Multilayer perceptron for gait type classification based on inertial sensors data

Damian Szczepański

DOI: http://dx.doi.org/10.15439/2016F265

Citation: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 8, pages 947–950 (2016)

Full text

Abstract. In this study, the gait type classification process is considered. Input data are obtained by using the inertial sensors tracking system. Three types of gait are recorded: normal walk, tiptoeing and walk retaining long stance phase. Two data set types, describing the registered motion, are prepared. The most significant input features are selected by means of the sensitivity analysis (SA) procedure. The classification process is conducted using multilayer perceptron (MLP) with various structures. The classification accuracy of the network is computed with the use of a cross validation procedure. The obtained results show that the successful classification of presented gait types can be achieved using relatively simple MLP architecture.

References

Statistics on parkinson’s. Accessed: 2016-05-01. [Online]. Available: http://www.pdf.org/en/parkinson_statistics
A. Ferrari, A. G. Cutti, P. Garofalo, M. Raggi, M. Heijboer, A. Cappello, and A. Davalli, “First in vivo assessment of "outwalk": a novel protocol for clinical gait analysis based on inertial and magnetic sensors,” Medical & biological engineering & computing, vol. 48, no. 1, pp. 1–15, 2010.
A. Ferrari, “Technical innovations for the diagnosis and the rehabilitation of motor and perceptive impairments of the child with cerebral palsy,” 2010.
A. Szopa, M. Domagalska-Szopa, Z. Kidoń, and M. Syczewska, “Quadriceps femoris spasticity in children with cerebral palsy: measurement with the pendulum test and relationship with gait abnormalities,” Journal of neuroengineering and rehabilitation, vol. 11, no. 1, p. 1, 2014.
A. Martinez-Ramirez, P. Lecumberri, M. Gomez, and M. Izquierdo, “Wavelet analysis based on time–frequency information discriminate chronic ankle instability,” Clinical Biomechanics, vol. 25, no. 3, pp. 256–264, 2010.
H.-P. Brückner, W. Theimer, and H. Blume, “Real-time low latency movement sonification in stroke rehabilitation based on a mobile platform,” in Consumer electronics (ICCE), 2014 IEEE international conference on, 2014, pp. 242–243.
D. Morris, T. S. Saponas, A. Guillory, and I. Kelner, “Recofit: using a wearable sensor to find, recognize, and count repetitive exercises,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 2014, pp. 3225–3234.
A. W. Lam, A. HajYasien, and D. Kulic, “Improving rehabilitation exercise performance through visual guidance,” in Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE. IEEE, 2014, pp. 1735–1738.
Mvn biomech. Accessed: 2016-05-01. [Online]. Available: http://www.xsens.com/products/mvn-biomech
Matlab. Accessed: 2016-05-01. [Online]. Available: http://www.mathworks.com/products/matlab/
Dtreg predictive modeling software. Accessed: 2016-05-01. [Online]. Available: http://www.dtreg.com
Mvn studio software. Accessed: 2016-05-01. [Online]. Available: http://www.xsens.com/mvn-studio-pro
M. Romei, M. Galli, F. Motta, M. Schwartz, and M. Crivellini, “Use of the normalcy index for the evaluation of gait pathology,” Gait & posture, vol. 19, no. 1, pp. 85–90, 2004.
L. Schutte, U. Narayanan, J. Stout, P. Selber, J. Gage, and M. Schwartz, “An index for quantifying deviations from normal gait,” Gait & posture, vol. 11, no. 1, pp. 25–31, 2000.
R. Tadeusiewicz, Sieci neuronowe. Akademicka Oficyna Wydawnicza Warszawa, 1993.
J. Korbicz, A. Obuchowicz, and D. Uciński, “Artificial neural networks,” AOW PLJ, Warsaw, 1994.
D. E. Rumelhart, J. L. McClelland, and C. PDP Research Group, Eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations. Cambridge, MA, USA: MIT Press, 1986.