Multi-degree Prosthetic Hand Control Using a New BP Neural Network
A human-like multi-fingered prosthetic hand, HIT hand, has been developed in Harbin Institute of Technology. This paper presents a new pattern discrimination method for HIT hand control. The method uses a bagged-BP neural network based on combing the BP neural networks using bagging algorithm. Bagging has been used to overcome the problem of limited number of training data in uni-model systems, by combining neural networks as weak learners. We compared the results of the bagging based BP network, using four features, with the results obtained separately from these uni-feature systems. The results show that the bagged-BP network improves both the accuracy and stability of the BP classifier.
KeywordsFinger Movement Robot Hand Hybrid Feature Discrimination Rate Mean Absolute Value
Unable to display preview. Download preview PDF.
- 1.Dietterich, T.G.: Machine-learning research. Four current directions. AI Magazine 18, 97–136 (1997)Google Scholar
- 2.Shi, S.C., Gao, X.H., Jiang, L., Liu, H.: Development of the Underactuated Self-adaptive Robotic Hand. Robot 26, 496–501 (2004)Google Scholar
- 8.Englehart, K., Hudgins, B., Parker, P.A., Stevenson, M.: Classification of the myoelectric signal using time-frequency based representations, vol. 21, pp. 431–438. Elsevier, Amsterdam (1999)Google Scholar