Abstract
The wearable knee angle detection system based on RBF neural network which is used to calculate knee joint angle can carry out tracking and control of lower limb exoskeleton robot through classification, tracking and prediction analysis of gait data so that lower limb exoskeleton robot’s dynamic stability can be improved. The learning samples were obtained by gait walking experiment in advance. Then the optimal model parameters of neural network were obtained by training the learning samples. Wearing the exoskeleton, experimenter’s knee joint angle can be accurately measured by wearing two gyroscopes and the trained neural network model. The trained neural network model can be used to compensate the output signals of two gyroscopes. The analytical relationship between the input signals and the output error signals of two gyroscopes is not necessary to be obtained, which means such method is simple and effective to implement. The knee joint angle can be accurately measured just by installing two gyroscopes with straps, when the neural network model is already established. The non-contact measurement of knee joint angle which is simple and low-cost has been realized and the experimental verification has been completed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhu, Y., Zhang, G., Zhang, C., Liu, G., Zhao, J.: Biomechanical modeling and load-carrying simulation of lower limb exoskeleton. Bio-Med. Mater. Eng. 26, S729–S738 (2015)
Cai, V., Bidaud, P., Hayward, V., Gosselin, F., Desailly, E.: Self-adjusting, isostatic exoskeleton for the human knee joint. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011(4), 612–618 (2011)
Maas, H., et al.: Analysis of the motion behaviour of Jakobshavn IsbrÆ glacier in Greenland by monocular image sequence analysis. Plant J. 7(3), 483–490 (2012)
Wang, L.L., Yang, Z., Liu, J.: S-EMG signal detection based on combining moving average of integrated EMG window with double threshold. J. Northeast Normal Univ. (Nat. Sci. Edn.) (3), 65–71 (2018)
Heisenberg, D., et al.: Device for measuring the angle and/or the angular velocity of a rotatable body and/or the torque acting upon said body (2005)
Gjoreski, H., Lustrek, M., Gams, M.: Accelerometer placement for posture recognition and fall detection. In: 2011 7th International Conference on Intelligent Environments (2011)
Lee, C.M., Ko, C.N.: Time series prediction using RBF neural networks with a nonlinear time-varying evolution PSO algorithm. Neurocomputing 73(1–3), 449–460 (2009)
Han, H.G., Chen, Q.L., Qiao, J.F.: An efficient self-organizing RBF neural network for water quality prediction. Neural Netw. Official J. Int. Neural Netw. Soc. 24(7), 717–725 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Guo, Y., Yang, F., Wang, H., Zhao, Q., Liu, S. (2022). Research on Wearable Knee Angle Detection System Based on RBF Neural Network. In: Jia, Y., Zhang, W., Fu, Y., Yu, Z., Zheng, S. (eds) Proceedings of 2021 Chinese Intelligent Systems Conference. Lecture Notes in Electrical Engineering, vol 804. Springer, Singapore. https://doi.org/10.1007/978-981-16-6324-6_49
Download citation
DOI: https://doi.org/10.1007/978-981-16-6324-6_49
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6323-9
Online ISBN: 978-981-16-6324-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)