Capacitive Sensing Based Knee-Angle Continuous Estimation by BP Neural Networks
In this paper, we propose a capacitive sensing based method for knee joint angle continuous estimation. The motion capture system is used to record the position information of knee joint and output knee joint angel as a fitting target. Two capacitance rings are fixed on the thigh and shank to record the relaxation and contraction of muscles. Three healthy subjects participate in the study. Based on BP (back propagation) neural networks, the map relationships (i.e. model) between capacitance signals and knee joint angles are built. In the continuous estimation of angle, capacitance signals are fed into the model, and then we can get the estimated angles. The error (root mean square) and the cross-correlation coefficient are 4.4\(^\circ \) and 97.01% between the estimated knee joint angles (based on capacitance signals) and actual keen knee-angle. The results show that capacitive sensing method is effective and feasible to estimate the joint angles.
KeywordsCapacitive sensing Knee joint angle Continuous estimation BP neural networks
This work was supported by the National Key R&D Program of China (No. 2018YFB1307302, 2018YFF0300606), the National Natural Science Foundation of China (No. 91648207, 61533001), the Beijing Nova Program (No. Z141101001814001) and the Beijing Municipal Science and Technology Project (No. Z181100009218007).
- 5.Huo, W., Mohammed, S., Amirat, Y., Kong, K.: Fast gait mode detection and assistive torque control of an exoskeletal robotic orthosis for walking assistance. IEEE Transact. Robot. 34(4), 1035–1052 (2018)Google Scholar
- 13.Anwar, T., Aung, Y.M., Jumaily, A.A.: The estimation of knee joint angle based on generalized regression neural network (GRNN). In: Proceedings of the IEEE International Symposium on Robotics and Intelligent Sensors, pp. 208–213. Langkawi, Malaysia (2015)Google Scholar
- 18.Xu, D., Yang, Y., Mai, J., Wang, Q.: Muscle redistribution surgery based capacitive sensing for upper-limb motion recognition: Preliminary results. In: Proceedings of the IEEE International Conference on Cyborg and Bionic Systems, Beijing, China, pp. 125–129 (2017)Google Scholar
- 20.Zheng, E., Wang, Q., Qiao, H.: Identification of the relationships between noncontact capacitive sensing signals and continuous grasp forces: preliminary study. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, USA, pp. 3922–3925 (2018)Google Scholar
- 21.Min, S., Lee, B., Yoon, S.: Deep learning in bioinformatics. Brief. Bioinf. 18(5), 851–869 (2017)Google Scholar