BrainÂcomputer interfaces (BCIs) enable users to control devices with electroencephalographic (EEG) activity from the scalp or with singleneuron activity from within the brain. Both methods have disadvantages: EEG has limited resolution and requires extensive training, while singleneuron recording entails significant clinical risks and has limited stability. In the light of these problems, the electrocorticographic (ECoG) signals recorded from the surface of the brain can enable users to control a onedimensional computer cursor rapidly and accurately. The classification MATLAB experiment of themotor imagery of the left little fingure and the tongue has reached a high classification accuracy of 94%. This result reveals that compared to the EEG signals, ECoG signals can accurately locate the function cortex and avoid the changes of amplitude, frequency and phase at the same time. In addition, our results suggest that an ECoGbased BCI could provide for people with severe motor disabilities a nonmuscular communication and control option that is more powerful and effective than EEG-based BCIs in the two- dimensional joystick movements.