{"links":{},"id":185999,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00185999","sets":["1164:4061:9376:9377"]},"path":["9377"],"owner":"11","recid":"185999","title":["屋内歩行軌跡統合のための共通部分推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-02-19"},"_buckets":{"deposit":"86ee49c4-d5c2-465b-b204-1bdff05b26d4"},"_deposit":{"id":"185999","pid":{"type":"depid","value":"185999","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"屋内歩行軌跡統合のための共通部分推定","author_link":["415552","415551","415557","415550","415554","415555","415549","415556","415547","415553","415548","415546"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"屋内歩行軌跡統合のための共通部分推定"},{"subitem_title":"Common Part Estimation For Integration of Indoor Walking Trajectory","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"屋内測位・参加型センシング","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-02-19","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"愛知工業大学情報科学部"},{"subitem_text_value":"三菱電機エンジニアリング株式会社"},{"subitem_text_value":"愛知工業大学情報科学部"},{"subitem_text_value":"愛知工業大学情報科学部"},{"subitem_text_value":"愛知工業大学情報科学部"},{"subitem_text_value":"愛知工業大学情報科学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Aichi Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Mitsubishi Electric Engineering Company","subitem_text_language":"en"},{"subitem_text_value":"Aichi Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Aichi Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Aichi Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Aichi Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/185999/files/IPSJ-UBI18057038.pdf","label":"IPSJ-UBI18057038.pdf"},"date":[{"dateType":"Available","dateValue":"2020-02-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-UBI18057038.pdf","filesize":[{"value":"1.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"36"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"dd132028-20a3-4bc2-92be-6f5aa50bc9a0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"杉本, 壮"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"伊藤, 信行"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"内藤, 克浩"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中條, 直也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"水野, 忠則"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"梶, 克彦"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Sou, Sugimoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuyuki, Ito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Katsuhiro, Naito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoya, Chujo","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tadanori, Mizuno","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Katsuhiko, Kaji","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11838947","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8698","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究の最終目標は，特定建物内の歩行センシングデータの複数ユーザからの収集と，推定された 3 次元歩行軌跡の統合による，歩行空間ネットワーク構造の自動生成である．歩行空間ネットワーク構造の生成のためには，複数の歩行軌跡の統合が必要である．推定された複数の 3 次元歩行軌跡には，同じ通路を歩く共通する部分が存在する．本稿では，このような共通部分を推定し，共通部分を手がかりとした複数の歩行軌跡同士の統合を目指す．既存の研究として，ノードの種類 （右折 ・ 左折） の並びや Wi-Fi，行動の種類，リンク長の類似度を閾値を用いて算出して，共通部分を推定する手法が存在する．しかし問題として，右左折の推定がイレギュラな動作の影響を受けるため誤検出されたり，類似度算出においてパラメータの種類だけ閾値を設定しなければならない点が挙げられる．そこで我々は，共通部分の推定に安定して直線的に歩行している区間 （安定歩行区間） を使用する．安定歩行区間は変化が少ない状態の継続を検出するので，右左折よりも推定精度が高くなると考えられる．安定歩行区間同士の対応関係を，歩行時間，歩行距離，高さ，Wi-Fi 情報を用いて機械学習により推定する．機械学習には，サポートベクトルマシン （Support Vector Machine，SVM） を使用する．屋内歩行センシングコーパス HASC-IPSC を用いた評価実験の結果，F 値が 0.81 という結果を得られた．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告ユビキタスコンピューティングシステム（UBI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2018-02-19","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"38","bibliographicVolumeNumber":"2018-UBI-57"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:53:03.500509+00:00","updated":"2025-01-20T02:45:59.197054+00:00"}