Brain-computer interface is a device that takes neural signals and transforms them to digital signals. The Computers can use these digital signals for multiple purposes. In this paper a novel brain-computer interface based on the gaze on rotating vane independent EEG signal is proposed. Classification of EEG signal in two forms of rotating vane when vane rotates fast and when it rotates slow, was done. All the signals were obtained at the Department of Electrical and Electronics Engineering Karadeniz Technical University from three healthy human subjects in age groups between 25 and 32 years old. Principle Component Analyze were used to extracted feature vectors and classified by k-nearest neighbor algorithm. The proposed method was implemented to the data sets and achieved a good average classification on the test data.