Decoding EEG Signals Both During and After Offset of Small and Short-Time Visual Target Stimulus

Conventional visual target detection with EEG signals has been experimented by exposing target objects that are large enough to be noticed without searching on visual image in order to average their corresponding responses such as event-related potentials (ERPs) to raise signal-to-noise ratio. Recent studies turn attention to decoding single-trial ERPs, while their experiments still minimize target object search time. In this paper, we studied the temporal aspects of target recognition of human brain including target object search by introducing the concept of semi-targets that are features posterior to offset of target visual stimuli, and applying it into a type of contrastive learning, Triplet MatchNet. The results showed that features five seconds posterior to target visual stimuli help increase in performance of EEG decoding.