Decoding covert visual attention based on phase transfer entropy

Covert attention to spatial and color features in the visual field is a relatively new control signal for brain-computer interfaces (BCI). To guide the processing resources to the related visual scene aspects, covert attention should be decoded from human brain. Here, a novel expert system is designed to decode covert visual attention based on the EEG signal provided from 15 subjects during a new task based on a change in lumination to two blue and orange color on the right and the left side of the screen, which is evaluated in two cases of binary and multi-class systems. For the first time, Phase transfer entropy (PTE) has been used in these systems, and after selecting the optimal decoding feature, the frequency band (8-13 Hz) Alpha and Beta1 (13-20 Hz) have the best performance compared to other frequency bands. Two-class classification accuracies of the designed system in two frequency bands (Alpha and Beta1) are 91.87% and 89.53%, respectively. Also, the accuracies are 65.11% and 63.38% for multi-class classification in specified frequency bands. In these frequency bands, the parietal and frontal lobes showed the most significant difference in comparison to the other lobes. Also, the obtained results declared that the expert system's performance in the Alpha band by the extracted features from the Posterior region is better than all frequency bands in other different brain regions. The performance of the proposed expert system by PTE is significantly better than the previous phase synchronization based features. Results have shown that the PTE feature performs better than the common methods for decoding covert visual attention.