Active hand training system and method based on brain-computer interaction and deep learning

The invention discloses an active hand training system and method based on brain-computer interaction and deep learning. The active hand training system comprises an electroencephalogram cap, an FPGAacquisition device, an image stimulation module, an upper computer and a hand movement support; the electroencephalogram cap and FPGA acquisition equipment are used for acquiring a motor imagery electroencephalogram signal of a testee, carrying out preprocessing operation and wirelessly transmitting the pretreated signal to the upper computer; the image stimulation module generates corresponding motion visual prompts according to the training items so as to prompt the testee to perform imagination of corresponding action; meanwhile, after receiving the electroencephalogram signal, the upper computer decodes the electroencephalogram signal and generates a corresponding control signal; and the hand movement support receives the control signal to pull the hand of the testee to move, and corresponding training is comp