WEKO3
アイテム
{"_buckets": {"deposit": "036225de-6ea9-41b0-84b3-860a8ea9a5c2"}, "_deposit": {"created_by": 1, "id": "22934", "owners": [1], "pid": {"revision_id": 0, "type": "depid", "value": "22934"}, "status": "published"}, "_oai": {"id": "oai:u-fukui.repo.nii.ac.jp:00022934", "sets": ["2480"]}, "author_link": ["66887", "66885", "66886"], "item_10003_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2013-12", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "65", "bibliographicPageStart": "61", "bibliographic_titles": [{"bibliographic_title": "2013 Second International Conference on Robot, Vision and Signal Processing"}]}]}, "item_10003_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Abstract—In order to generate or tune fuzzy rules, Neuro- Fuzzy learning algorithms with Gaussian type membership functions based on gradient-descent method are well known. In this paper, we propose a new learning approach, the Quaternion Neuro-Fuzzy learning algorithm. This method is an extension of the conventional method to four-dimensional space by using a quaternion neural network that maps quaternion to real values. Input, antecedent membership functions and consequent singletons are quaternion, and output is real. Four-dimensional input can be better represented by quaternion than by real values. We compared it with the conventional method by several function identification problems, and revealed that the proposed method outperformed the counterpart: The number of rules was reduced to 5 from 625, the number of epochs by one fortieth, and error by one tenth in the best cases.", "subitem_description_type": "Abstract"}]}, "item_10003_description_6": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "The Second International Conference on Robot, Vision and Signal Processing December 10-12, 2013 Kitakyushu, Japan", "subitem_description_type": "Other"}]}, "item_10003_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE"}]}, "item_10003_relation_10": {"attribute_name": "ISBN", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "9781479931842", "subitem_relation_type_select": "ISBN"}}]}, "item_10003_relation_11": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "TD00007956", "subitem_relation_type_select": "NCID"}}]}, "item_10003_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1109/RVSP.2013.22", "subitem_relation_type_select": "DOI"}}]}, "item_10003_version_type_20": {"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_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Hata, Ryusuke"}], "nameIdentifiers": [{"nameIdentifier": "66885", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Islam, Monirul"}], "nameIdentifiers": [{"nameIdentifier": "66886", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Murase, Kazuyuki"}], "nameIdentifiers": [{"nameIdentifier": "66887", "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": "2020-08-04"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "Hata_3184a061.pdf", "filesize": [{"value": "290.4 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "(c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.", "licensetype": "license_free", "mimetype": "application/pdf", "size": 290400.0, "url": {"label": "Hata_3184a061.pdf", "url": "https://u-fukui.repo.nii.ac.jp/record/22934/files/Hata_3184a061.pdf"}, "version_id": "7f9ae9f4-9527-409d-abaa-c73f2bad2bd3"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "neuro fuzzy", "subitem_subject_scheme": "Other"}, {"subitem_subject": "quaternion neural networks", "subitem_subject_scheme": "Other"}, {"subitem_subject": "fuzzy", "subitem_subject_scheme": "Other"}, {"subitem_subject": "neural networks", "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": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "Quaternion Neuro-Fuzzy Learning Algorithm for Fuzzy Rule Generation", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Quaternion Neuro-Fuzzy Learning Algorithm for Fuzzy Rule Generation"}]}, "item_type_id": "10003", "owner": "1", "path": ["2480"], "permalink_uri": "http://hdl.handle.net/10098/8432", "pubdate": {"attribute_name": "公開日", "attribute_value": "2014-07-30"}, "publish_date": "2014-07-30", "publish_status": "0", "recid": "22934", "relation": {}, "relation_version_is_last": true, "title": ["Quaternion Neuro-Fuzzy Learning Algorithm for Fuzzy Rule Generation"], "weko_shared_id": -1}
Quaternion Neuro-Fuzzy Learning Algorithm for Fuzzy Rule Generation
http://hdl.handle.net/10098/8432
http://hdl.handle.net/10098/8432df146c3d-8076-44fc-a8aa-9f313ea13900
名前 / ファイル | ライセンス | アクション |
---|---|---|
Hata_3184a061.pdf (290.4 kB)
|
(c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2014-07-30 | |||||
タイトル | ||||||
タイトル | Quaternion Neuro-Fuzzy Learning Algorithm for Fuzzy Rule Generation | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | neuro fuzzy | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | quaternion neural networks | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | fuzzy | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | neural networks | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
資源タイプ | conference paper | |||||
著者 |
Hata, Ryusuke
× Hata, Ryusuke× Islam, Monirul× Murase, Kazuyuki |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Abstract—In order to generate or tune fuzzy rules, Neuro- Fuzzy learning algorithms with Gaussian type membership functions based on gradient-descent method are well known. In this paper, we propose a new learning approach, the Quaternion Neuro-Fuzzy learning algorithm. This method is an extension of the conventional method to four-dimensional space by using a quaternion neural network that maps quaternion to real values. Input, antecedent membership functions and consequent singletons are quaternion, and output is real. Four-dimensional input can be better represented by quaternion than by real values. We compared it with the conventional method by several function identification problems, and revealed that the proposed method outperformed the counterpart: The number of rules was reduced to 5 from 625, the number of epochs by one fortieth, and error by one tenth in the best cases. | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | The Second International Conference on Robot, Vision and Signal Processing December 10-12, 2013 Kitakyushu, Japan | |||||
書誌情報 |
2013 Second International Conference on Robot, Vision and Signal Processing p. 61-65, 発行日 2013-12 |
|||||
出版者 | ||||||
出版者 | IEEE | |||||
ISBN | ||||||
識別子タイプ | ISBN | |||||
関連識別子 | 9781479931842 | |||||
書誌レコードID | ||||||
識別子タイプ | NCID | |||||
関連識別子 | TD00007956 | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1109/RVSP.2013.22 | |||||
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 |