2024 年 23 巻 3 号 p. 241-249
We have been developing a cognitive, brain-machine interface (BMI)-based, training system called the “Neurotrainer.” This system was initially designed to detect averaged event-related potentials (ERPs), which reflect momentary heightened attention, allowing these individuals to participate in cognitive training without the need for hands-on interaction. In this study, we expanded our method to decode single-trial ERPs during a racing game, with the expectation that neurofeedback would accelerate the training process. We assessed the performance of the prototype system with healthy volunteers. The decoding accuracy of the target character was approximately 54% for a single trial and 83% for five trials (chance level = 12.5%). Moreover, ERP responses were stronger in the feedback condition than in the no-feedback condition. These results suggest that the BMI could be an effective tool for cognitive training, as real-time neurofeedback influences the brain activation of the players.
