An SSVEP based brain computer interface system to control electric wheelchairs

Abstract

Brain-computer interface (BCI) based systems can be used to control external devices by translating a certain set of patterns in the brain signals into actions. An example of this is a BCI controlled wheelchair, with the actions being navigating the wheelchair. In this paper, a Steady State Visual Evoked Potential (SSVEP) based BCI system that controls the operations (forward, reverse, left, and right) of an electrical wheelchair is presented. This system utilizes four LEDs with different flickering frequencies as a visual stimulation source. By providing concentration to these visual stimulation sources, the SSVEP signals are entrained in the occipital and posterior region of the brain. The acquired SSVEP signals are classified into four different frequency ranges representing each of the directions using suitable signal processing algorithms. Based on this classification, a specific control signal is derived to navigate the wheelchair in the desired direction. This system can assist individuals who suffer from neuromuscular degenerative diseases such as Amyotrophic Lateral Sclerosis (ALS), Locked-in Syndrome (LIS), etc., with the navigation of an electric wheelchair using their brain waves. Five peripheral safety sensors are mounted on the wheelchair to avoid the risk of collisions while operating the wheelchair. Once an obstacle is detected by these sensors, a control signal is sent from the Arduino microcontroller to stop the wheelchair. Three experiments were conducted on four subjects to measure the accuracy and reliability of the system. Our results show that the presented system allows the user to navigate to their intended direction with an average accuracy of 79.4%. Also, the safety mechanism incorporated results in an accuracy of 100% obstacle avoidance. Our results show that on average a user can navigate 50 feet set path in approximately five minutes.