The Application of Machine-Learning on Lower Limb Motion Analysis in Human Exoskeleton System
This article briefly describes the research status of the human exoskeleton system, and gives a summary of the human lower limb gait analysis. On this basis, the machine learning classification algorithms and clustering algorithms are used for offline data mining on a data collection of prototype, in order to establish a classifier for movement prediction and judgment of lower limb. At the same time, the article analyses the procedure of standing from sitting utilizing clustering algorithm for rehabilitation exoskeleton. Experiments mainly refer to the C4.5 decision tree algorithm, Bayesian classification algorithm and clustering algorithm EM. Weka software simulation results show that the lower limb motion can be judged by the classifier making use of gait analysis data accurately, and the lower limb motion for different users at different time and different environments could be clustered by cluster. Effectively using of these results can offer great convenience to the flexibility control for exoskeleton so that exoskeleton system could achieve human-computer coupling.
KeywordsExoskeleton machine learning gait analysis classifier cluster
Unable to display preview. Download preview PDF.
- 1.Wang, L., Gu, T., Tao, X., Lu, J.: A hierarchical approach to real-time activity recognition in body sensor networks. Pervasive and Mobile Computing (8), 115–130 (2012)Google Scholar
- 2.Tapia, E.M., Intille, S.: Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. In: Proceedings of the 11th International Conference on Wearable Computers, Boston, MA (2007)Google Scholar
- 3.Krishnan, N.C., Colbry, D., Juillard, C., Panchanathan, S.: Real time human activity recognition using tri-axial accelerometers. In: Proceedings of Sensors Signals and Information Processing Workshop, Sedona, AZ (2008)Google Scholar
- 4.Beyl, P.: Design and control of a knee exoskeleton powered by pleated pneumatic artificial muscles for robot-assisted gait rehabilitation. Academic and Scientific Publishers, Brussels (2010)Google Scholar
- 6.He, J., Li, H., Tan, J.: Real-time daily activity classification with wireless sensor networks using hidden Markov model. In: Proceedings of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2007)Google Scholar
- 7.Kawamoto, H., Sankai, Y.: Comfortable power assist control method for walking aid by HAL-3. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 4 (2002)Google Scholar
- 8.Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann Publishers, Waikato Hamilton (2000)Google Scholar
- 9.Jun, X., Yueting, Z., WuFei: Computer Vision and Machine Learning in 3D Human Animation: a Survey. Journal of Computer-aided Design & Computer Graphics 20(3), 281–290 (2008)Google Scholar
- 10.Gomes, M.A., Silveira, G.L.M., Siqueira, A.A.G.: Gait-Pattern Adaptation Algorithms based on Neural Network for Lower Limbs Active Orthoses. IEEE Intelligent Robots and Systems, 4475–4480 (2009)Google Scholar
- 11.Liu, G., Pan, Z., Cheng, X., Li, L., Zhang, M.: A Survey on Machine Learning in the Synthesis of Human Motions. Journal of Computer-aided Design & Conputer Graphics 22(9), 1620–1627 (2010)Google Scholar
- 13.Kong, K., Moon, H., Hwang, B., Jeon, D., Tomizuka, M.: Robotic rehabilitation treatments: Realization of aquatic therapy effects in exoskeleton systems. Robotics and Automation, 1923–1928 (2009)Google Scholar