Environment control is one of the critical difficulties for handicapped individuals who experience the ill effects of neuromuscular ailments. Brain-computer interface systems empower a subject to communicate with a PC machine without drawing down any solid action. This communication does not depend in light of any ordinary medium of correspondences like physical movement, talking, and motion and so forth. The most vital desire for a home control application is high accuracy and solid control. In this study, row-column–based (2 Row, 3 columns) P300 paradigm for home appliances control was designed. In this article, we analyze real-time EEG data for P300 speller using support vector machine and artificial neural network for high accuracy. Using this proposed method we are able to find the target appliance in the correct and fastest way. Four paralyzed people were participating in this study. The artificial neural network gives 85% accuracy within 10 flashes. The results show this paradigm can be used to select the option of a home appliances control application for paralyzed people with users convenient and reliable.
Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain–computer interface: three-class classification of rest, right-, and left-hand motor execution
