The Operator's Selection Method for Human-Machine Interaction Using Independent Event-Related Synchronization

In complex real-world environments, unmanned systems often struggle to achieve coordinated control through independent autonomous algorithms and traditional manual operations. Human-machine interaction (HMI), by decoding brain intentions, directly deliveries control to unmanned devices, effectively integrating the system with the human brain into a cohesive unit. Despite significant research focusing on the development of pattern recognition and system control methods, selecting high-quality human operators and providing them with suitable training protocols are essential for achieving high-precision control and low-mental load monitoring. In this paper, we propose a representation model based on independent event-related synchronization to investigate the neurophysiological basis of HMI performance variation. Our results demonstrate that the model could significantly highly account for variations in HMI performance, with an adjusted R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.863. The three-graded training protocols for candidates were also provided according to the model. The proposed model is valuable for selecting excellent operators and recommending personalized training protocols for other candidates, thereby enhancing the stability and effectiveness of HMI.