WEKO3
アイテム
{"_buckets": {"deposit": "24496c85-0cd6-495e-b68a-3718474f2f76"}, "_deposit": {"created_by": 13, "id": "8848", "owners": [13], "pid": {"revision_id": 0, "type": "depid", "value": "8848"}, "status": "published"}, "_oai": {"id": "oai:uec.repo.nii.ac.jp:00008848", "sets": ["6"]}, "author_link": ["24028", "24024", "24023", "24026", "24025", "24027", "24029"], "item_10001_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2019-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "87", "bibliographicPageStart": "75", "bibliographicVolumeNumber": "47", "bibliographic_titles": [{}, {"bibliographic_title": "Biomedical Signal Processing and Control", "bibliographic_titleLang": "en"}]}]}, "item_10001_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "To enhance electrocardiogram (ECG) monitoring systems in personalized detections, deep neural networks (DNNs) are applied to overcome individual differences by periodical retraining. As introduced previously [4], DNNs relieve individual differences by fusing ECG with impulse radio ultra-wide band (IR-UWB) radar. However, such DNN-based ECG monitoring system tends to overfit into personal small datasets and is difficult to generalize to newly collected unlabeled data. This paper proposes a self-adjustable domain adaptation (SADA) strategy to prevent from overfitting and exploit unlabeled data. Firstly, this paper enlarges the database of ECG and radar data with actual records acquired from 28 testers and expanded by the data augmentation. Secondly, to utilize unlabeled data, SADA combines self organizing maps with the transfer learning in predicting labels. Thirdly, SADA integrates the one-class classification with domain adaptation algorithms to reduce overfitting. Based on our enlarged database and standard databases, a large dataset of 73200 records and a small one of 1849 records are built up to verify our proposal. Results show SADA\u0027s effectiveness in predicting labels and increments in the sensitivity of DNNs by 14.4% compared with existing domain adaptation algorithms.", "subitem_description_type": "Abstract"}]}, "item_10001_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Elsevier"}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1016/j.bspc.2018.08.002", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "関連サイト", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.1016/j.bspc.2018.08.002", "subitem_relation_type_select": "DOI"}}]}, "item_10001_rights_15": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© 2018 The Authors"}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "17468094", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"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": "Yin, Wenfeng", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24023", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Yang, Xiuzhu", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24024", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Li, Lei", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24025", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Zhang, Lin", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24026", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kitsuwan, Nattapong", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24027", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Shinkuma, Ryoichi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24028", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Oki, Eiji", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24029", "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": "2019-01-11"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "1-s2.0-S1746809418301927-main.pdf", "filesize": [{"value": "5.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "CC BY-NC-ND 4.0", "licensetype": "license_free", "mimetype": "application/pdf", "size": 5100000.0, "url": {"label": "1-s2.0-S1746809418301927-main", "url": "https://uec.repo.nii.ac.jp/record/8848/files/1-s2.0-S1746809418301927-main.pdf"}, "version_id": "414d6eaa-f8af-4db7-8706-6a9bba7fe6b7"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Transfer learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Domain adaptation", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "One-class classification", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Self organizing maps", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "ECG monitoring", "subitem_subject_language": "en", "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": "Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "13", "path": ["6"], "permalink_uri": "https://uec.repo.nii.ac.jp/records/8848", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-01-11"}, "publish_date": "2019-01-11", "publish_status": "0", "recid": "8848", "relation": {}, "relation_version_is_last": true, "title": ["Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar"], "weko_shared_id": -1}
Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar
https://uec.repo.nii.ac.jp/records/8848
https://uec.repo.nii.ac.jp/records/88487067de67-441b-441b-aab6-4ad3baad6142
名前 / ファイル | ライセンス | アクション |
---|---|---|
1-s2.0-S1746809418301927-main (5.1 MB)
|
CC BY-NC-ND 4.0
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-01-11 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Transfer learning | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Domain adaptation | |||||
キーワード | ||||||
言語 | en | |||||
主題 | One-class classification | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Self organizing maps | |||||
キーワード | ||||||
言語 | en | |||||
主題 | ECG monitoring | |||||
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 |
Yin, Wenfeng
× Yin, Wenfeng× Yang, Xiuzhu× Li, Lei× Zhang, Lin× Kitsuwan, Nattapong× Shinkuma, Ryoichi× Oki, Eiji |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | To enhance electrocardiogram (ECG) monitoring systems in personalized detections, deep neural networks (DNNs) are applied to overcome individual differences by periodical retraining. As introduced previously [4], DNNs relieve individual differences by fusing ECG with impulse radio ultra-wide band (IR-UWB) radar. However, such DNN-based ECG monitoring system tends to overfit into personal small datasets and is difficult to generalize to newly collected unlabeled data. This paper proposes a self-adjustable domain adaptation (SADA) strategy to prevent from overfitting and exploit unlabeled data. Firstly, this paper enlarges the database of ECG and radar data with actual records acquired from 28 testers and expanded by the data augmentation. Secondly, to utilize unlabeled data, SADA combines self organizing maps with the transfer learning in predicting labels. Thirdly, SADA integrates the one-class classification with domain adaptation algorithms to reduce overfitting. Based on our enlarged database and standard databases, a large dataset of 73200 records and a small one of 1849 records are built up to verify our proposal. Results show SADA's effectiveness in predicting labels and increments in the sensitivity of DNNs by 14.4% compared with existing domain adaptation algorithms. | |||||
書誌情報 |
en : Biomedical Signal Processing and Control 巻 47, p. 75-87, 発行日 2019-01 |
|||||
出版者 | ||||||
出版者 | Elsevier | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 17468094 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1016/j.bspc.2018.08.002 | |||||
権利 | ||||||
権利情報 | © 2018 The Authors | |||||
関連サイト | ||||||
識別子タイプ | DOI | |||||
関連識別子 | https://doi.org/10.1016/j.bspc.2018.08.002 | |||||
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 |