A hybrid model for EEG-based gender recognition

• DOI: 10.1007/s11571-019-09543-y
• Publication Date: 2019-07-04T15:03:22Z
• Authors: Ping Wang; Jianfeng Hu
• Keywords: Robustness

The gender recognition is an important research field to study evidence regarding some personal characteristics in the information and data society. However, current traditional methods such as vision sound have been exposed their own security weaknesses. Recently, biometric based on Electroencephalography (EEG) signals has widely used safety medical fields. It necessary explore potential of using EEG present a more robust accurate result with larger training sophisticated machine learning approaches. In this contribution, we automated system by hybrid model resting state from twenty-eight subjects. These are useful handy get insights into assessing differences gender. For achieving good performance strong robustness, develops combining random forest logistic regression, employs four common entropy measures analyze non-stationary signals. Result also suggests that achieve improved progress accuracy 0.9982 AUC 0.9926 nested tenfold cross-validation loop, implying show significant applicability proposed approach capable recognizing