EEG-Based Age and Gender Prediction Using Deep Neural Network

Brain-computer interfaces (BCIs) have witnessed remarkable progress and are finding applications in diverse domains. This research paper introduces a novel application of BCI technology, focusing on the prediction of age and gender via EEG analysis using Deep CNN and ResNet models. A widely adopted EEG recording device was employed to capture cerebral activities from 64 subjects, encompassing both male and female participants, in a comfortable situation with eyes closed and eyes opened. The CNN model achieved an accuracy of 99.8% for age classification and 99.93% for gender classification. On the other hand, the ResNet model attained an accuracy of 99.05% for age and 99.32% for gender classification. Furthermore, our analysis indicates that utilizing all channels of the EEG signals yields superior performance in predicting age and gendercompared to brain regions.