A brain computer interface (BCI) is a device that lets those with cognitive or motor disabilities to control computers or other devices. BCIs utilize a variety of sensors, recording techniques, signal-processing algorithms, and machine learning to convert brain signals into operating commands. They can control a variety of devices, including cursors on computer monitors as well as wheelchairs and robotic arms.

Most BCIs measure activity from the scalp, such as electroencephalographic (EEG) or functional near-infrared imaging (fNIRS) signaling. The signals are recorded by a device that detects the activity of neurons. Software converts them to operating commands.

In a variety of BCI systems, the user is required to undergo an iterative education process to understand how to create signals that are recognized by the system. For instance, in a BCI that is specifically designed to type letters the user will have to imagine moving their left or right hand.

The most exciting BCI innovations involve implantable or invasible systems that record on the neural tissue, instead of the scalp. These about his devices are more precise than non-invasive BCIs but require surgery and have some risks.

Invasive BCIs are still in the very early stages of testing and it is vital that patients who undergo this procedure are aware of the potential dangers and benefits of this technology. Privacy and data security are also major issues, because BCIs read neural signals, which could contain sensitive behavioral or health information. Some people are not a fan of BCIs because they fear that hackers can gain access to their minds and take control of them.