Brain Computer Interface based on virtual sound image with other modal information

2014 Fiscal Year Final Research Report

• Project/Area Number: 24300051
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Nagaoka University of Technology
• Principal Investigator: WADA Yasuhiro 長岡技術科学大学, 工学(系)研究科(研究院), 教授 (70293248)
• Co-Investigator(Kenkyū-buntansha): OHISHI Kiyoshi 長岡技術科学大学, 工学部, 教授 (40185187) ; YANO Shohei 長岡工業高等専門学校, 電気電子システム工学科, 准教授 (90332006) ; NAMBU Isao 長岡技術科学大学, 工学部, 助教 (40553235)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: BCI / 頭外音像定位技術 / 脳波 / 機能的近赤外分光法

Outline of Final Research Achievements

Brain-computer interface (BCI) is actively researched to control various interfaces by using human brain activity. Many BCI studies utilized an electroencephalogram (EEG), and visual stimulation paradigm. However, in patients with vision loss, visual BCI is not the preferred choice. Thus, auditory BCI has been focused attention. However, many auditory BCI are necessary to arrange the speaker for listening. We focused on auditory BCI paradigm using a virtual sound source by earphones.
We extended to 13 virtual sound sources and examined its performance. Eight subjects participated in the oddball experiments and their brain activity was measured using EEG. The measured EEG signal was used for estimating the intended direction by support vector machine (SVM). As a result, average classification rate across subjects in 10-trial signal averaging was 80.1%. This suggests a possibility to estimate intended direction of the virtual sound source from 13 directions.

Free Research Field

ブレイン・コンピュータ・インターフェース