argilium

I’m working on Ovio (https://ovio.au), a record-keeping app for Australian freelancers/sole traders/small businesses. The current version is deliberately narrow: send receipts by email/whatsapp; import bank transactions from CSV; and Ovio extracts the details and auto reconciles. From there you can check a BAS/GST-style summary and export organised records for an accountant.

It's been quite fun building this as this solves my exact problem, but trying to find an audience for a product is a completely different game

Building a simple iOS app that's free (ad supported) for tracking expenses/receipts. Everything out there was subscriptions and I didn't want another monthly expense to track my simple expenses ... http://loomlabs.au/docket

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.

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.

This is part of my honours thesis for my comp-sci degree. Once i've completed that, i'll definitely look at open sourcing.

You're right on the ball. I'm indeed using temporal features to classify, along with various other statistical ones.

The repetition counting in my next aim. Once apple opens up the gyro on the Watch, I think there could be a good chance to get something like this out the door.

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 great accuracy levels. Whilst i'd have to reconstruct a decision tree each time.

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!

That's an interesting point. The problem here would be that video input would not provide accel+gryo motion information, which is what the network needs in order to learn.

If we instead simply used video information to track exercises the problem would be scaling that to consumers. They'd require an external camera to watch them.

But the idea of using Mechanical Turk is quite smart. It'd help me get varied form - especially if I can get them to wear a band/phone that has the sensors.