| Project/Area Number |
15500078
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Kochi University of Technology |
|---|
Principal Investigator |
TAKEDA Fumiaki Kochi University of Technology, Engineering, Professor, 工学部, 教授 (40320121)
|
|---|
| Project Period (FY) |
2003 – 2004
|
| Project Status |
Completed (Fiscal Year 2004)
|
| Budget Amount *help |
¥3,700,000 (Direct Cost: ¥3,700,000)
Fiscal Year 2004: ¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 2003: ¥2,200,000 (Direct Cost: ¥2,200,000)
|
|---|
| Keywords | EMG / DSP / Online tuning system / Continuous leaning / Neural Network / Man-machine interface / Pattern recognition / Mobile terminal / 汎化能力 / オンライン学習 / 自己学習 |
|---|
| Research Abstract |
In this research, we propose an online tuning system for Electromyogram (EMG). EMG is minute electricity and it is easy to be influenced by noise. In some research fields, such as biometrics, the target of the system was to recognize patterns whose data varied widely because of the difference of individuals and surroundings, but its recognition ability was not enough. We designed the DSP unit for online tuning and verified them. The proposed system, which is consisted of DSP unit and the NN continuous learning and recognition parts, is used to recognize the patterns. Results of examination show recognition ability improved when the learning data were increased. We show possibility of online tuning whit DSP unit for EMG. Finally, we apply to machine, which is control three fingers hand.As a research achievement, six times presentation were given at each, international conferences and domestic conferences.
|
