Prediction of finger movements from electroencephalogram for constructing a virtual keyboard using brain signals

2016 Fiscal Year Final Research Report

• Project/Area Number: 26560303
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Rehabilitation science/Welfare engineering
• Research Institution: Nagaoka University of Technology
• Principal Investigator: Nambu Isao 長岡技術科学大学, 工学研究科, 助教 (40553235)
• Co-Investigator(Renkei-kenkyūsha): OSU Rieko 国際電気通信基礎技術研究所, 研究員 (60374112)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 脳活動 / EEG / fNIRS / BCI / 運動

Outline of Final Research Achievements

In this research, we explored a possibility to make a virtual keyboard system using brain signals. First, we measured brain activity using an electroencephalogram (EEG) and showed a possibility for decoding individual finger movements or its imagery from EEG signals. Next, using functional magnetic resonance imaging, we found that types of sequential finger movements can be decoded from preparatory brain activities in the premotor and supplementary motor areas contralateral to the moving hand. Finally, we proposed a method for reduction of systemic artifacts from scalp layers in functional near-infrared spectroscopy and evaluated its effectiveness. Taken all together, our results suggest that we can predict finger movements from non-invasive brain imaging techniques. This techniques could be used for constructing a brain-based virtual keyboard in future.

Free Research Field

脳計測工学、生体情報処理