Assessing the Capture of SSVEP Components from EEG Signals for Efficient Target Detection

BCI(Brain computer Interface)is a remarkable technology which develops a direct link within the human brain with anexternally installed device, like ascomputer or a prosthetic limb. By enabling this direct communication, BCIs have the potential to completely transform our interaction with technology, opening up new possibilities and applications. Imagine being able to control devices, play video games, or even write an email, just by using your thoughts. It’s like having telekinetic powers but without the need for any physical movement. SSVEP-based BCIs have been used in various applications, including communication systems for individuals with disabilities. This paper introduces a novel method for capturing SSVEP components from EEG signals named as AO (Adaptive and optimized)-SFCE (spatial Filtering aware component filtering) - AO-SFCE. In this study, we explore methods for target identification through EEG analysis. The execution of the proposed AO-SFCE model is evaluated using a MAMEM SSVEP dataset. The obtained results are presented in terms of detection accuracy and Information Transfer Rate (ITR), and they are compared with different SSVEP acquisition methods. Across all 11 subjects, the mean target detection accuracy and ITR using the proposed AO-SFCE model are found to be ${9 3 . 4 8 \%}$ and 308.23 bpm, respectively.