Brain Controlled Wheelchair: System Description and Fuzzy Almost Nearest Neighbors Classification

The brain-computer interface is a complex system that allows one to control external electronic devices using brain activity. This system includes several elements - a device for reading brain activity signals, a hardware and software complex that processes and analyzes those signals, as well as a set of controlled devices. The main challenge here is the development of methods and algorithms that can correctly recognize and predict the intentions of the person who uses this interface to provide solutions to control problems. This paper describes the mathematical formulation of the equipment control problem as well as the methods for preprocessing EEG signals, analyzing them and taking decisions about control signal. The structure of the software implementation of these methods is described and the plan for experimental testing of the performance of the entire system that forms the brain-computer interface is presented. For classification of EEG signals, a modification of the k-nearest neighbors method called “fuzzy almost nearest neighbors method” is proposed to allow for a weaker dependence of the results on the choice of the parameter “k”.