{"created":"2023-03-30T09:23:54.560794+00:00","id":3042,"links":{},"metadata":{"_buckets":{"deposit":"9b9c3316-dda9-49d3-9d20-7887ffcea330"},"_deposit":{"created_by":7,"id":"3042","owners":[7],"pid":{"revision_id":0,"type":"depid","value":"3042"},"status":"published"},"_oai":{"id":"oai:nied-repo.bosai.go.jp:00003042","sets":[]},"author_link":[],"item_10001_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2019","bibliographicIssueDateType":"Issued"},"bibliographicPageStart":"4K2J1302","bibliographicVolumeNumber":"JSAI2019","bibliographic_titles":[{"bibliographic_title":"人工知能学会全国大会論文集","bibliographic_titleLang":"ja"},{"bibliographic_title":"Proceedings of the Annual Conference of JSAI","bibliographic_titleLang":"en"}]}]},"item_10001_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"これまで著者らは機械学習を用いて地震動予測式の構築を試みてきた[久保 2018]。しかしながら先行研究で用いたデータには強い地震動記録が極端に少ないという大きな偏りがあり、それは機械学習を用いた地震動予測器に影響を与え、強震動時の過小評価を引き起こす。本研究でこの問題の解決法を模索する過程で、学習データの重みづけと、既往の距離減衰式およびランダムフォレストの両方を組み合わせたハイブリッド手法の二つのアプローチを提案している。テストデータを用いた検証の結果、ハイブリッド手法を用いることによって強震動時の過小評価が大きく改善されることが分かった。ただし1000gal を超えるような非常に強い地震動を予測する際にはハイブリッド手法を用いても依然として過小評価気味であり、更なる検討が必要であることも示された。","subitem_description_language":"ja","subitem_description_type":"Other"},{"subitem_description":"Previous study [Kubo 2018] tried to construct a predictor of ground-motion index using a random forest method and strong-motion data recorded in Japan. However, the data-set is very biased and there are few strong ground-motion records. This causes the underestimation of the predictor for strong ground-motions. To overcome this problem, in this study, we suggest two approaches: one is the weighting of train data, and the other is the hybrid method integrating the conventional ground motion prediction equation and a machine learning approach. The verification using test data indicates that the hybrid method can largely improve the underestimation, although the underestimation still remains in predicting very strong groundmotions (>1000 gal).","subitem_description_language":"en","subitem_description_type":"Other"}]},"item_10001_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"一般社団法人 人工知能学会","subitem_publisher_language":"ja"},{"subitem_publisher":"The Japanese Society for Artificial Intelligence","subitem_publisher_language":"en"}]},"item_10001_relation_14":{"attribute_name":"DOI","attribute_value_mlt":[{"subitem_relation_type_id":{"subitem_relation_type_id_text":"10.11517/pjsai.JSAI2019.0_4K2J1302"}}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"久保久彦","creatorNameLang":"ja"},{"creatorName":"Hisahiko Kubo","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"功刀卓","creatorNameLang":"ja"},{"creatorName":"Takashi Kunugi","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"鈴木進吾","creatorNameLang":"ja"},{"creatorName":"Shingo Suzuki","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"鈴木亘","creatorNameLang":"ja"},{"creatorName":"Wataru Suzuki","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"青井真","creatorNameLang":"ja"},{"creatorName":"Shin Aoi","creatorNameLang":"en"}]}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_title":"機械学習を用いた地震動予測において偏ったデータセットが与える影響を軽減するための試み","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"機械学習を用いた地震動予測において偏ったデータセットが与える影響を軽減するための試み","subitem_title_language":"ja"},{"subitem_title":"Attempt to reduce the effect of biased data-set on ground-motion prediction using machine learning","subitem_title_language":"en"}]},"item_type_id":"40001","owner":"7","path":["1670839190650"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2023-09-20"},"publish_date":"2023-09-20","publish_status":"0","recid":"3042","relation_version_is_last":true,"title":["機械学習を用いた地震動予測において偏ったデータセットが与える影響を軽減するための試み"],"weko_creator_id":"7","weko_shared_id":-1},"updated":"2023-09-20T08:10:33.474327+00:00"}