WEKO3
アイテム
{"_buckets": {"deposit": "269711c8-7892-45df-8cf5-b9c0dc459e6c"}, "_deposit": {"created_by": 3, "id": "6021", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "6021"}, "status": "published"}, "_oai": {"id": "oai:kyutech.repo.nii.ac.jp:00006021", "sets": ["24"]}, "author_link": ["24664", "24661", "24663", "24662"], "item_21_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2019-05-07", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "5", "bibliographicPageStart": "95", "bibliographicVolumeNumber": "12", "bibliographic_titles": [{"bibliographic_title": "Algorithms"}]}]}, "item_21_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Transfer learning aims for high accuracy by applying knowledge of source domains for which data collection is easy in order to target domains where data collection is difficult, and has attracted attention in recent years because of its significant potential to enable the application of machine learning to a wide range of real-world problems. However, since the technique is user-dependent, with data prepared as a source domain which in turn becomes a knowledge source for transfer learning, it often involves the adoption of inappropriate data. In such cases, the accuracy may be reduced due to “negative transfer.” Thus, in this paper, we propose a novel transfer learning method that utilizes the flipping output technique to provide multiple labels in the source domain. The accuracy of the proposed method is statistically demonstrated to be significantly better than that of the conventional transfer learning method, and its effect size is as high as 0.9, showing high performance.", "subitem_description_type": "Abstract"}]}, "item_21_description_60": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_description": "Journal Article", "subitem_description_type": "Other"}]}, "item_21_publisher_7": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "MDPI"}]}, "item_21_relation_12": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.3390/a12050095", "subitem_relation_type_select": "DOI"}}]}, "item_21_relation_14": {"attribute_name": "情報源", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.3390/a12050095", "subitem_relation_type_select": "DOI"}}]}, "item_21_rights_13": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "The authors"}]}, "item_21_select_59": {"attribute_name": "査読の有無", "attribute_value_mlt": [{"subitem_select_item": "yes"}]}, "item_21_source_id_8": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1999-4893", "subitem_source_identifier_type": "ISSN"}]}, "item_21_subject_16": {"attribute_name": "日本十進分類法", "attribute_value_mlt": [{"subitem_subject": "548", "subitem_subject_scheme": "NDC"}]}, "item_21_text_36": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_text_value": "Advanced Manufacturing Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Saga 841-0052, Japan"}, {"subitem_text_value": "Advanced Manufacturing Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Saga 841-0052, Japan"}, {"subitem_text_value": "Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology (Kyutech), Fukuoka 808-0196, Japan"}]}, "item_21_text_63": {"attribute_name": "連携ID", "attribute_value_mlt": [{"subitem_text_value": "7778"}]}, "item_21_version_type_58": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Koishi, Yasutake"}], "nameIdentifiers": [{"nameIdentifier": "24661", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ishida, Shuichi"}], "nameIdentifiers": [{"nameIdentifier": "24662", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tabaru, Tatsuo"}], "nameIdentifiers": [{"nameIdentifier": "24663", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Hiroyuki, Miyamoto"}], "nameIdentifiers": [{"nameIdentifier": "24664", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-06-19"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "a12050095.pdf", "filesize": [{"value": "501.5 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 501500.0, "url": {"label": "a12050095.pdf", "url": "https://kyutech.repo.nii.ac.jp/record/6021/files/a12050095.pdf"}, "version_id": "4ab6206e-702a-4ec1-80f8-4ff785e01b19"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "transfer learning", "subitem_subject_scheme": "Other"}, {"subitem_subject": "ensemble learning", "subitem_subject_scheme": "Other"}, {"subitem_subject": "data expansion", "subitem_subject_scheme": "Other"}, {"subitem_subject": "flipping output", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output"}]}, "item_type_id": "21", "owner": "3", "path": ["24"], "permalink_uri": "http://hdl.handle.net/10228/00007231", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-06-19"}, "publish_date": "2019-06-19", "publish_status": "0", "recid": "6021", "relation": {}, "relation_version_is_last": true, "title": ["A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output"], "weko_shared_id": 3}
A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output
http://hdl.handle.net/10228/00007231
http://hdl.handle.net/10228/00007231d138e48e-8653-4d6c-b313-c4699111018a
名前 / ファイル | ライセンス | アクション |
---|---|---|
a12050095.pdf (501.5 kB)
|
|
Item type | 学術雑誌論文 = Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-06-19 | |||||
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 | |||||
タイトル | ||||||
タイトル | A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output | |||||
言語 | ||||||
言語 | eng | |||||
著者 |
Koishi, Yasutake
× Koishi, Yasutake× Ishida, Shuichi× Tabaru, Tatsuo× Hiroyuki, Miyamoto |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Transfer learning aims for high accuracy by applying knowledge of source domains for which data collection is easy in order to target domains where data collection is difficult, and has attracted attention in recent years because of its significant potential to enable the application of machine learning to a wide range of real-world problems. However, since the technique is user-dependent, with data prepared as a source domain which in turn becomes a knowledge source for transfer learning, it often involves the adoption of inappropriate data. In such cases, the accuracy may be reduced due to “negative transfer.” Thus, in this paper, we propose a novel transfer learning method that utilizes the flipping output technique to provide multiple labels in the source domain. The accuracy of the proposed method is statistically demonstrated to be significantly better than that of the conventional transfer learning method, and its effect size is as high as 0.9, showing high performance. | |||||
書誌情報 |
Algorithms 巻 12, 号 5, p. 95, 発行日 2019-05-07 |
|||||
出版社 | ||||||
出版者 | MDPI | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.3390/a12050095 | |||||
日本十進分類法 | ||||||
主題Scheme | NDC | |||||
主題 | 548 | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1999-4893 | |||||
著作権関連情報 | ||||||
権利情報 | The authors | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | transfer learning | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | ensemble learning | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | data expansion | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | flipping output | |||||
出版タイプ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
査読の有無 | ||||||
値 | yes | |||||
連携ID | ||||||
7778 | ||||||
資料タイプ | ||||||
内容記述タイプ | Other | |||||
内容記述 | Journal Article | |||||
著者所属 | ||||||
Advanced Manufacturing Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Saga 841-0052, Japan | ||||||
著者所属 | ||||||
Advanced Manufacturing Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Saga 841-0052, Japan | ||||||
著者所属 | ||||||
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology (Kyutech), Fukuoka 808-0196, Japan | ||||||
情報源 | ||||||
識別子タイプ | DOI | |||||
関連識別子 | https://doi.org/10.3390/a12050095 |