WEKO3
アイテム
{"_buckets": {"deposit": "5fdcfdb3-973d-4ab0-b00e-02268cfe2627"}, "_deposit": {"id": "35792", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "35792"}, "status": "published"}, "_oai": {"id": "oai:tsukuba.repo.nii.ac.jp:00035792", "sets": ["2529", "1058"]}, "item_5_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2015-10", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "10", "bibliographicPageEnd": "2644", "bibliographicPageStart": "2632", "bibliographicVolumeNumber": "27", "bibliographic_titles": [{"bibliographic_title": "IEEE transactions on knowledge and data engineering"}]}]}, "item_5_creator_3": {"attribute_name": "著者別名", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "日野, 英逸"}], "nameIdentifiers": [{"nameIdentifier": "120928", "nameIdentifierScheme": "WEKO"}]}]}, "item_5_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "In this paper, the limitation that is prominent in most existing works of change-point detection methods is addressed by proposing a nonparametric, computationally efficient method. The limitation is that most works assume that each data point observed at each time step is a single multi-dimensional vector. However, there are many situations where this does not hold. Therefore, a setting where each observation is a collection of random variables, which we call a bag of data, is considered. After estimating the underlying distribution behind each bag of data and embedding those distributions in a metric space, the change-point score is derived by evaluating how the sequence of distributions is fluctuating in the metric space using a distance-based information estimator. Also, a procedure that adaptively determines when to raise alerts is incorporated by calculating the confidence interval of the change-point score at each time step. This avoids raising false alarms in highly noisy situations and enables detecting changes of various magnitudes. A number of experimental studies and numerical examples are provided to demonstrate the generality and the effectiveness of our approach with both synthetic and real datasets.\n", "subitem_description_type": "Abstract"}]}, "item_5_publisher_27": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE"}]}, "item_5_relation_11": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1109/TKDE.2015.2426693", "subitem_relation_type_select": "DOI"}}]}, "item_5_rights_12": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission."}]}, "item_5_select_15": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "author"}]}, "item_5_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1041-4347", "subitem_source_identifier_type": "ISSN"}]}, "item_5_source_id_9": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA10692959", "subitem_source_identifier_type": "NCID"}]}, "item_5_subject_20": {"attribute_name": "NIIサブジェクト", "attribute_value_mlt": [{"subitem_subject": "情報学", "subitem_subject_scheme": "Other"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Koshijima, K."}], "nameIdentifiers": [{"nameIdentifier": "120925", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Hino, H"}], "nameIdentifiers": [{"nameIdentifier": "120926", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Murata, N."}], "nameIdentifiers": [{"nameIdentifier": "120927", "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": "2015-10-21"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "IEEE_27-10.pdf", "filesize": [{"value": "1.8 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1800000.0, "url": {"label": "IEEE_27-10", "url": "https://tsukuba.repo.nii.ac.jp/record/35792/files/IEEE_27-10.pdf"}, "version_id": "cd2e96c2-0f5e-4596-a9a1-80d5eae52807"}]}, "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": "Change-Point Detection in a Sequence of Bags-of-Data", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Change-Point Detection in a Sequence of Bags-of-Data"}]}, "item_type_id": "5", "owner": "1", "path": ["2529", "1058"], "permalink_uri": "http://hdl.handle.net/2241/00128943", "pubdate": {"attribute_name": "公開日", "attribute_value": "2015-10-21"}, "publish_date": "2015-10-21", "publish_status": "0", "recid": "35792", "relation": {}, "relation_version_is_last": true, "title": ["Change-Point Detection in a Sequence of Bags-of-Data"], "weko_shared_id": 5}
Change-Point Detection in a Sequence of Bags-of-Data
http://hdl.handle.net/2241/00128943
http://hdl.handle.net/2241/00128943a661d2ab-af20-441f-8138-3c7dc2489aa7
名前 / ファイル | ライセンス | アクション |
---|---|---|
IEEE_27-10 (1.8 MB)
|
|
Item type | Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2015-10-21 | |||||
タイトル | ||||||
タイトル | Change-Point Detection in a Sequence of Bags-of-Data | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_6501 | |||||
タイプ | journal article | |||||
著者 |
Koshijima, K.
× Koshijima, K.× Hino, H× Murata, N. |
|||||
著者別名 |
日野, 英逸
× 日野, 英逸 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | In this paper, the limitation that is prominent in most existing works of change-point detection methods is addressed by proposing a nonparametric, computationally efficient method. The limitation is that most works assume that each data point observed at each time step is a single multi-dimensional vector. However, there are many situations where this does not hold. Therefore, a setting where each observation is a collection of random variables, which we call a bag of data, is considered. After estimating the underlying distribution behind each bag of data and embedding those distributions in a metric space, the change-point score is derived by evaluating how the sequence of distributions is fluctuating in the metric space using a distance-based information estimator. Also, a procedure that adaptively determines when to raise alerts is incorporated by calculating the confidence interval of the change-point score at each time step. This avoids raising false alarms in highly noisy situations and enables detecting changes of various magnitudes. A number of experimental studies and numerical examples are provided to demonstrate the generality and the effectiveness of our approach with both synthetic and real datasets. | |||||
書誌情報 |
IEEE transactions on knowledge and data engineering 巻 27, 号 10, p. 2632-2644, 発行日 2015-10 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1041-4347 | |||||
書誌レコードID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA10692959 | |||||
DOI | ||||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1109/TKDE.2015.2426693 | |||||
権利 | ||||||
権利情報 | © 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. | |||||
著者版フラグ | ||||||
値 | author | |||||
出版者 | ||||||
出版者 | IEEE |