WEKO3
アイテム
{"_buckets": {"deposit": "4b22f523-02fb-44f3-82fd-1db048918801"}, "_deposit": {"created_by": 18, "id": "10368", "owners": [18], "pid": {"revision_id": 0, "type": "depid", "value": "10368"}, "status": "published"}, "_oai": {"id": "oai:muroran-it.repo.nii.ac.jp:00010368", "sets": ["46", "316", "352"]}, "author_link": ["21131", "39157", "54988"], "item_79_biblio_info_10": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2019", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "76", "bibliographicPageStart": "67", "bibliographicVolumeNumber": "4", "bibliographic_titles": [{"bibliographic_title": "IEEE Transactions on Sustainable Computing", "bibliographic_titleLang": "en"}]}]}, "item_79_description_23": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_79_description_7": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Three-dimensional (3D) scene understanding is of great significance to many robotic applications. With the huge development of the deep learning methods, especially the convolutional neural network (CNN), 3D robotic vision has achieved a satisfactory performance. However, in most scenarios, sustainability becomes a severe problem, and few existing approaches pay enough attention to energy consumption. In this paper, we propose an energy-aware system for sustainable robotic 3D vision. Our contributions mainly include: 1) an effective CNN model for the 3D scene understanding; and 2) an offloading strategy to make the deep model more sustainable. First, we design a deep CNN model to analyze the 3D point cloud data. The proposed model contains 92 layers for a state-of-the-art recognition accuracy, which, however, bring a big burden to the computing hardware. Then, we formulate this deep learning computation problem as a non-cooperative game, and adopt a heuristic algorithm to balance the local computing and cloud offloading, in order to obtain an optimal solution, in which both the efficiency and energy-saving are taken into account. Simulations demonstrate that our approach is robust and efficient, and outperforms the state-of-the-art in several related tasks.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_79_link_17": {"attribute_name": "出版者版へのリンク", "attribute_value_mlt": [{"subitem_link_text": "10.1109/TSUSC.2018.2844348", "subitem_link_url": "https://doi.org/10.1109/TSUSC.2018.2844348"}]}, "item_79_link_5": {"attribute_name": "室蘭工業大学研究者データベースへのリンク", "attribute_value_mlt": [{"subitem_link_text": "太田 香(OTA Kaoru)", "subitem_link_url": "http://rdsoran.muroran-it.ac.jp/html/100000140_ja.html"}, {"subitem_link_text": "董 冕雄(DONG Mianxiong)", "subitem_link_url": "http://rdsoran.muroran-it.ac.jp/html/100000145_ja.html"}]}, "item_79_publisher_11": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE", "subitem_publisher_language": "en"}]}, "item_79_relation_18": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1109/TSUSC.2018.2844348", "subitem_relation_type_select": "DOI"}}]}, "item_79_rights_19": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.", "subitem_rights_language": "en"}]}, "item_79_subject_9": {"attribute_name": "日本十進分類法", "attribute_value_mlt": [{"subitem_subject": "007", "subitem_subject_scheme": "NDC"}]}, "item_79_text_4": {"attribute_name": "著者ID(非表示)", "attribute_value_mlt": [{"subitem_text_value": "1000050713971@@@1000020728274"}]}, "item_79_version_type_21": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorAffiliations": [{"affiliationNameIdentifiers": [], "affiliationNames": [{"affiliationName": "", "affiliationNameLang": "ja"}]}], "creatorNames": [{"creatorName": "LI, Liangzhi", "creatorNameLang": "en"}, {"creatorName": "李, 良知", "creatorNameLang": "ja"}], "familyNames": [{"familyName": "LI", "familyNameLang": "en"}, {"familyName": "李", "familyNameLang": "ja"}], "givenNames": [{"givenName": "Liangzhi", "givenNameLang": "en"}, {"givenName": "良知", "givenNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "54988", "nameIdentifierScheme": "WEKO"}]}, {"creatorAffiliations": [{"affiliationNameIdentifiers": [{"affiliationNameIdentifier": "10103", "affiliationNameIdentifierScheme": "kakenhi"}], "affiliationNames": [{"affiliationName": "室蘭工業大学", "affiliationNameLang": "ja"}, {"affiliationName": "Muroran Institute of Technology", "affiliationNameLang": "en"}]}], "creatorNames": [{"creatorName": "OTA, Kaoru", "creatorNameLang": "en"}, {"creatorName": "太田, 香", "creatorNameLang": "ja"}, {"creatorName": "オオタ, カオル", "creatorNameLang": "ja-Kana"}], "familyNames": [{"familyName": "OTA", "familyNameLang": "en"}, {"familyName": "太田", "familyNameLang": "ja"}, {"familyName": "オオタ", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": " Kaoru", "givenNameLang": "en"}, {"givenName": "香", "givenNameLang": "ja"}, {"givenName": "カオル", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "21131", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000050713971", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000050713971"}]}, {"creatorAffiliations": [{"affiliationNameIdentifiers": [{"affiliationNameIdentifier": "10103", "affiliationNameIdentifierScheme": "kakenhi"}], "affiliationNames": [{"affiliationName": "室蘭工業大学", "affiliationNameLang": "ja"}, {"affiliationName": "Muroran Institute of Technology", "affiliationNameLang": "en"}]}], "creatorNames": [{"creatorName": "DONG, Mianxiong", "creatorNameLang": "en"}, {"creatorName": "トウ, メンユウ", "creatorNameLang": "ja-Kana"}, {"creatorName": "董, 冕雄", "creatorNameLang": "ja"}], "familyNames": [{"familyName": "DONG", "familyNameLang": "en"}, {"familyName": "トウ", "familyNameLang": "ja-Kana"}, {"familyName": "董", "familyNameLang": "ja"}], "givenNames": [{"givenName": " Mianxiong", "givenNameLang": "en"}, {"givenName": "メンユウ", "givenNameLang": "ja-Kana"}, {"givenName": "冕雄", "givenNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "39157", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000020728274", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000020728274"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2020-11-16"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "TSUSC_4_1_67_76.pdf", "filesize": [{"value": "1.4 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 1400000.0, "url": {"label": "TSUSC_4_1_67_76", "objectType": "fulltext", "url": "https://muroran-it.repo.nii.ac.jp/record/10368/files/TSUSC_4_1_67_76.pdf"}, "version_id": "e79bc0b0-1a81-4ac0-955f-41fe7f5e4c36"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Sustainable computing", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "convolutional neural network (CNN)", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "3D scene understanding", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "robotic", "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": "Sustainable CNN for Robotic: An Offloading Game in the 3D Vision Computation,", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Sustainable CNN for Robotic: An Offloading Game in the 3D Vision Computation,", "subitem_title_language": "en"}]}, "item_type_id": "79", "owner": "18", "path": ["46", "316", "352"], "permalink_uri": "http://hdl.handle.net/10258/00010309", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2020-11-16"}, "publish_date": "2020-11-16", "publish_status": "0", "recid": "10368", "relation": {}, "relation_version_is_last": true, "title": ["Sustainable CNN for Robotic: An Offloading Game in the 3D Vision Computation,"], "weko_shared_id": -1}
Sustainable CNN for Robotic: An Offloading Game in the 3D Vision Computation,
http://hdl.handle.net/10258/00010309
http://hdl.handle.net/10258/0001030953de85b5-77e9-4197-8f3c-9a8f13653e6e
名前 / ファイル | ライセンス | アクション |
---|---|---|
TSUSC_4_1_67_76 (1.4 MB)
|
|
Item type | 学術雑誌論文 / Journal Article.(1) | |||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2020-11-16 | |||||||||||||||||
タイトル | ||||||||||||||||||
言語 | en | |||||||||||||||||
タイトル | Sustainable CNN for Robotic: An Offloading Game in the 3D Vision Computation, | |||||||||||||||||
言語 | ||||||||||||||||||
言語 | eng | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Sustainable computing | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | convolutional neural network (CNN) | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | 3D scene understanding | |||||||||||||||||
キーワード | ||||||||||||||||||
言語 | en | |||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | robotic | |||||||||||||||||
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 | |||||||||||||||||
アクセス権 | ||||||||||||||||||
アクセス権 | open access | |||||||||||||||||
アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||||||||||||||
著者 |
李, 良知
× 李, 良知× 太田, 香
WEKO
21131
× 董, 冕雄
WEKO
39157
|
|||||||||||||||||
室蘭工業大学研究者データベースへのリンク | ||||||||||||||||||
太田 香(OTA Kaoru) | ||||||||||||||||||
http://rdsoran.muroran-it.ac.jp/html/100000140_ja.html | ||||||||||||||||||
室蘭工業大学研究者データベースへのリンク | ||||||||||||||||||
董 冕雄(DONG Mianxiong) | ||||||||||||||||||
http://rdsoran.muroran-it.ac.jp/html/100000145_ja.html | ||||||||||||||||||
抄録 | ||||||||||||||||||
内容記述タイプ | Abstract | |||||||||||||||||
内容記述 | Three-dimensional (3D) scene understanding is of great significance to many robotic applications. With the huge development of the deep learning methods, especially the convolutional neural network (CNN), 3D robotic vision has achieved a satisfactory performance. However, in most scenarios, sustainability becomes a severe problem, and few existing approaches pay enough attention to energy consumption. In this paper, we propose an energy-aware system for sustainable robotic 3D vision. Our contributions mainly include: 1) an effective CNN model for the 3D scene understanding; and 2) an offloading strategy to make the deep model more sustainable. First, we design a deep CNN model to analyze the 3D point cloud data. The proposed model contains 92 layers for a state-of-the-art recognition accuracy, which, however, bring a big burden to the computing hardware. Then, we formulate this deep learning computation problem as a non-cooperative game, and adopt a heuristic algorithm to balance the local computing and cloud offloading, in order to obtain an optimal solution, in which both the efficiency and energy-saving are taken into account. Simulations demonstrate that our approach is robust and efficient, and outperforms the state-of-the-art in several related tasks. | |||||||||||||||||
言語 | en | |||||||||||||||||
書誌情報 |
en : IEEE Transactions on Sustainable Computing 巻 4, 号 1, p. 67-76, 発行日 2019 |
|||||||||||||||||
出版者 | ||||||||||||||||||
言語 | en | |||||||||||||||||
出版者 | IEEE | |||||||||||||||||
出版者版へのリンク | ||||||||||||||||||
10.1109/TSUSC.2018.2844348 | ||||||||||||||||||
https://doi.org/10.1109/TSUSC.2018.2844348 | ||||||||||||||||||
DOI | ||||||||||||||||||
関連タイプ | isVersionOf | |||||||||||||||||
識別子タイプ | DOI | |||||||||||||||||
関連識別子 | 10.1109/TSUSC.2018.2844348 | |||||||||||||||||
日本十進分類法 | ||||||||||||||||||
主題Scheme | NDC | |||||||||||||||||
主題 | 007 | |||||||||||||||||
権利 | ||||||||||||||||||
言語 | en | |||||||||||||||||
権利情報 | © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |||||||||||||||||
著者版フラグ | ||||||||||||||||||
出版タイプ | AM | |||||||||||||||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||||||||
フォーマット | ||||||||||||||||||
内容記述タイプ | Other | |||||||||||||||||
内容記述 | application/pdf |