| Presentation | 2014-10-19 EMG motion classification based on Wavelet transformation Takayuki MUKAEDA, Nan BU, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Studies of motion classification using EMG signal are has been performed in many cases. Recently, study utilizing frequency features of EMG signals are performed. We extracted frequency features from EMG signals using short-time Fourier transform, and occurred forearm motion classification. However, classification becomes unstable by switching part of the operation for improving temporal resolution is difficult. Therefore, we focused on Wavelet transform (WT) which can be solve the problem of temporal resolution. In this study, the frequency features are extracted by WT, and these feature patterns are then inputted into a multi-layer perceptron (MLP) neural network in order to classify forearm motions. As a result, classification rates of the proposed method were used for compare with EMG motion classification method of our previous study using STFT. From this result, the validity of the proposed method was confirmed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | EMG signal / frequency features / Wavelet transform / pattern classification / neural network / forearm motion |
| Paper # | WIT2014-45 |
| Date of Issue |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2014/10/12(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 | Well-being Information Technology(WIT) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | EMG motion classification based on Wavelet transformation |
| Sub Title (in English) | |
| Keyword(1) | EMG signal |
| Keyword(2) | frequency features |
| Keyword(3) | Wavelet transform |
| Keyword(4) | pattern classification |
| Keyword(5) | neural network |
| Keyword(6) | forearm motion |
| 1st Author's Name | Takayuki MUKAEDA |
| 1st Author's Affiliation | NIT, Kumamoto College() |
| 2nd Author's Name | Nan BU |
| 2nd Author's Affiliation | NIT, Kumamoto College |
| Date | 2014-10-19 |
| Paper # | WIT2014-45 |
| Volume (vol) | vol.114 |
| Number (no) | 261 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |