WEKO3
アイテム
Toward Pioneering Sensors and Features Using Large Language Models in Human Activity Recognition
http://hdl.handle.net/10228/0002001121
http://hdl.handle.net/10228/00020011210ae99245-d5a7-4c7a-a79c-374b90aad48d
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
|
|
|
| アイテムタイプ | 共通アイテムタイプ(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2025-01-16 | |||||||||||
| タイトル | ||||||||||||
| タイトル | Toward Pioneering Sensors and Features Using Large Language Models in Human Activity Recognition | |||||||||||
| 言語 | en | |||||||||||
| 著者 |
Kaneko, Haru
× Kaneko, Haru
× 井上, 創造
WEKO
27425
|
|||||||||||
| 著作権関連情報 | ||||||||||||
| 権利情報 | Copyright (c) ACM 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ACM Conferences, https://doi.org/10.1145/3594739.3610741. | |||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Abstract | |||||||||||
| 内容記述 | In this paper, we propose a feature pioneering method using Large Language Models (LLMs). In the proposed method, we use ChatGPT 1 to find new sensor locations and new features. Then we evaluate the machine learning model which uses the found features using an open dataset. In current machine learning, humans make features, for this engineers visit real sites and have discussions with experts and veteran workers. However, this method has the problem that the quality of the features depends on the engineer. In order to solve this problem, we propose a way to make new features using LLMs. As a result, we obtain almost the same level of accuracy as the proposed model which used fewer sensors and the model uses all sensors in the dataset. This indicates that the proposed method is able to extract important features efficiently. | |||||||||||
| 言語 | en | |||||||||||
| 備考 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | UbiComp/ISWC '23: The 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing Cancun, October 8 - 12, 2023, Quintana Roo, Mexico | |||||||||||
| 書誌情報 |
en : UbiComp/ISWC '23 Adjunct: Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing p. 475-479, 発行日 2023-10-08 |
|||||||||||
| 出版社 | ||||||||||||
| 出版者 | ACM | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| 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 | |||||||||||
| 出版タイプ | ||||||||||||
| 出版タイプ | AM | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||
| DOI | ||||||||||||
| 識別子タイプ | DOI | |||||||||||
| 関連識別子 | https://doi.org/10.1145/3594739.3610741 | |||||||||||
| 会議記述 | ||||||||||||
| 会議名 | ACM International Joint Conference on Pervasive and Ubiquitous Computing Cancun | |||||||||||
| 開始年 | 2023 | |||||||||||
| 開始月 | 10 | |||||||||||
| 開始日 | 8 | |||||||||||
| 終了年 | 2023 | |||||||||||
| 終了月 | 10 | |||||||||||
| 終了日 | 12 | |||||||||||
| 開催国 | MEX | |||||||||||
| 査読の有無 | ||||||||||||
| 値 | yes | |||||||||||
| 研究者情報 | ||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/140_ja.html | |||||||||||
| 論文ID(連携) | ||||||||||||
| 値 | 10403091 | |||||||||||
| 連携ID | ||||||||||||
| 値 | 12753 | |||||||||||