Yumi Dobashi, Atsushi Takemot , Shu Shigezumi, Takumi Shiraki, Katsuki Nakamura, Takashi Matsumoto
Biomedical Signal Processing, Biomedical Computing,Brain–Machine Interface (BMI), electroencephalography(EEG).
This paper proposes an EEG-based Brain–Machine Inter- face (BMI) system such that 1) the machine can determine when to end the learning phase automatically by monitor- ing the learning progress using the Sequential Error Rate (SER) as an evaluation index and 2) it involves sequen- tial learning in both the brain and the machine in a co- operative manner. In the proposed ’Brain–Machine Co- learning’, subjects learn how to use the system by means of real-time visual feedback, whereas the machine learns the subjects’ EEG signals by Bayesian sequential learning. The SER refers to the average classification error rate win- dowed over a short time period, and it represents the status of Bayesian sequential learning in real time. In our pro- posed approach, subjects can use the system while elim- inating unnecessary training. The proposed system was tested against an SSVEP classification problem. The train- ing phase varied for each subject and was sometimes short, yet satisfactory, leading to high classification accuracy.
Important Links:
Go Back
