du W, Wu X, Wang C, Qiao Y, editors. Deep rehabilitation gait learning for modeling knee joints of lower-limb exoskeleton. 2016 IEEE international conference on robotics and biomimetics (ROBIO); 2016: IEEE.
  31. Thongsook A, Nunthawarasilp T, Kraypet P, Lim J, Ruangpayoongsak N, editors. C4. 5 decision tree against neural network on gait phase recognition for lower limp exoskeleton. 2019 First International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP); 2019: IEEE.
  32. Mezghani N, Fuentes A, Gaudreault N, Mitiche A, Aissaoui R, Hagmeister N, et al. Identification of knee frontal plane kinematic patterns in normal gait by principal component analysis. Journal of Mechanics in Medicine and Biology. 2013;13(03):1350026-13.
  33. Simonsen EB, Alkjær T. The variability problem of normal human walking. Medical engineering & physics. 2012;34(2):219-24.
  34. Vardaxis VG, Allard P, Lachance R, Duhaime M. Classification of able-bodied gait using 3-D muscle powers. Human Movement Science. 1998;17(1):121-36.
  35. Phinyomark A, Osis S, Hettinga BA, Ferber R. Kinematic gait patterns in healthy runners: A hierarchical cluster analysis. Journal of biomechanics. 2015;48(14):3897-904.
  36. Roche N, Pradon D, Cosson J, Robertson J, Marchiori C, Zory R. Categorization of gait patterns in adults with cerebral palsy: a clustering approach. Gait & Posture. 2014;39(1):235-40.
  37. Toro B, Nester CJ, Farren PC. Cluster analysis for the extraction of sagittal gait patterns in children with cerebral palsy. Gait & posture. 2007;25(2):157-65.
  38. Ferrarin M, Bovi G, Rabuffetti M, Mazzoleni P, Montesano A, Pagliano E, et al. Gait pattern classification in children with Charcot–Marie–Tooth disease type 1A. Gait & posture. 2012;35(1):131-7.
  39. Kinsella S, Moran K. Gait pattern categorization of stroke participants with equinus deformity of the foot. Gait & posture. 2008;27(1):144-51.
  40. Watelain E, Barbier F, Allard P, Thevenon A, Angué J-C. Gait pattern classification of healthy elderly men based on biomechanical data. Archives of physical medicine and rehabilitation. 2000;81(5):579-86.
  41. Hoerzer S, von Tscharner V, Jacob C, Nigg BM. Defining functional groups based on running kinematics using Self-Organizing Maps and Support Vector Machines. Journal of biomechanics. 2015;48(10):2072-9.
  42. Ezugwu AE, Ikotun AM, Oyelade OO, Abualigah L, Agushaka JO, Eke CI, et al. A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Engineering Applications of Artificial Intelligence. 2023;56:6439-6475. https://doi.org/10.1007/s10462-022-10325-y.
  43. Saxena A, Prasad M, Gupta A, Bharill N, Patel OP, Tiwari A, et al. A review of clustering techniques and developments. Neurocomputing. 2017;267:664-81.
  44. Ruff L, Kauffmann JR, Vandermeulen RA, Montavon G, Samek W, Kloft M, et al. A unifying review of deep and shallow anomaly detection. Proceedings of the IEEE. 2021;109(5):756-95.
  45. Grau S, Maiwald C, Krauss I, Axmann D, Horstmann T. The influence of matching populations on kinematic and kinetic variables in runners with iliotibial band syndrome. Research quarterly for exercise and sport. 2008;79(4):450-7.
  46. Hreljac A, Ferber R. A biomechanical perspective of predicting injury risk in running. International SportMed Journal. 2006;7(2):98-108.
  47. Ferber R, Hreljac A, Kendall KD. Suspected mechanisms in the cause of overuse running injuries: a clinical review. Sports health. 2009;1(3):242-6.
  48. Fukuchi RK, Stefanyshyn DJ, Stirling L, Duarte M, Ferber R. Flexibility, muscle strength and running biomechanical adaptations in older runners. Clinical Biomechanics. 2014;29(3):304-10.
  49. Phinyomark A, Hettinga BA, Osis ST, Ferber R. Gender and age-related differences in bilateral lower extremity mechanics during treadmill running. PloS one. 2014;9(8):e105246.
  50. Osis ST, Hettinga BA, Macdonald SL, Ferber R. A novel method to evaluate error in anatomical marker placement using a modified generalized Procrustes analysis. Computer methods in biomechanics and biomedical engineering. 2015;18(10):1108-16.

 

 

 

Files

History

  • Receive Date: 01 July 2023
  • Revise Date: 05 August 2023
  • Accept Date: 04 September 2023

Share

How to cite

Statistics