書誌事項
- タイトル別名
-
- EMG-to-Motion Classification for Prosthetic Applications-A Self-Organizing Approach with Level of Proficiency-
- シュウジュクド オ コウリョ シタ ジコ ソシキテキ ドウサ シキベツホウ ノ コウチク
- — A Self-Organizing Approach with Level of Proficiency —
この論文をさがす
抄録
The purpose of this research is to discriminate many motions using EMG signal for prosthetic application's control. The basic idea of this study is that, the current degree of proficiency, i.e., how well the application is operated by a user is to be analyzed from bio-signal closely related to human motor process, and control rule is generated depending on the proficiency level. Thus, our proposed system consists of two parts: estimation of user's proficiency level using EMG signal, and motion classification using self-organized clustering. In the experiment, users trained to discriminate motions using our proposed system, and then they all were able to discriminate seven forearm motions with approximately 90% accuracy. In addition, one of the users was able to discriminate nine motions with 21% higher accuracy than before training. The results indicated the effectiveness of proposed system.
収録刊行物
-
- 日本ロボット学会誌
-
日本ロボット学会誌 28 (7), 783-791, 2010
一般社団法人 日本ロボット学会
- Tweet
キーワード
詳細情報
-
- CRID
- 1390282679702176512
-
- NII論文ID
- 10026578720
- 130002152522
-
- NII書誌ID
- AN00141189
-
- ISSN
- 18847145
- 02891824
-
- NDL書誌ID
- 10824271
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可