Update (04/03/2023): Ildar Rakhmatulin's PIEEG, an open-source add-on for the Raspberry Pi and compatible single-board computers which adds support for electroencephalograph (EEG), electromyograph (EMG), and electrocardiograph (ECG) sensors, is now available to order in a crowd-funding campaign.
The hardware starts at $250, including shipping, for a four-channel sensor shipping in November this year; a more expensive $350 model offers eight channels and ships at the end of the month.
More details are available on the PIEEG Crowd Supply campaign page.
Original article continues below.
Maker Ildar Rakhmatulin is working to make entry-level brain-computer interfaces affordable and easy to build, designing an open source add-on for the Raspberry Pi family of single-board computers to interface with electroencephalograph sensors: the PIEEG.
"This project is the result of several years of work on the development of BCI [Brain-Computer Interfaces]," Rakhmatulin explains. "We believe that the easiest way to get started with bio-signals is to use a shield."
That's exactly what Rakhmatulin has designed: A board which connects to the general-purpose input/output (GPIO) header of a Raspberry Pi single-board computer and acts as an interface to a head-worn EEG sensor — picking up the minute electrical signals of brain activity and amplifying them for processing on the device.
In theory, the process is simple - but there are a few gotchas. For starters, the Raspberry Pi must be entirely isolated from mains power — meaning you have to run it from a battery, and use a display which is in turn powered by the Raspberry Pi or via a battery. For the best signal, you also have to wear insulated shoes — and real-time readings need a mix of C/C++ for reading the sensors and Python for processing and visualization.
At the same time as the Raspberry Pi add-on, Rakhmatulin is working on bringing the same capabilities to the NVIDIA Jetson Nano range — using a specially-shaped PCB to work around the heatsink which keeps the board's system-on-module cool.
Source code for the project is available on Rakhmatulin's GitHub repository, though promised design files for the hardware have not yet been uploaded — and the whole thing is very clearly marked as a work-in-progress.