Drone Movement Control by Electroencephalography Signals Based on BCI System

Abstract

Brain Computer Interface enables indi- viduals to communicate with devices through Elec- troEncephaloGraphy (EEG) signals in many applica- tions that use brainwave-controlled units. This paper presents a new algorithm using EEG waves for control- ling the movements of a drone by eye-blinking and at- tention level signals. Optimization of the signal recog- nition obtained is carried out by classifying the eye- blinking with a Support Vector Machine algorithm and converting it into 4-bit codes via an artificial neural network. Linear Regression Method is used to cate- gorize the attention to either low or high level with a dynamic threshold, yielding a 1-bit code. The con- trol of the motions in the algorithm is structured with two control layers. The first layer provides control with eye-blink signals, the second layer with both eye-blink and sensed attention levels. EEG signals are extracted and processed using a single channel NeuroSky Mind- Wave 2 device. The proposed algorithm has been vali- dated by experimental testing of five individuals of dif- ferent ages. The results show its high performance compared to existing algorithms with an accuracy of 91.85 % for 9 control commands. With a capability of up to 16 commands and its high accuracy, the algorithm can be suitable for many applications