In this paper a novel brain-computer interface based on the gaze on rotating vane using five channels of EEG signal is proposed. Classification of EEG signal is done in three sessions: 1-when vane rotates fast and slow in an anti-clockwise manner, 2-when vane rotates slow in a clockwise and rotates fast in an anti-clockwise manner, 3-when vane rotates slow in a clockwise and rotates slow in an anti-clockwise manner. The signals were obtained from seven healthy human subjects in age groups between 25 and 32 years old. Discrete Wavelet transform (DWT) were used to extracted feature vectors. The features classified by two classifiers, k-nearest neighbor (k-NN) algorithm and Linear Discriminant Classifier (LDC). Our results demonstrated that LDC was more accurate compared to k-NN. Analysis was carried out using MATLAB Software.