Classification of Cognitive Fatigue with EEG Signals

• Published in: 2020 Medical Technologies Congress (TIPTEKNO) pp. 1 - 4
• Main Authors: EKIM, Ayse, AYDEMIR, Onder, DEMIR, Mengu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19-11-2020
• Subjects: Brain modeling; Cognitive Fatigue; Electroencephalography; Fatigue; Fractals; Higuchi Fractal Size; Katz Fractal Size; Sun; Support vector machines; Task analysis
• ISSN: 2687-7783
• DOI: 10.1109/TIPTEKNO50054.2020.9299239

Cognitive fatigue is the natural result of longtime mental effort during the execution of a high mental workload or a strenuous task. This situation often leads to decreased productivity and increased security risks. In this study, it was aimed to detect cognitive fatigue quickly and accurately, regardless of subjective data. CogBeacon dataset was used for this. Data that make up the CogBeacon dataset were collected from 19 participants in 76 sessions with the help of a 4-electrode MUSE electroencephalography (EEG) device. The collected raw EEGs were randomly separated and feature extraction was performed. Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) algorithms were used in the classification process. Katz and Higuchi Fractal Dimension, standard deviation, median, variance and covariance were tested as features. When the classification was made with SVM, the education average was 93.99% and the test average was 83.14%. The average success rate increased between 4.43% and 7.40%, compared to the trials that were not used in the trials where Fractal Dimension features were used. When the classification was made with KNN, the education averange was 91.71% and the test average was 83.34%. The average success rate increased between 5.10% and 8.92% compared to the trials that were not used in the trials in which Fractal Dimension features were used.