At first, we would think that being able to control machinery and certain devices via sending signals from the brain is fictional. But in a recent report in Nature Machine Intelligence, researchers from Georgia Institute of Technology may have taken a step forward to doing that.
Currently, brain-machine interface, or BMI, is already in use. However, its use employs electroencephalography, or EEG, signals connected to a bulky and complex apparatus. But by combining artificial intelligence with engineering of flexible electrodes, the researchers have extended the capabilities of existing BMI technologies.
The device features a high resolution EEG monitoring system in a miniature flexible sensor. Here, EEG signals are sent from the brain to a tablet computer that is as far as 50 feet, or 15 meters, from the user. To put this together, the team used three main components. First of the three is a set of hair-mounted electrodes that are made to be in direct contact with the user's scalp. Second is a nanomembrane electrode. And lastly, a flexible circuitry equipped with a Bluetooth telemetry unit.
Principal researcher and Georgia Institute of Technology School of Mechanical Engineering and Department of Biomedical Engineering professor, Woon-Hong Yeo, compared their device with traditional once. "Typical EEG systems must cover the majority of the scalp to get signals, but potential users may be sensitive about wearing them," said Yeo in a statement. "This miniaturized, wearable soft device is fully integrated and designed to be comfortable for long-term use."
In a set of tests with six people without disabilities, the device was able to control an electric wheelchair, a small robotic vehicle, and a display system. This was done without a physical controller like a mouse or a joystick.
Right now, the system is composed of three elastomeric scalp electrodes that are attached onto the head of the user with a head band made of fabric, a set of wireless electrodes attached to the back of the neck, and another electrode attached below one ear. In the future, the team hopes to improve the physical connection of the device to further make it compact. "Future study would focus on investigation of fully elastomeric, wireless self-adhesive electrodes that can be mounted on the hairy scalp without any support from headgear," explained Yeo, "along with further miniaturization of the electronics to incorporate more electrodes for use with other studies."