Noise robust brain computer interface that improve the quality of life of the ALS patient

2016 Fiscal Year Final Research Report

• Project/Area Number: 15K12614
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Rehabilitation science/Welfare engineering
• Research Institution: Kagoshima National College of Technology
• Principal Investigator: HARADA HARUYUKI 鹿児島工業高等専門学校, 電子制御工学科, 嘱託教授 (80192285)
• Research Collaborator: MATSUYAMA Ryota ; KASHIWADA Daiki
• Project Period (FY): 2015-04-01 – 2017-03-31
• Keywords: ヒューマンインターフェイス / BCI / ALS患者 / バイノーラル・ビート

Outline of Final Research Achievements

By focusing on the binaural beats and the correlation between the high frequency components of the measured brain wave, we studied BCI that had high recognition rate and was superior in anti-noise characteristics even if the number of electrodes was few, and got the following results.
(1) The recognition rate was improved by the training system that feeds back the graph of the characteristic vector on the monitor to a test subject in real time, but there were individual differences of the recognition rate. (2) We examined the significance of the difference of the element of the characteristic vector of each task by a multiple comparison assay and we showed that if we selected the meaningful elements of the characteristic vector, we might be able to reduce the number of the electrodes. (3) If the binaural beats were used, the high frequency components of brain wave would become dominant, but the recognition rates were not improved, even if mental tasks were executed in such a condition.

Free Research Field

デジタル信号処理　医用生体工学