{"created":"2023-07-27T06:24:49.597469+00:00","id":7889,"links":{},"metadata":{"_buckets":{"deposit":"a00774f4-eb16-44ab-adba-634c455e308b"},"_deposit":{"created_by":3,"id":"7889","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"7889"},"status":"published"},"_oai":{"id":"oai:kanazawa-u.repo.nii.ac.jp:00007889","sets":["934:935:936"]},"author_link":["353","10822","377"],"item_8_biblio_info_8":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2008-11-01","bibliographicIssueDateType":"Issued"},"bibliographicPageStart":"P-17","bibliographic_titles":[{"bibliographic_title":"第23回信号処理シンポジュウム（金沢）"}]}]},"item_8_description_21":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"階層形ニューラルネットワークによるブレイン・コンピュータ・インターフェイス（BCI）において，メンタルタスク固有の特徴を抽出するために，脳波の個々のチャネルの特徴を強調する方法を提案している．7 チャネルの脳波を7 つのベクトルと見なすことにより，チャネル間でグラムシュミットの直交化を適用した．直交化するチャネルの順番には自由度が存在するので，直交化するチャネル順による分類精度について検討した．次に，2 種類のチャネル順で直交化した脳波をニューラルネットワークの入力データととする方法を検討した．更に，汎化能力を向上させるために，入力データにランダムノイズを付 加する方法を検討した．シミュレーションには、コロラド州立大学が公開している脳波データを用いた．直交化したデータを用いることにより，分類の正答率は70%から78%に上昇し，誤答率は10%から8%に低下した．正答率と誤答率の比は0.875 から0.907 に上昇した．異なるチャネル順により直交化した2 つの入力データを用いた場合には，誤答率は10%から2%へと大幅に低下し，比も0.973 に上昇した．FFT and Multilayer neural networks (MLNN) have been applied to 'Brain Computer Interface' (BCI). In this paper, in order to extract features of mental tasks, individual feature of brain waves of each channel is emphasized. Since the brain wave in some interval can be regarded as a vector, Gram-Schmidt orthogonalization is applied for this purpose. There exists degree of freedom in the channel order to be orthogonalized. Effect of the channel order on classi cation accuracy is investigated. Next, two channel orders are used for generating the MLNN input data. Two kinds of methods using a single NN and double NNs are examined. Furthermore, a generalization method, adding small random numbers to the MLNN input data, is applied. Simulations are carried out by using the brain waves, available from the Colorado State University website. By using the orthogonal components, a correct classi cation rate Pc can be improved from 70% to 78%, an incorrect classi cation rate Pe can be suppressed from 10% to 8%. As a result, a rate Rc = Pc = (Pc + Pe) can be improved from 0.875 to 0.907. When two di erent channel orders are used, Pe can be drastically suppressed from 10% to 2%, and Rc can be improved up to 0.973. The generalization method is useful especially for using a single channel order. Pc can be increased up to 84～88% and Pe can be suppressed down to 2～4%, resulting in Rc = 0.957～0.977.","subitem_description_type":"Abstract"}]},"item_8_description_5":{"attribute_name":"提供者所属","attribute_value_mlt":[{"subitem_description":"金沢大学理工研究域　電子情報学系","subitem_description_type":"Other"}]},"item_8_publisher_17":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"IEICE 電子情報通信学会 / 信号処理研究専門委員会 / 第23回 信号処理シンポジウム"}]},"item_8_relation_28":{"attribute_name":"関連URI","attribute_value_mlt":[{"subitem_relation_type_id":{"subitem_relation_type_id_text":"http://www.ieice.org/~sip/symp/2008/","subitem_relation_type_select":"URI"}}]},"item_8_version_type_25":{"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":"堀田, 大貴"},{"creatorName":"ナカヤマ, ケンジ","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中山, 謙二"}],"nameIdentifiers":[{},{},{}]},{"creatorNames":[{"creatorName":"平野, 晃宏"}],"nameIdentifiers":[{},{},{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2017-10-03"}],"displaytype":"detail","filename":"TE-PR-NAKAYAMA-K-P17.pdf","filesize":[{"value":"453.0 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"TE-PR-NAKAYAMA-K-P17.pdf","url":"https://kanazawa-u.repo.nii.ac.jp/record/7889/files/TE-PR-NAKAYAMA-K-P17.pdf"},"version_id":"2b78673f-b53b-42e8-b8e7-b411faffd1cf"}]},"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":"conference paper","resourceuri":"http://purl.org/coar/resource_type/c_5794"}]},"item_title":"多チャンネル脳波の直交成分を用いたニューラルネットワークによるブレイン・コンピュータ・インターフェイス","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"多チャンネル脳波の直交成分を用いたニューラルネットワークによるブレイン・コンピュータ・インターフェイス"},{"subitem_title":"Neural Network Based BCI by Using Orthogonal Components of Multi-Channel","subitem_title_language":"en"}]},"item_type_id":"8","owner":"3","path":["936"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-10-03"},"publish_date":"2017-10-03","publish_status":"0","recid":"7889","relation_version_is_last":true,"title":["多チャンネル脳波の直交成分を用いたニューラルネットワークによるブレイン・コンピュータ・インターフェイス"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-07-28T02:17:54.614214+00:00"}