Cool stuff. Is this open sourced by any chance? Just want to tinker with this a bit
This is part of my honours thesis for my comp-sci degree. Once i've completed that, i'll definitely look at open sourcing.
Recognising gym excerises in real-time using a neural network
21–30 of 31 posts
Re: Recognising gym excerises in real-time using a neural network
#22This might be a good chance to ask something that's been bothering me -- is there a good training log format for weightlifting? I can find apps for recording training data, but they all use their own formats. Anyway, if there is one it would be cool if this program could use it as output, instead of making up its own ad-hoc format.
That's a good question. I'm also quite sick of all the logging apps that have their own unique formats.
If there is a standard out there, I'll definitely look at integrating that for the output.
Re: Recognising gym excerises in real-time using a neural network
#23Here's a problem: I'm pretty sure you'd get just as good (probably superior ) results with a simpler, faster out-of-the-box algorithm like logistic regression, random forests or boosted trees (depending on the amount of data). This just isn't a problem that seems well suited for neural networks. Gyroscope/accelerometer data might seem like the kind of extremely-noisy, high-dimensional data well-suited for neural nets…
You're right that I could get just as good results with other potentially faster algorithms but those algorithms don't afford me the ability (especially decision trees) to personalise. The system is designed to be personalised. So for example if it's not doing well in recognising your squats for instance, you can immediately 'show' it what they look like. A neural network can immediately integrate that, and spit out…
You definitely can use online learning with logistic regression. There are also ways to get it to work with random forests / boosted trees.
Re: Recognising gym excerises in real-time using a neural network
#24Here's a problem: I'm pretty sure you'd get just as good (probably superior ) results with a simpler, faster out-of-the-box algorithm like logistic regression, random forests or boosted trees (depending on the amount of data). This just isn't a problem that seems well suited for neural networks. Gyroscope/accelerometer data might seem like the kind of extremely-noisy, high-dimensional data well-suited for neural nets…
I agree and disagree. I would definitely start with a simpler algorithm like logistic regression or even trees and use temporal features like power at different frequencies by taking an FFT. I would even add time lagged features. After that I'd graduate to a single hidden layer MLP. If I had tons of data (a lot of different people using it), I'd experiment with LSTM neural networks because I think the temporal inform…
I'm still pretty sure you'd get superior results with other standard techniques for time series data (HMMs, conditional random fields, etc.). You really need a crapload of data to train an RNN well.
Re: Recognising gym excerises in real-time using a neural network
#25Earlier quoted context omitted.
You're right that I could get just as good results with other potentially faster algorithms but those algorithms don't afford me the ability (especially decision trees) to personalise. The system is designed to be personalised. So for example if it's not doing well in recognising your squats for instance, you can immediately 'show' it what they look like. A neural network can immediately integrate that, and spit out…
You definitely can use online learning with logistic regression. There are also ways to get it to work with random forests / boosted trees.
I never even considered logistic regression for this problem. Now that you've pointed it out, I'm going to look into.
Neural networks aren't really core part of the system. As long as I can get good + quick results, I'm really open to swapping out the learning algorithm.
Re: Recognising gym excerises in real-time using a neural network
#26This might be a good chance to ask something that's been bothering me -- is there a good training log format for weightlifting? I can find apps for recording training data, but they all use their own formats. Anyway, if there is one it would be cool if this program could use it as output, instead of making up its own ad-hoc format.
That's a good question. I'm also quite sick of all the logging apps that have their own unique formats. If there is a standard out there, I'll definitely look at integrating that for the output.
Thanks! If you find one ping me, I'll do the same.
Re: Recognising gym excerises in real-time using a neural network
#27And this what happens when you bring a Computer Scientist into the gym! One question: how well would a neural network recognize a more complex and involved exercise like Kettlebell Turkish Getup compared to an exercise with simple movement like Push-ups?
That's a good question! Turkish Getup's are very complex like you say. Given my current setup and window length, it's unlikely that it'll recognise them, because one rep is very long. Maybe if I did exercise based window lengths it could work better? I'm honestly not sure. But that is something to try out!
To be honest, a human seeing it for the first time would have a hard time identifying Turkish Getups too :)
Also, identifying good form--that's an app that could help a lot of amateur athletes.
Re: Recognising gym excerises in real-time using a neural network
#28Actually thought about an app that would do this on a smartwatch. I would definitely buy a smartwatch if I could have this level of accuracy of body movement tracking.
Hi. FocusMotion here. You you download and play with our SDK that works on any wearable device with an open accelerometer (Apple Watch, Android Wear, Microsoft Band, Pebble). We track 50 exercises, auto classify 22, and there's a machine learning tool that let's you add new movements to the system and improve it over time.
www.focusmotion.io
Re: Recognising gym excerises in real-time using a neural network
#29Cool stuff. Is this open sourced by any chance? Just want to tinker with this a bit
Not truly open, but we have an SDK similar to this that you can play with.
It works with any open accelerometer (Apple Watch, Android Wear, Microsoft Band, Pebble). We track 50 exercises, auto classify 22, and there's a machine learning tool that let's you add new movements to the system and improve it over time.
www.focusmotion.io
Re: Recognising gym excerises in real-time using a neural network
#30Cool stuff. Is this open sourced by any chance? Just want to tinker with this a bit
Not truly open, but we have an SDK similar to this that you can play with. It works with any open accelerometer (Apple Watch, Android Wear, Microsoft Band, Pebble). We track 50 exercises, auto classify 22, and there's a machine learning tool that let's you add new movements to the system and improve it over time. www.focusmotion.io
Ok. I'll try it. Does this have a NodeJS SDK?