NIRSを用いた未知情報判別に関する検討

カテゴリ: 論文誌(論文単位)

グループ名: 【E】センサ・マイクロマシン部門

発行日: 2012/10/01

タイトル(英語): A Study on Distinction of Unfamiliar Information using NIRS

著者名: 参沢　匡将（富山大学大学院理工学研究部），後藤　かをり（富山大学大学院理工学研究部），下川　哲矢（東京理科大学経営学部），広林　茂樹（富山大学大学院理工学研究部）

著者名(英語): Tadanobu Misawa (Graduate School of Science and Engineering, University of Toyama), Kaori Goto (Graduate School of Science and Engineering, University of Toyama), Tetsuya Shimokawa (The School of Management, Tokyo University of Science), Shigeki Hirobayashi (Graduate School of Science and Engineering, University of Toyama)

キーワード: 近赤外分光法，ブレイン・コンピュータ・インターフェース，ニューロマーケティング，単一試行分類　　Near Infrared Spectroscopy (NIRS)，Brain-computer interface，Neuromarketing，Single-trial classification

要約(英語): Recent developments in functional neuroimaging technologies have given us a better understanding of the activation of sites in the brain. These technologies have been applied to brain-computer interfaces (BCIs). These technologies have been used in medicine and economics and for decision-making in business, thereby leading to the emergence of new fields of neuroeconomics and neuromarketing. In the current study, we investigate the possibility that brain activity distinguishes unfamiliar information. Typical applications are that a user who encounters unfamiliar information while browsing a website can automatically obtain the details of this information through BCIs without having to perform a web search. In this study, we use near infrared spectroscopy (NIRS) system that acquires data in real time in order to measure brain activity. The results of our experiment indicated that our proposed method allows for the distinguishing of unfamiliar information with about 80% accuracy, as demonstrated in the performance of 60 tasks. So, it is indeed possible to develop a BCI that can distinguish unfamiliar information.

本誌: 電気学会論文誌E（センサ・マイクロマシン部門誌） Vol.132 No.10 （2012） 特集：脳機能計測技術

本誌掲載ページ: 348-354 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejsmas/132/10/132_348/_article/-char/ja/