Res. Biomed. Eng. 2017
10.1590/2446-4740.01017 doi: http://dx.doi.org/10.1590/2446-4740.01017
Abstract:Introduction: Historically, assessing the quality of human gait has been a difficult process. Advanced studies can be conducted using modern 3D systems. However, due to their high cost, usage of these 3D systems is still restricted to research environments. 2D systems offer simpler and more affordable solutions. Methods: In this study, the gait of 40 volunteers walking on a treadmill was recorded in the sagittal plane, using a 2D motion capture system. The extracted joint angles data were used to create cyclograms. Sections of the cyclograms were used as inputs to artificial neural networks (ANNs), since they can represent the kinematic behavior of the lower body. This allowed for prediction of future states of the moving body. Results: The results indicate that ANNs can predict the future states of the gait with high accuracy. Both single point and section predictions were successfully performed. Pearson’s correlation coefficient and matched-pairs t-test ensured that the results were statistically significant. Conclusion: The combined use of ANNs and simple, accessible hardware is of great value in clinical practice. The use of cyclograms facilitates the analysis, as several gait characteristics can be easily recognized by their geometric shape. The predictive model presented in this paper facilitates generation of data that can be used in robotic locomotion therapy as a control signal or feedback element, aiding in the rehabilitation process of patients with motor dysfunction. The system proposes an interesting tool that can be explored to increase rehabilitation possibilities, providing better quality of life to patients.
Keywords:Gait, Cyclogram, Artificial Neural Network
Advanced Realtime Tracking. Arttrack system [software]. Weilheim: ART; 2017. [cited 2017 May 5]. Available from: http://www.ar-tracking.com/products/tracking-systems/arttrack-system/.
Associação Brasileira de Normas Técnicas. NBR 9050: acessibilidade a edificações, mobiliário, espaços e equipamentos urbanos. Rio de Janeiro: ABNT; 2004.
Barton J, Lees A. An application of neural networks for distinguishing gait patterns on the basis of hip-knee joint angle diagrams. Gait & Posture. 1997; 5(1):28-33. http://dx.doi.org/10.1016/S0966-6362(96)01070-3.
BTS Bioengineering. Smart-dx [internet]. Brooklyn: BTS; 2017. [cited 2017 May 5]. Available from: http://www.btsbioengineering.com/products/smart-dx/
Ellermeijer AL, Heck AJP. Walk like a physicist: an example of authentic education. In: Proceedings of the GIREP 2002 Conference [internet]; 2002 Aug 05-09; Lund, Sweden. Italy: GIREP; 2003 [cited 2017 May 5]. p. 1-13. Available from: https://www.researchgate.net/publication/228692663_Walk_like_a_Physicist_An_Example_of_Authentic_Education
Fisher S, Lucas L, Thrasher TA. Robot-assisted gait training for patients with hemiparesis due to stroke. Topics in Stroke Rehabilitation. 2011; 18(3):269-76. PMid:21642064. http://dx.doi.org/10.1310/tsr1803-269.
Forczek W, Staszkiewicz R. An evaluation of symmetry in the lower limb joints during the able-bodied gait of women and men. Journal of Human Kinetics. 2012; 35(1):47-57. PMid:23486255. http://dx.doi.org/10.2478/v10078-012-0078-5.
Goswami A. Kinematic quantification of gait symmetry based on bilateral cyclograms. In: Proceedings of the XIX Congress of the International Society of Biomechanics; 2003 July 6-11; Dunedin, New Zealand. Otago: University of Otago; 2003. p. 1-6.
Grieve DW. Gait patterns and the speed of walking. Bio-Medical Engineering. 1968; 3(3):119-22.
Hauke J, Kossowski T. Comparison of values of Pearson's and Spearman's correlation coefficients on the same sets of data. Quaestiones Geographicae. 2011; 30(2):87-93.
Inman VT, Ralston HJ, Todd F. Human walking. Filadélfia: Williams & Wilkins; 1981.
Jezernik S, Colombo G, Keller T, Frueh H, Morari M. Robotic orthosis lokomat: a rehabilitation and research tool. Neuromodulation. 2003; 6(2):108-15. PMid:22150969. http://dx.doi.org/10.1046/j.1525-1403.2003.03017.x.
Kendall FP, McCreary EK, Provance PG, Rodgers MM, Romani WA. Músculos: provas e funções com postura e dor. Barueri: Manole; 2007.
Kerrigan DC. Gait analysis. In: Delisa J, Gans B, editors. Rehabilitation medicine: principles and practice. Philadelphia: Williams & Wilkins; 1998. p. 167-87.
Kutilek P, Farkasova B. Prediction of lower extremities’ movement by angle-angle diagrams and neural networks. Acta of Bioengineering and Biomechanics. 2011; 13(2):57-65. PMid:22097908.
Kutilek P, Viteckova S. Prediction of lower extremity movement by cyclograms. Acta Polytechnica. 2012; 52(1):51-60.
Optitrack. Natural point optitrack hardware [internet]. Corvallis. 2017. [cited 2017 May 5]. Available from http://optitrack.com/hardware
Perry J. Análise de marcha: marcha normal. São Paulo: Manole; 2004.
Rudt S, Moos M, Seppey S, Riener R, Marchal-Crespo L. Towards more efficient robotic gait training: a novel controller to modulate movement errors. In: Proceedings of the 6th IEEE International Conference on Biomedical Robotics and Biomechatronics (BioRob); 2016 June 26-29; Singapure. Singapure: IEEE; 2016.
Saggini R, Barassi G, Ancona E, Carmignano SM, Sablone A, Bellomo RG. Effect of robotic gait training versus sensory-motor systems in rehabilitation of gait and balance impairment and fatigue in multiple sclerosis. Biophilia. 2016; 2(2):26. http://dx.doi.org/10.14813/ibra.2016.26.
Semwal VB, Raj M, Nandi GC. Biometric gait identification based on a multilayer perceptron. Robotics and Autonomous Systems. 2015; 65:65-75. http://dx.doi.org/10.1016/j.robot.2014.11.010.
Sharma DG, Yusuf R, Tanev I, Shimohara K. Human gait analysis based on biological evolutionary computing. Artificial Life and Robotics. 2016; 21(2):188-94. http://dx.doi.org/10.1007/s10015-016-0267-8.
Sutton RS, Barto G. Reinforcement learning: an Introduction. Cambridge: MIT Press; 1998.
Vries WHK, Veeger HEJ, Baten CTM, Helm FCT. Can shoulder joint reaction forces be estimated by neural networks? Journal of Biomechanics. 2016; 49(1):73-9. PMid:26654109. http://dx.doi.org/10.1016/j.jbiomech.2015.11.019.
Wang J. Pearson correlation coefficient: encyclopedia of systems biology. New York: Springer; 2013.
Yu H, Wilamowski BM. Levenberg–Marquardt training. In: Wilamowski BM, Irwin JD. Industrial electronics handbook: intelligent systems. Boca Raton: CRC Press; 2011. p. 1-16. [ Links ]