Brain-Controlled Robotic Arm Based on Adaptive FBCCA

Abstract

The SSVEP-BCI system usually uses a fixed calculation time and a static window stop method to decode the EEG signal, which reduces the efficiency of the system. In response to this problem, this paper uses an adaptive FBCCA algorithm, which uses Bayesian estimation to dynamically find the optimal data length for result prediction, adapts to the differences between different trials and different individuals, and effectively improves system operation effectiveness. At the same time, through this method, this paper constructs a brain-controlled robotic arm grasping life assistance system based on adaptive FBCCA. In this paper, we selected 20 subjects and conducted a total of 400 experiments. A large number of experiments have verified that the system is available and the average recognition success rate is 95.5%. This also proves that the system can be applied to actual scenarios. Help the handicapped to use the brain to control the mechanical arm to grab the needed items to assist in daily life and improve the quality of life. In the future, SSVEP’s adaptive FBCCA decoding algorithm can be combined with the motor imaging brain-computer interface decoding algorithm to build a corresponding system to help patients with upper or lower limb movement disorders caused by stroke diseases to recover, and reshape the brain and Control connection of limbs.