Electromyography Hack Chat

Dan Maloney12:06 PM
I'd almost imagine that dry electrodes would help decrease the background noise from other signals in the body, like ECG or just plain EMI noise coupled from the environment.

hut12:06 PM
@anfractuosity yes, I placed electrodes on the Flexor digitorum superficialis muscle and recorded the patterns that arise when I press individual fingers onto the table, and I found distinct patterns in the resulting EMG signal from which you can deduce which finger was used

perlinwarp12:07 PM
@curiousmarc for some implementation details on EMG, I'd recommend reading this: https://www.delsys.com/downloads/TUTORIAL/semg-detection-and-recording.pdf

You get a potential difference from points on the skin and then amplify them commonly using an instrumentation amplifier. The psylink blog also has more great details

curiousmarc12:08 PM
@perlinwarp Thanks, I'm off to the wizard, er, link.

Agnese Grison joined  the room.12:08 PM

hut12:08 PM
@anfractuosity if you look at the video, the electrode module is actually sitting on the flexor digitorum superficialis muscle.

Pete Warden12:08 PM
What kind of algorithms do you need to interpret the signals?

anfractuosity12:08 PM
@hut neat :) would i be right in thinking you'd need a large number of electrodes to monitor each finger simulatenously? they seem to use lots of electrodes unless i'm mistaken?

Dan Maloney12:08 PM
Guess you've got to know your anatomy pretty well. Seems like most people think the muscles for the fingers are actually in the fingers, not in the forearm like they are.

hut12:09 PM
I also tried typing on a keyboard while training the AI, and hoped that I can later type on an invisible keyboard to reproduce the same keys, but unfortunately this worked only when I restricted myself to a small number of keys (2 or 3)

hut12:09 PM
@Dan Maloney yes, I spend a lot of time exploring the forearm :D

pwl.lorenc joined  the room.12:10 PM

the_3d612:10 PM
@anfractuosity that depends on level of detail you want to extract. 5 fingers rough flexion/extension can be done with 5 electrodes (did that myself), but you won't get very high reliability this way

Agnese Grison12:10 PM
@hut Sounds super interesting! Did you just use the raw EMG for training the network or did you find some features that work better?

anfractuosity12:10 PM
it looked to me like they used 20+ i think

anfractuosity12:10 PM
but didn't count properly

hut12:11 PM
@Pete Warden when I started out, I used FFT and various methods of averaging, rolling window sampling, but before digging into signal processing algorithms further, I decided to give it a try to just throw the raw signals into a neural network and let it make sense of it.... and it just works. It's a pretty simple neural network too, with 6 layers and <1000 neurons

perlinwarp12:11 PM
@anfractuosity 8 has been proven to be enough by using the Myo, although some papers suggest you can get away with 4 using some clever ML, e.g. this one: https://dl.acm.org/doi/abs/10.1145/3442381.3449890 , It's also been implemented using the Thalmic Labs Myo to control VR here: https://github.com/PerlinWarp/NeuroGloves

RichardCollins12:12 PM
@hut I designed a 10 finger EMG keyboard in high school, 1024 codes and it is not too hard to learn binary. No motion. One hand, 5 fingers, is 32 symbols, and you can use arm or other places for shift or a three bit modifier. 2^8 is 256 characters. Faster than moving fingers.

Agnese Grison12:12 PM
@hut great thanks! What kind of force feedback did you use for measuring force in flexion and extension? I'm not sure about how sensitive the load cells should be to record the single finger activity..

Pete Warden12:12 PM
@hut neat! I work on TensorFlow Lite Micro, so I'm very interested in neural net approaches

anfractuosity12:12 PM
@perlinwarp , thanks, will have a look!

hut12:13 PM
@RichardCollins that sounds fascinating, do you have a link?

RichardCollins12:13 PM
That was 55 years ago, we still used paper and pencil. I had computers the next few years, but not ones with digital media I could keep.

hut12:14 PM
@Agnese Grison there is no force feedback, PsyLink is only reading signals

AaronA12:14 PM
@hut Love the project! Is very inspirational with trying to develop a workout tracker device that records movements to skip having to enter your rep count and such into a workout tracker.

hut12:15 PM
@AaronA thank you :) you can probably do workout tracking with purely an IMU with gyroscope/accelerometer though

hut12:16 PM
@perlinwarp thanks for the image and the extra information :)

RichardCollins12:16 PM
@hut I was just indicating that one hand dedicated to generating the bulk of the signal was sufficient, then convenient muscles sites on the neck face arms legs toes give you enough to communicate - at speed. When you learn to read fast, the first think it to not subvocalize. The way that works for fingers and typing is to measure any small signal of the "intention" to move the fingers, not the movement itself.

AaronA12:16 PM
I started with that, but feel like recording the muscle contractions is more accurate.

RichardCollins12:18 PM
The ElectroMyoGram signals are voltages. The currents are small so differential amplifiers and high amplifications are needed. But "instrumentation" amplifier chips and systems are widespread. Most don't tell you the signal characteristics.

perlinwarp12:18 PM
@hut You're welcome! Thanks for inspiring the community with such an awesome project, especially for publishing the schematics and code as open-source!

Daren Schwenke12:19 PM
I was about to ask that. if differential signaling is still required with the machine learning.

hut12:20 PM
@Daren Schwenke not necessarily. My first approaches were actually with plugging the electrode straight into the ADC of the microcontroller (arduino nano 33 ble sense), and while the readout is rather noisy, the signal is still detectable. But you get better results with differential amplification

mseinhorst1999 joined  the room.12:20 PM

the_3d612:20 PM
@Daren Schwenke I have rather promising results with single reference and 4 channel electrodes (still running them through buffer opamps, but not instrumentation ones)

hut12:22 PM
@RichardCollins I also want to get to the point where one can detect signals without visible movement. If you did that in high school, then I'm hopeful I'll get there eventually :)

hut12:22 PM
(actually PsyLink might also be able to do this. I haven't tested that recently.)

Preston12:22 PM
@hut lots of interesting research on EMG based detection of subvocalization

anfractuosity12:23 PM
of speech?

Preston12:23 PM
yep

anfractuosity12:23 PM
yeah, that looks really neat too

RichardCollins12:23 PM
A neural net can take noisy input. If you have 15,000 samples per second that is more than enough date to discriminate 1024 codes. I did not see the sampling rate mentioned, nor the bit size, no any recorded data samples for testing and creating algorithms. An open group shares data and algorithms, in near real time.

Daren Schwenke12:23 PM
that sounds like a military contract waiting to happen.

Dan Maloney12:23 PM
@Preston -- Where would the electrodes go for subvocalization? On the neck I'd imagine.

Preston12:24 PM
@Dan Maloney neck and face, look into the 'alter ego' work from the MIT media lab and its derivatives for a promising system

c joined  the room.12:25 PM

hut12:26 PM
@RichardCollins the sampling rate of psylink is 500Hz @ 8 bit, 8 channels. But indeed there's no recorded data published. I can add that to the website

hut12:27 PM
(it could go up to 12 bit, but currently bandwidth over BLE is a concern)

anfractuosity12:27 PM
would wifi use too much power compared to BLE?

hut12:28 PM
I chose BLE specifically because you can use it to emulate a human input device (keyboard or mouse) and connect to e.g. a phone to control it

hut12:28 PM
this has not been implemented yet though

anfractuosity12:29 PM
ah sorry, gotcha

the_3d612:29 PM
@anfractuosity wifi has high peak consumption, you'll need to put more effort in isolating analog schematics from its influence. Not impossible, but not easy as well

anfractuosity12:29 PM
ahh

Daren Schwenke12:31 PM
have you experienced any issues with the radio broadcasts affecting the signals that you have read?

RichardCollins12:31 PM
It helps to break up into "projects". When you try to do all things with all ways of doing those things, almost nothing gets done. And, when I search on topics like EMG there are tens of thousands of groups out there - all mostly trying the same things, and mostly not talking to each other.

Dmitry Sukhoruchkin12:31 PM
what about multichannel EMG? with devices like this https://hackaday.io/project/166893-freeeeg32-alpha15 and this https://hackaday.io/project/181521-freeeeg128-alpha

perlinwarp12:32 PM
And the 33 BLE Sense supports TensorFlow for Micros so hopefully you can process some of the data on the board and reduce what needs sending, but still doesn't solve the bottlenecks for when training or gathering data for ML

hut12:32 PM
@Daren Schwenke not yet, but if you shine a bright lamp on the wires that connect the electrode module to the arduino, the noise goes crazy

Daren Schwenke12:32 PM
the difference between Wi-Fi and BLE I imagine is a an order of magnitude of power.

Daren Schwenke12:33 PM
interesting!

anfractuosity12:33 PM
Am i right in thinking looking at the schematic you're amplifying the difference between two electrodes, on each of your PCBs?

hut12:34 PM
@RichardCollins communication between groups is indeed an issue, wish I knew how to bridge the groups

Dmitry Sukhoruchkin12:34 PM
there 32 differential inputs on FreeEEG32 and 128 differential inputs on FreeEEG128

Thomas Shaddack12:35 PM
there is a possibility, re wifi, to know when it will broadcast and sandwich the packets between the measurements.

hut12:35 PM
@anfractuosity the current electrode module ( https://psylink.me/b3.1/ ) supports 8 electrodes (the big yellow circles) and 4 differential amplifier chips calculate the difference between 2 electrodes each

Dmitry Sukhoruchkin12:36 PM
all with simultaneous sampling, used ad7771 and ads131m08

anfractuosity12:36 PM
cool , the pcb images are v. helpful

Jacob Tong joined  the room.12:36 PM

Daren Schwenke12:37 PM
any thoughts on possibly enhancing your data using something like ultrasound?

RichardCollins12:37 PM
We should have pictures of the things you mentioned floating on these screens. So we can just point to things, and keep adding details. Taking text words and associating them, and going back to earlier mentions is time consuming. @hut A friend of mine's husband broke his neck at C4 and I spent all of October Nov Dec finding all the groups doing 3D imaging of nerve activity, and stimulation of muscles by many methods. Stimulated muscles can substitute for brain control. So take the "intention" and convert directly to the suite and timing of muscles needed to move the body using existing muscles. The weak muscles get put through training to maintain tone and strenght. Same works for micro-g environments in space, mars, moon.

hut12:37 PM
@Dmitry Sukhoruchkin those links sound very interesting, will research that project after the chat :) perhaps we can collaborate

hut12:38 PM