Most AI researchers agree the trusty keyboard will not be the preferred human-machine interface of the future. While smart device-based voice interfaces are now increasingly popular, direct, brain-computer interfaces (BCIs) have tremendous potential in terms of speed and efficiency, with possible applications in neuroscience research, medical devices, and even videogames. There are many challenges in enabling BCI as an everyday means of human-computer interaction, one of which is maintaining high precision while reducing device cost.
In the new paper PIEEG: Turn a Raspberry Pi into a Brain-Computer-Interface to Measure Biosignals, PhD electronic researcher Ildar Rakhmatulin and brain-computer interface developer Sebastian Völkl tackle this challenge, open-sourcing an inexpensive, high-precision, easy-to-maintain PIEEG board that converts a Raspberry Pi into a BCI for measuring and processing eight real-time EEG (electroencephalography) signals.
Although BCI research has been promising, the ongoing global chip shortage has increased the cost of ICs and set back the development of full-fledged BCI devices. The researchers also struggled to find software for signal processing in the current market, forcing them to look elsewhere for appropriate methods and tools for reading signals to produce a practical, low-cost BCI device.
The researchers observed that single board computers (SBC) are good at reading signals and suitable for sending data to a desktop computer. Inspired by this, they developed a shield that receives and transmits data to a Raspberry Pi (a cheap and popular SBC introduced in 2012) and wrote clear and simple software that processes data in real-time on it, thus converting the Raspberry Pi into a functional BCI interface.
The proposed device also includes a screen and battery, and, for reading and processing biosignals, eight dry electrodes mounted in a skull cap according to the International 10-20 standard for EEG exams.
The researchers presented encouraging results for real-time PIEEG chewing and blinking artifact detection, and believe their low-cost device will enable machine learning enthusiasts to create projects for controlling robots, unmanned aerial vehicles and mechanical limbs “using the power of thought.” In their next hardware version, they will consider installing gyroscopes and accelerometers to control the position of the object and add shields to protect against external electromagnetic interference.
Author: Hecate He | Editor: Michael Sarazen
We know you don’t want to miss any news or research breakthroughs. Subscribe to our popular newsletter Synced Global AI Weekly to get weekly AI updates.