CRGFFNet: an adaptive inter-channel relation guided feature fusion network for enhanced EEG personality recognition

Objective.Personality recognition holds significant potential in fields such as clinical psychology and human-computer interaction. Despite the promising performance of electroencephalography (EEG)-based personality recognition, its advancement is still limited by insufficient exploitation of the intrinsic spatial topology and ineffective multi-dimensional feature fusion of EEG signals. To overcome these challenges, this paper proposes an adaptive inter-channel relation guided feature fusion network (CRGFFNet) comprising two innovative integrated components. The spatial proximal-channel-reordering algorithm formulates full-channel ordering as a traveling salesman problem solved viaQ-learning to preserve the 3D spatial topology while attenuating high-frequency noise. Moreover, the spatio-temporal-frequency hybrid convolutional feature augmentation (STFA) module employs orthogonal strip convolutions to explicitly decouple temporal and spatial dynamics, and parallel max/average pooling to separate high- and low-frequency components. Outputs from the STFA module are then used as input embedding to a Transformer encoder, thereby enabling modeling of global contextual relationships across the entire sequence. To validate the proposed model, a 64-channel EEG dataset was collected from 22 subjects while they were exposed to happy, calm, and sad emotional stimuli. Each subject was then annotated according to the Big Five personality traits. Experimental results demonstrate that CRGFFNet achieves strong performance on our dataset, attaining an average accuracy of 89.94% across all personality dimensions and outperforming existing methods in our experiments.