FAST USER ACTIVITY PHASE RECOGNITION FOR THE SAFETY OF TRANSFEMORAL PROSTHESIS CONTROL

Aleksandr Poliakov, Vladimir Pakhaliuk

DOI Number
https://doi.org/10.22190/FUME190210004P
First page
135
Last page
151

Abstract


In the process of creating powered transfemoral prostheses, one of the most important tasks is the provision of the user safety while walking. Experience shows that security depends not only on the mechanical strength of such devices, but also on the quality of their control systems, which, among other things, must ensure that latency and error rates of recognition are acceptable for each of the possible changes in gait. Incorrect or late recognition of the activity mode at best can lead to suboptimal assistance from the auxiliary device, and at worst - to loss of stability of the user with a subsequent fall. Loss of stability can also occur due to exceeding the critical time or critical errors of the activity phase recognition and the associated incorrect commands generated by the control system. In this paper, a method for quickly recognizing the phase of the user's activity based on the properties of Hu’s moment invariants is substantiated. Its use in the intelligent control systems will minimize the critical errors that contribute to the loss of the user's equilibrium with the powered transfemoral prosthesis.

Keywords

Powered Transfemoral Prosthesis, Safety, Activity Mode, Activity Phase, Recognition, Moment Invariant

Full Text:

PDF

References


Poliakov, A., Pakhaliuk, V., Kolesova, M., Shtanko, P., Ovchinnikova, M., 2017, Transfemoral prostheses control in a frame of intellectual-synergetic concept, Proc. of the 2017 2nd Int. Conf. on Autom., Mech. and Elect. Eng. (Amee 2017), 87, pp. 245-253.

Varol, H.A., Sup, F., Goldfarb, M., 2010, Multiclass real-time intent recognition of a powered lower limb prosthesis, IEEE Transactions on Biomedical Engineering, 57(3), pp. 542–551.

Poliakov, A., Pakhaliuk, V., Lozinskiy, N., Kolesova, M., Bugayov, P., Shtanko, P., 2016, Biosimilar artificial knee for transfemoral prostheses and exoskeletons, Facta Universitatis-Series Mechanical Engineering, 14(3), pp. 321-328.

Tucker, M.R., Olivier, J., Pagel, A., Bleuler, H., Bouri, M., Lambercy, O., Millan, J.-R., Riener, R., Vallery, H., Gassert, R., 2015, Control strategies for active lower extremity prosthetics and orthotics: a review, Journal of NeuroEngineering and Rehabilitation, 12(1), pp. 1-29.

Huang, H., Zhang, F., Hargrove, L.J., Dou, Z., Rogers, D.R., Englehart, K.B., 2011, Continuous locomotion-mode identification for prosthetic legs based on neuromuscular mechanical fusion, IEEE Transactions on Biomedical Engineering, 58(10), pp. 2867-2875.

Zhang, F., Liu, M., Huang, H., 2012, Preliminary study of the effect of user intent recognition errors on volitional control of powered lower limb prostheses, Conf. Proc. IEEE Eng. Med. Biol. Soc., pp. 2768-2771.

Zhang, F., Liu, M., Huang, H., 2014, Effects of locomotion mode recognition errors on volitional control of powered above-knee prostheses, IEEE Transactions on Neural Systems and Rehabiliation Engineering, 23(1), pp. 64-72.

Hu, M.K., 1962, Visual pattern recognition by moment invariants, IRE Transactions on Information Theory, 8(2), pp. 179-187.

Bernstein, N.A., 1991, On dexterity and its development, Physical Education and Sport, Moscow, 287 p.

Flusser, J., Suk, T., Zitova, B., 2009, Moments and moment invariants in pattern recognition, John Wiley and Sons Ltd Pub., Chichester, 294 p.

Abramov, N.S., Khachumov, V.M., 2014, Object recognition based on invariant moments, Bulletin of the Peoples' Friendship University of Russia Series Mathematics, Computer science, Physics, 2, pp. 142-149.

Arafah, M., Moghli, Q.A., 2017, Efficient image recognition technique using invariant moments and principle component analysis, Journal of Data Analysis and Information Processing, 5, pp. 1-10.

Al-Azzo, F., Taqi, A.M., Milanova, M., 2017, 3D Human action recognition using Hu moment invariants and euclidean distance classifier, International Journal of Advanced Computer Science and Applications, 8(4), pp. 12-21.

Hochreiter, S., Schmidhuber, J., 1997, Long short-term memory, Neural Computation, 9(8), pp. 1735-1780.




DOI: https://doi.org/10.22190/FUME190210004P

Refbacks

  • There are currently no refbacks.


ISSN: 0354-2025 (Print)

ISSN: 2335-0164 (Online)

COBISS.SR-ID 98732551

ZDB-ID: 2766459-4