WEKO3
インデックスリンク
アイテム
においセンサを用いた居住者の活動認識: 相関ルールによる認識率の向上
http://hdl.handle.net/2297/35249
http://hdl.handle.net/2297/3524966272a33-a882-420f-a344-ffef6b2ed949
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
TE-PR-KIMURA-H-343.pdf (1.6 MB)
|
|
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2017-10-03 | |||||
| タイトル | ||||||
| タイトル | においセンサを用いた居住者の活動認識: 相関ルールによる認識率の向上 | |||||
| タイトル | ||||||
| タイトル | Recognition of Residential Behavious Using Odor Sensor Characteristics Improvement of Recognition Rate by Applying of an Association Rule | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | jpn | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
| 資源タイプ | journal article | |||||
| 著者 |
上田, 芳弘
× 上田, 芳弘× 古川, 真士× 木村, 春彦× 大薮, 多可志 |
|||||
| 書誌情報 |
電気学会論文誌. E, センサ・マイクロマシン部門誌 = The transactions of the Institute of Electrical Engineers of Japan. A publication of Sensors and Micromachines Society 巻 121, 号 6, p. 343-350, 発行日 2001-01-01 |
|||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 1341-8939 | |||||
| NCID | ||||||
| 収録物識別子タイプ | NCID | |||||
| 収録物識別子 | AN1052634X | |||||
| DOI | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | 10.1541/ieejsmas.121.343 | |||||
| 出版者 | ||||||
| 出版者 | 電気学会 = Institute of Electrical Engineers of Japan | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Recognition rate of human behaviors in a residence is improved using an association rule, which is widely used in the field of the data mining. In the present study, plural odor-sensor characteristics are adopted to introduce the features of the behaviors. The rules in the database with positive instances, which are the real data, can be derived in this method. On the other hand, the negative instances are also focused to introduce various kinds of behavior-features. These instances express error data in the recognition process. First, we propose a method by which the positive and negative rules can be derived from the both kinds of instances. And we supose that the recognition results can be obtained by the rules. Secondarily, we perform evaluation experiments and compare the recognition rates of the LBG clustering with those of the proposed method. As for the results, we achieved the following results. (1) The recognition rate can be improved by the proposed method except the case of lack of the negative instances and the case of category in which the same activities are included as the positive and negative instances. (2) By analyzing the activity history, which the resident recorded his behaviors, we confirmed that the positive and the negative rules could correct the recognition results. The proposed method is useful to recognize the human behaviors in the residence. | |||||
| 権利 | ||||||
| 権利情報 | Copyright © 電気学会 The Institute of Electrical Engineers of Japan | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
| 関連URI | ||||||
| 識別子タイプ | URI | |||||
| 関連識別子 | http://www.iee.or.jp/ | |||||
| 関連URI | ||||||
| 識別子タイプ | URI | |||||
| 関連識別子 | https://www.jstage.jst.go.jp/browse/ieejsmas/-char/ja/ | |||||
