In the studies for safe driving, data from sensors and methods using psychological parameter values have been developed. Unlike these methods, electroencephalogram (EEG) signals and driving assistant development work can be detected as instant decisions on driving status. In this study, the acceleration and deceleration of the accelerator pedal were determined by using the EEG signals. For this estimation process, EEG data of 18 different drivers were analyzed by Welch method. The power density values of the delta, theta, alpha and beta frequency bands obtained as a result of the analysis were applied to the artificial neural network model as the features of the EEG signals. When the test data were applied to the trained network, an accuracy of 83% was estimated.