A brain computer interface (BCI) is a device that lets people with motor or cognitive limitations to control computers and other devices. BCIs make use of different combinations of sensors, recording methods, signal-processing algorithms, and machine learning to translate brain signals into operating commands. They can be used to control a diverse range of devices, ranging from cursors on computer screens to 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 presence of neuronal activity and software transforms them into operating commands.
In a variety of BCI systems the user must go though an iterative training process to understand how to create signals that are recognized by the system. For example in a BCI that is specifically designed to type letters the user will have to imagine moving his or her right or left hand.
The most exciting BCI innovations involve implantable or surgical systems that record directly from neural tissue instead of the scalp. These devices are more accurate than non-invasive BCIs but require surgery and pose some risks.
Invasive BCIs are still in the very about his early stages of testing and it is essential that patients who undergo this procedure fully are aware of the potential dangers and benefits of this procedure. Privacy and data security are also a major concern, since BCIs read neural signals, which could contain sensitive behavioral or health information. Some people are against the technology because they fear that hackers could hack into their minds and influence them.