Gait features analysis using artificial neural networks : testing the footwear effect

• Autorzy: Wang J , Zielińska T.

Identyfikatory

DOI

10.5277/ABB-00490-2015-05

• Języki publikacji: EN

Abstrakty

EN

Purpose: The aim of this paper is to provide the methods for automatic detection of the difference in gait features depending on a footwear. Methods: Artificial neural networks were applied in the study. The gait data were recorded during the walk with different footwear for testing and validation of the proposed method. The gait properties were analyzed considering EMG (electromyography) signals and using two types of artificial neural networks: the learning vector quantization (LVQ) classifying network, and the clustering competitive network. Results: Obtained classification and clustering results were discussed. For comparative studies, velocities of the leg joint trajectories, and accelerations were used. The features indicated by neural networks were compared with the conclusions formulated analyzing the above mentioned trajectories for ankle and knee joints. Conclusions: The matching between experimentally recorded joint trajectories and the results given by neural networks was studied. It was indicated what muscles are most influenced by the footwear, the relation between the footwear type and the muscles work was concluded.

Słowa kluczowe

EN

neural network; footwear; gait; EMG

PL

sieć neuronowa; chód człowieka; obuwie; EMG

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Acta of Bioengineering and Biomechanics
• Rocznik: 2017
• Tom: Vol. 19, no. 1
• Strony: 17--32
• Opis fizyczny: Bibliogr. 20 poz., rys., wykr.

Twórcy

autor

Wang J

• Faculty of Power and Aeronautical Engineering, Warsaw University of Technology, Warsaw, Poland

autor

Zielińska T.

• Faculty of Power and Aeronautical Engineering, Warsaw University of Technology, Warsaw, Poland

Bibliografia

• [1] AL-MASHHADANY Y.I., Measurement of human leg joint angle through motion based on electromygraphy (EMG) signal, Iraqi Journal of Computers, Communications, Control and Systems Engineering, 2011, 11, 2.
• [2] ABEL E.W., ZACHARIA P.C., FORSTER A., FARROW T.L., Neural network analysis of the EMG interference pattern, Med. Eng. Phys., 1996, Vol. 18, No. 1, 12–17.
• [3] BLANCHETTE M.G., BRAULT J.R., POWERS C.M., The influence of heel height on utilized coefficient of friction during walking, Gait & Posture, 2011, 34, 107–110.
• [4] BARKEMA D.D., DERRICK T.R., MARTIN P.E., Heel height affects lower extremity frontal plane joint moments during walking, Gait Posture, 2012, 35(3), 483–488.
• [5] CAETANO D., MATTIOLI F., NOGUEIRA K., LAMOUNIER E., CARDOSO A., Comparison between MLP and LVQ neural networks for virtual upper limb prosthesis control, Intelligent Data Engineering and Automated Learning, 2012, Vol. 7435, 382–389.
• [6] DAVID R., ZIPSER D., MCCLELLAND J.L. et al., Parallel distributed processing, MIT Press, 1986, Vol. 1, 151–193.
• [7] DOLLAR A.M., HERR H., Lower extremity exoskeletons and active orthoses: challenges and state-of-the-art, Robotics, 2008, Vol. 24, No. 1, 144–158.
• [8] ERFANIAN A., CHIZECK H.J., HASHEMIL R.M., The relationship between joint angle and evoked EMG in electrically stimulated muscle, Engineering in Medicine and Biology Society, 1994, 345–346.
• [9] GUPTA A., VIVEKANANDAN S., EMG myopathy signal detection using wavelet transform and neural network techniques, International Journal of Science and Advanced Technology, 2012, Vol. 2, No. 4.
• [10] HO K., BLANCHETTE M.G., POWERS C.M., The influence of heel height on patella femoral joint kinetics during walking, Gait & Posture, 2012, 36, 271–275.
• [11] KACZMARCZYK K., WIT A. KRAWCZYK M., ZABORSKI J., Artificial neural networks (ANN) applied for gait classification and physiotherapy monitoring in post stroke patients, Artificial Neural Networks – Methodological Advances and Biomedical Applications, 2011, DOI: 10.5772/15363.
• [12] KOHONEN T., Self-organizing maps. Springer, Berlin, 1997.
• [13] KOHONEN T., Learning vector quantization, The Handbook of Brain Theory and Neural Networks, [in:] M.A. Arbib (ed.), MIT Press, Cambridge, MA, 1995, 537–540.
• [14] KITA K., KATO R., YOKOI H., Self-organized clustering approach for motion discrimination using EMG signal, 31st Annual International Conference of the IEEE EMBS, 2009, 2587–2590.
• [15] LI J.X., LEE S., Joint moment of lower limbs during walking with high-heeled shoes and asymmetric load carrying in young females, 30th Annual Conference of Biomechanics in Sports Melbourne, 2012, 30, 393.
• [16] LIU Z., LUO Z., Hand motion pattern classifier based on EMG using wavelet packet transform and LVQ neural networks, IT in Medicine and Education, 2008, 28–32.
• [17] MIKA A., CLARK B.C., OLEKSY Ł., The influence of high and low heeled shoes on EMG timing characteristics of the lumbar and hip extensor complex during trunk forward flexion and return task, Manual Therapy, 2013, 18(6), 506–511.
• [18] MOSLEM B., DIAB M.O., KHALIL M., MARQUE C., Classification of multichannel uterine EMG signals by using unsupervised competitive learning, Signal Processing Systems, 2011, 267–272.
• [19] SU X., GU Y., EMG in people with different heel height condition, Applications of EMG in Clinical and Sports Medicine, 2012. DOI: 10.5772/25672.
• [20] SUBASI A., YILMAZ M., OZCALIK H.R., Classification of EMG signals using wavelet neural network, Journal of Neuroscience Methods, 2006, 156, 360–367.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).