Automatic brain cognitive control detection method

In the Internet of Things (IoT) times, our brains are powerful control center. In order to solve the newly appearing problem of automatic brain cognitive control detection, we design a system in this paper. An auditory cognitive control EEG experiment was used to acquire EEG data of the user. We proposed a complete cognitive control process which contains three stages: (sensory stage: 110~140ms, identification stage: 260~320ms, execution stage: 500~700ms). Based on this cognitive process, each EEG sample is divided into three parts. Average amplitude in time domain and LZC (LempelZiv Complexity) was computed for the divided part of each EEG sample and used to extract features from the EEG signal. Optimized SVM was used to recognize the EEG sample. The results show that the union of average amplitude time domain and nonlinear dynamics parameter-LZC with the better recognition accuracy of 99.33%. The experiment result shows that the proposed method can effectively solve the problem of automatic brain cognitive control detection. This study shows for the first time a new pattern recognition problem of cognitive control detection and gives the solution.