[Updated on Apr. 18] Integration of CiNii Articles into CiNii Research

RB-ARQにおけるN-gram情報の利用とP300 spellerへの適用

IR

Bibliographic Information

Other Title
  • RB-ARQ ニ オケル N-gram ジョウホウ ノ リヨウ ト P300 speller エ ノ テキヨウ
  • Application of RB-ARQ using N-gram information to P300 speller

Search this article

Abstract

P300 spellerは,脳波から得られるP300を特徴量に用い,ユーザーが思考によって文字入力を行うBrainComputer Interface (BCI)の一種である.ここで用いられるP300はSN比が悪く,判別精度向上のためには加算平均を行う必要があるが,これによる入力速度の低下が問題となっている.一方,文章の入力においては,ある文字の出現確率やある文字の次に生じる文字の起こりやすさ,すなわち文字間の遷移確率の偏りが存在する.そこで本稿では,日本語P300 spellerにおいて,ひらがなの出現確率や文字間の遷移確率を事前確率により考慮する手法を提案し,従来手法と比較して,P300 spellerにおける入力速度が向上することを示す.P300 speller is one of the Brain Computer Interfaces, which uses P300 as the feature quantity and allows users to select letters just by thinking. Because of the low signal-to-noise ratio of the P300, signal averaging is often performed to improve the spelling accuracy instead of the degradation of the spelling speed. In texts, there is variability in occurrence probabilities and transition probabilities between letters. This paper proposes Japanese interface of P300 speller considering the occurrence probabilities and the transition probabilities as the priori probabilities. It shows that the spelling speed is improved by the proposed method comparing with the conventional method.

identifier:http://ci.nii.ac.jp/naid/110009713271

identifier:http://hdl.handle.net/2237/23518

Journal

Citations (0)*help

See more

References(0)*help

See more

Related Articles

See more

Related Data

See more

Related Books

See more

Related Dissertations

See more

Related Projects

See more

Related Products

See more

Details

Report a problem

Back to top