Brain Activity Detection Method for NIRS-BCI Rehabilitation System

概要

論文の詳細を見る
Brain-computer interface (BCI) is used to controls machines and devices by extracting neural information from human brain activity. BCI is expected to medical care as a rehabilitation system. In an earlier study developed an NIRS-BCI rehabilitation system. But , this study's detection method of brain activity is simple threshold. For this reason, it is difficult obtain highly accurate control operations. This study proposes a new brain activity detection method that uses separability and perseptron to achieve highly accurate on/off operations for rehabilitation system. Brain activity during actual grasping tasks and imagined grasping tasks are measured to demonstrate the validity of the proposed method. As a result, the proposed method of correct could be confirmed to have improved detection precision. In grasping task, the average correct rate by the proposed method improved 18.6 point compared with the conventional method. In imagined grasping task, the average correct rate by the proposed method improved 10.5 point compared with the conventional method. These results indicate that our proposed method enabled more accurate detection than conventional method. Results show that the proposed method is effective for detecting brain activity level.