WEKO3
アイテム
{"_buckets": {"deposit": "70703bda-aa3d-4c2a-b2b8-4c6d45e0375b"}, "_deposit": {"created_by": 1, "id": "48419", "owners": [1], "pid": {"revision_id": 0, "type": "depid", "value": "48419"}, "status": "published"}, "_oai": {"id": "oai:jaxa.repo.nii.ac.jp:00048419", "sets": ["1893", "2177", "2194"]}, "author_link": ["545823", "545818", "545813", "545812", "545819", "545811", "545809", "545814", "545820", "545821", "545822", "545816", "545808", "545817", "545810", "545815"], "item_3_alternative_title_2": {"attribute_name": "その他のタイトル(英)", "attribute_value_mlt": [{"subitem_alternative_title": "Application of Machine Learning and Visualization of Evidence for Cosmic-Ray Antiparticle Identification"}]}, "item_3_biblio_info_10": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2022-02-28", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "43", "bibliographicPageStart": "37", "bibliographicVolumeNumber": "JAXA-RR-21-008", "bibliographic_titles": [{"bibliographic_title": "宇宙航空研究開発機構研究開発報告: 宇宙科学情報解析論文誌: 第11号"}, {"bibliographic_title": "JAXA Research and Development Report: Journal of Space Science Informatics Japan: Volume 11", "bibliographic_titleLang": "en"}]}]}, "item_3_description_16": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "GAPS(General AntiParticle Spectrometer)は宇宙線反粒子の高感度観測によって暗黒物質を起源とする反重陽子の探索を目指す気球実験計画である.GAPS では,高い識別率や正確性が求められる宇宙線反粒子識別に対して機械学習の活用が検討されている.先行研究では,三次元のCNN(畳み込みニューラルネットワーク)モデルに用いることで,反粒子の入射角と入射位置を固定した限定的な条件下でのシミュレーションデータに対して高い識別精度が確認されている.本研究では機械学習の高い精度の識別における要因の分析によって識別の説明性を求めるため,CNN モデルが識別において注視している部分を可視化し,誤って識別したケースを分析した.", "subitem_description_type": "Abstract"}]}, "item_3_description_17": {"attribute_name": "抄録(英)", "attribute_value_mlt": [{"subitem_description": "The General AntiParticle Spectrometer (GAPS) aims to search for antideuterons originating from dark matter through highly sensitive observation of cosmic ray antiparticles. In GAPS, the use of machine learning is being considered for cosmic ray antiparticle identification, which requires high rejection power and identification accuracy. In a previous study, a three-dimensional convolutional neural network (CNN) model was used to achieve high rejection power for simulated data under limited conditions where the incident angle and position of the antiparticle are fixed. In this study, in order to seek the explanatory power of discrimination by analyzing the factors that contribute to the high accuracy of machine learning, the parts that the CNN model focuses on in discrimination are visualized, and the cases of incorrect discrimination are analyzed.", "subitem_description_type": "Other"}]}, "item_3_description_18": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "形態: カラー図版あり", "subitem_description_type": "Other"}]}, "item_3_description_19": {"attribute_name": "内容記述(英)", "attribute_value_mlt": [{"subitem_description": "Physical characteristics: Original contains color illustrations", "subitem_description_type": "Other"}]}, "item_3_description_32": {"attribute_name": "資料番号", "attribute_value_mlt": [{"subitem_description": "資料番号: AA2130033004", "subitem_description_type": "Other"}]}, "item_3_description_33": {"attribute_name": "レポート番号", "attribute_value_mlt": [{"subitem_description": "レポート番号: JAXA-RR-21-008", "subitem_description_type": "Other"}]}, "item_3_identifier_registration": {"attribute_name": "ID登録", "attribute_value_mlt": [{"subitem_identifier_reg_text": "10.20637/00048403", "subitem_identifier_reg_type": "JaLC"}]}, "item_3_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "宇宙航空研究開発機構(JAXA)"}]}, "item_3_publisher_9": {"attribute_name": "出版者(英)", "attribute_value_mlt": [{"subitem_publisher": "Japan Aerospace Exploration Agency (JAXA)"}]}, "item_3_source_id_22": {"attribute_name": "ISSNONLINE", "attribute_value_mlt": [{"subitem_source_identifier": "2433-2216", "subitem_source_identifier_type": "ISSN"}]}, "item_3_text_34": {"attribute_name": "メタデータ提供者", "attribute_value_mlt": [{"subitem_text_value": "メタデータ提供者: JAXA"}]}, "item_3_text_35": {"attribute_name": "JAXAカテゴリ", "attribute_value_mlt": [{"subitem_text_value": "JAXAカテゴリ: 研究開発報告"}]}, "item_3_text_36": {"attribute_name": "JAXAカテゴリ2", "attribute_value_mlt": [{"subitem_text_value": "JAXAカテゴリ2: IS"}]}, "item_3_text_38": {"attribute_name": "NASA分類コード", "attribute_value_mlt": [{"subitem_text_value": "NASA分類コード: 77"}]}, "item_3_text_39": {"attribute_name": "NASA分類表目標", "attribute_value_mlt": [{"subitem_text_value": "NASA分類: Physics of Elementary Particles and Fields"}]}, "item_3_text_40": {"attribute_name": "jaxa出版物種類", "attribute_value_mlt": [{"subitem_text_value": "jaxa出版物種類: RR"}]}, "item_3_text_41": {"attribute_name": "jaxa出版物シリーズ", "attribute_value_mlt": [{"subitem_text_value": "jaxa出版物シリーズ: 001"}]}, "item_3_text_6": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_text_value": "東京都立大学"}, {"subitem_text_value": "東京都立大学"}, {"subitem_text_value": "群馬大学"}, {"subitem_text_value": "宇宙航空研究開発機構宇宙科学研究所学際科学研究系(JAXA)(ISAS)"}, {"subitem_text_value": "宇宙航空研究開発機構宇宙科学研究所学際科学研究系(JAXA)(ISAS)"}, {"subitem_text_value": "神奈川大学"}, {"subitem_text_value": "青山学院大学"}, {"subitem_text_value": "青山学院大学"}]}, "item_3_text_7": {"attribute_name": "著者所属(英)", "attribute_value_mlt": [{"subitem_text_language": "en", "subitem_text_value": "Tokyo Metropolitan University"}, {"subitem_text_language": "en", "subitem_text_value": "Tokyo Metropolitan University"}, {"subitem_text_language": "en", "subitem_text_value": "Gunma University"}, {"subitem_text_language": "en", "subitem_text_value": "Department of Interdisciplinary Space Science, Institute of Space and Astronautical Science, Japan Aerospace Exploration Agency (JAXA)(ISAS)"}, {"subitem_text_language": "en", "subitem_text_value": "Department of Interdisciplinary Space Science, Institute of Space and Astronautical Science, Japan Aerospace Exploration Agency (JAXA)(ISAS)"}, {"subitem_text_language": "en", "subitem_text_value": "Kanagawa University"}, {"subitem_text_language": "en", "subitem_text_value": "Aoyama gakuin University"}, {"subitem_text_language": "en", "subitem_text_value": "Aoyama gakuin University"}]}, "item_3_version_type_30": {"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": "今福, 拓海"}], "nameIdentifiers": [{"nameIdentifier": "545808", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "石川, 博"}], "nameIdentifiers": [{"nameIdentifier": "545809", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "荒木, 徹也"}], "nameIdentifiers": [{"nameIdentifier": "545810", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "山本, 幸生"}], "nameIdentifiers": [{"nameIdentifier": "545811", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "福家, 英之"}], "nameIdentifiers": [{"nameIdentifier": "545812", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "清水, 雄輝"}], "nameIdentifiers": [{"nameIdentifier": "545813", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "和田, 拓也"}], "nameIdentifiers": [{"nameIdentifier": "545814", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "中上, 裕輔"}], "nameIdentifiers": [{"nameIdentifier": "545815", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "IMAFUKU, Takumi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545816", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "ISHIKAWA, Hiroshi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545817", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "ARAKI, Tetsuya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545818", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "YAMAMOTO, Yukio", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545819", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "FUKE, Hideyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545820", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "SHIMIZU, Yuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545821", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "WADA, Takuya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545822", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "NAKAGAMI, Yusuke", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "545823", "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": "2022-02-28"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "AA2130033004.pdf", "filesize": [{"value": "1.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1100000.0, "url": {"label": "AA2130033004.pdf", "url": "https://jaxa.repo.nii.ac.jp/record/48419/files/AA2130033004.pdf"}, "version_id": "a928beb6-c6a5-4366-8e75-011e97e9b434"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "3DCNN", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Grad-CAM", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "GAPS", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "technical report", "resourceuri": "http://purl.org/coar/resource_type/c_18gh"}]}, "item_title": "宇宙線反粒子識別を対象とした機械学習の応用と根拠の可視化", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "宇宙線反粒子識別を対象とした機械学習の応用と根拠の可視化"}]}, "item_type_id": "3", "owner": "1", "path": ["1893", "2177", "2194"], "permalink_uri": "https://doi.org/10.20637/00048403", "pubdate": {"attribute_name": "公開日", "attribute_value": "2022-02-28"}, "publish_date": "2022-02-28", "publish_status": "0", "recid": "48419", "relation": {}, "relation_version_is_last": true, "title": ["宇宙線反粒子識別を対象とした機械学習の応用と根拠の可視化"], "weko_shared_id": 1}
宇宙線反粒子識別を対象とした機械学習の応用と根拠の可視化
https://doi.org/10.20637/00048403
https://doi.org/10.20637/00048403fe83aa4f-069b-421c-9695-35b37e55423d
名前 / ファイル | ライセンス | アクション |
---|---|---|
AA2130033004.pdf (1.1 MB)
|
|
Item type | テクニカルレポート / Technical Report(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2022-02-28 | |||||
タイトル | ||||||
タイトル | 宇宙線反粒子識別を対象とした機械学習の応用と根拠の可視化 | |||||
言語 | ||||||
言語 | jpn | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | 3DCNN | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Grad-CAM | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | GAPS | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||
資源タイプ | technical report | |||||
ID登録 | ||||||
ID登録 | 10.20637/00048403 | |||||
ID登録タイプ | JaLC | |||||
その他のタイトル(英) | ||||||
その他のタイトル | Application of Machine Learning and Visualization of Evidence for Cosmic-Ray Antiparticle Identification | |||||
著者 |
今福, 拓海
× 今福, 拓海× 石川, 博× 荒木, 徹也× 山本, 幸生× 福家, 英之× 清水, 雄輝× 和田, 拓也× 中上, 裕輔× IMAFUKU, Takumi× ISHIKAWA, Hiroshi× ARAKI, Tetsuya× YAMAMOTO, Yukio× FUKE, Hideyuki× SHIMIZU, Yuki× WADA, Takuya× NAKAGAMI, Yusuke |
|||||
著者所属 | ||||||
東京都立大学 | ||||||
著者所属 | ||||||
東京都立大学 | ||||||
著者所属 | ||||||
群馬大学 | ||||||
著者所属 | ||||||
宇宙航空研究開発機構宇宙科学研究所学際科学研究系(JAXA)(ISAS) | ||||||
著者所属 | ||||||
宇宙航空研究開発機構宇宙科学研究所学際科学研究系(JAXA)(ISAS) | ||||||
著者所属 | ||||||
神奈川大学 | ||||||
著者所属 | ||||||
青山学院大学 | ||||||
著者所属 | ||||||
青山学院大学 | ||||||
著者所属(英) | ||||||
en | ||||||
Tokyo Metropolitan University | ||||||
著者所属(英) | ||||||
en | ||||||
Tokyo Metropolitan University | ||||||
著者所属(英) | ||||||
en | ||||||
Gunma University | ||||||
著者所属(英) | ||||||
en | ||||||
Department of Interdisciplinary Space Science, Institute of Space and Astronautical Science, Japan Aerospace Exploration Agency (JAXA)(ISAS) | ||||||
著者所属(英) | ||||||
en | ||||||
Department of Interdisciplinary Space Science, Institute of Space and Astronautical Science, Japan Aerospace Exploration Agency (JAXA)(ISAS) | ||||||
著者所属(英) | ||||||
en | ||||||
Kanagawa University | ||||||
著者所属(英) | ||||||
en | ||||||
Aoyama gakuin University | ||||||
著者所属(英) | ||||||
en | ||||||
Aoyama gakuin University | ||||||
出版者 | ||||||
出版者 | 宇宙航空研究開発機構(JAXA) | |||||
出版者(英) | ||||||
出版者 | Japan Aerospace Exploration Agency (JAXA) | |||||
書誌情報 |
宇宙航空研究開発機構研究開発報告: 宇宙科学情報解析論文誌: 第11号 en : JAXA Research and Development Report: Journal of Space Science Informatics Japan: Volume 11 巻 JAXA-RR-21-008, p. 37-43, 発行日 2022-02-28 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | GAPS(General AntiParticle Spectrometer)は宇宙線反粒子の高感度観測によって暗黒物質を起源とする反重陽子の探索を目指す気球実験計画である.GAPS では,高い識別率や正確性が求められる宇宙線反粒子識別に対して機械学習の活用が検討されている.先行研究では,三次元のCNN(畳み込みニューラルネットワーク)モデルに用いることで,反粒子の入射角と入射位置を固定した限定的な条件下でのシミュレーションデータに対して高い識別精度が確認されている.本研究では機械学習の高い精度の識別における要因の分析によって識別の説明性を求めるため,CNN モデルが識別において注視している部分を可視化し,誤って識別したケースを分析した. | |||||
抄録(英) | ||||||
内容記述タイプ | Other | |||||
内容記述 | The General AntiParticle Spectrometer (GAPS) aims to search for antideuterons originating from dark matter through highly sensitive observation of cosmic ray antiparticles. In GAPS, the use of machine learning is being considered for cosmic ray antiparticle identification, which requires high rejection power and identification accuracy. In a previous study, a three-dimensional convolutional neural network (CNN) model was used to achieve high rejection power for simulated data under limited conditions where the incident angle and position of the antiparticle are fixed. In this study, in order to seek the explanatory power of discrimination by analyzing the factors that contribute to the high accuracy of machine learning, the parts that the CNN model focuses on in discrimination are visualized, and the cases of incorrect discrimination are analyzed. | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 形態: カラー図版あり | |||||
内容記述(英) | ||||||
内容記述タイプ | Other | |||||
内容記述 | Physical characteristics: Original contains color illustrations | |||||
ISSNONLINE | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 2433-2216 | |||||
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 | |||||
資料番号 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 資料番号: AA2130033004 | |||||
レポート番号 | ||||||
内容記述タイプ | Other | |||||
内容記述 | レポート番号: JAXA-RR-21-008 |