AUTHOR=Zhang Bingxue , Zhuge Yuyang , Yin Zhong 

TITLE=Design and implementation of an EEG-based recognition mechanism for the openness trait of the Big Five

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.926256

DOI=10.3389/fnins.2022.926256

ISSN=1662-453X

ABSTRACT=The differentiation between the openness and other dimension of the Big Five personality model indicated that it was necessary to design a specific paradigm as the supplement of the Big Five recognition. The present study examined the relationship between one’s openness trait of the Big Five model and the task-related power change of upper alpha band (10-12 Hz). We found that individuals from high openness group displayed a greater task-related power changes of alpha band in symbolic reasoning task, while the reverse applied in deductive reasoning task. These results indicate that these two kinds of reasoning tasks could be used as the supplement of the Big Five recognition.
Further, we divided one’s openness score into three levels, and proposed a hybrid-SNN (Spiking Neural Networks)-ANN (Analog Neural Networks) architecture based on EEGNet to recognize one’s openness level, named Spike-EEGNet. The recognition accuracy was 90.6% and 92.2% on two tasks. In order to retest the robustness of Spike-EEGNet on EEG classification task, we retested our model on DEAP dataset and achieved an accuracy rise of 2.4%, compared with the original EEGNet. This result is highly significant for the validation of using a model with hybrid-SNN-ANN architecture for EEG classification tasks.