We don’t see lots of EMG (electromyography) projects, in spite of exactly how awesome the applications can be. This may be since of technical difficulties with seeing the small muscular electrical signals amongst the noise, it might be the problem of translating any type of signal you do find. Regardless, [hut] has been striving forwards with a stream of prototypes, culminating in the aptly named ‘Prototype 8’

The present prototype utilizes a primary power board holding an Arduino Nano 33 BLE Sense, in addition to a improve converter to pump up the AAA battery to supply 5 volts for the Arduino as well as a choice of linked EMG amplifier units. The EMG sensor is based around the INA128 instrumentation amplifier, in a quite simple configuration. The EMG samples together with data from the IMU on the Nano 33 BLE Sense, are passed along to a linked PC by means of Bluetooth, running the PsyLink software application stack. This is based on Python, utilizing the BLE-GATT library for BT comms, PynPut handing the PC input gadgets (to emit keyboard as well as mouse events) as well as tensorflow for the maker discovering side of things. The concept is to utilize maker discovering from the EMG data to partner with a certain individual interface event (such as a keypress) as well as with a bit training, be able to play games on the PC with just hand/arm gestures. IMU data are utilized to augment this, however in this demo, that’s not absolutely clear.

An earlier prototype of the PsyLink.
All hardware as well as software application can be discovered on the job codeberg page, which did make us double-take as to why GnuRadio was being used, however believing about it, it’s truly great for signal processing as well as visualization. What a great idea!

Obviously there are lots of other utilize situations for such a EMG managed input device, however who doesn’t want to play Mario Kart, you know, for science?

Checkout the demo video (embedded below) as well as you can see for yourself, just be conscious that this is streaming from peertube, so the video may be a bit choppy depending upon your regional peers. Finally, if Mastodon is your cup of tea, here’s the link for that. earlier jobs have attempted to dip into EMG before, such as this Bioamp board from Upside Down Labs. likewise we dug out an earlier tutorial on the subject by our own [Bil Herd.]