Presentation | 2001/7/6 Simplification of EMG Feature Extraction System Using Backpropagation Learning Algorithm with Forgetting Hisashi SAKAKIHARA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper reports a forearm motion discrimination system for control of myoelectric hand prostheses. The neural network used in the system can learn a mapping from the EMG spectral features. Simplification of EMG feature extraction system is important to design small-sized prosthesis control system. The EMG feature extraction circuit has 8 channel band-pass filters. The discriminating rates of the network trained by the backpropagation learning algorithm with forgetting are useful to estimate the feature extraction ability of band-pass filters. After drastic simplification of feature extraction circuits, the discriminating rate about 92% was carried out. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | EMG / hand prosthesis / feature extraction system / learning algorithm with forgetting |
Paper # | MBE2001-45 |
Date of Issue |
Conference Information | |
Committee | MBE |
---|---|
Conference Date | 2001/7/6(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | ME and Bio Cybernetics (MBE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Simplification of EMG Feature Extraction System Using Backpropagation Learning Algorithm with Forgetting |
Sub Title (in English) | |
Keyword(1) | EMG |
Keyword(2) | hand prosthesis |
Keyword(3) | feature extraction system |
Keyword(4) | learning algorithm with forgetting |
1st Author's Name | Hisashi SAKAKIHARA |
1st Author's Affiliation | Niihama National College of Technology() |
Date | 2001/7/6 |
Paper # | MBE2001-45 |
Volume (vol) | vol.101 |
Number (no) | 181 |
Page | pp.pp.- |
#Pages | 7 |
Date of Issue |