The study was published on August 8, 2026 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering. The developed brain-computer interface hardware-software complex can function on the basis of both synchronous and asynchronous paradigms, designed for introduction into various control loops of complex human-machine systems. The hardware includes an electroencephalography (EEG) signal recording board as well as a neural headband with sensor electrodes. The Cyton EEG signal registration board is the key hardware component—an 8-channel device compatible with the OpenBCI platform and designed for high-precision registration of brain biopotentials as well as signals of heart and muscle activity.
The software was developed in Python and enables recording of EEG signals, preprocessing electroencephalography signals for both synchronous and asynchronous interfaces, classification of EEG data, and generation of control signals to robotic devices. A fully connected artificial neural network model (Multi-Layer Perceptron) was employed for EEG data classification. In synchronous mode, the P300 component achieved approximately 60% recognition accuracy, while in asynchronous mode, binary classification of motor imagery (imaginary left and right hand movements) achieved 65% accuracy. The system allows operators to work without preliminary training. The researchers noted that this system opens prospects for introducing brain-computer interfaces into critical technological processes requiring high reliability of human-machine interaction. Future development aims include improving classification accuracy, expanding the number of recognizable commands, and optimizing hardware for mobile applications.