Hacker News new | ask | show | jobs
by mmachlin 4903 days ago
Hi guys. This is my new startup. I'm happy to answer any questions that you may have about it.
3 comments

In your calibration tests against GPS, what sort of error do you see after 500 miles of accelerometer data?
Initial test showed over 95% accuracy, and we are working on make it even better. On one hand it's not intends to be instead of your GPS to count each and every run mileage, even though you can. BTW, it will clearly count also treadmill runs, while a GPS will not...
After training on three five mile data sets, I was able to get very accurate speed/distance estimates for subsequent runs (say 99%+).

The method? 1st derivative of accelerometer data to determine cadence. Then correlate cadence with actual speed with a simple linear regression when GPS data was available.

This was more intended for dead reckoning on a wrist mounted device, though. We had a 3 axis accelerometer and a 3 axis magnetometer.

How waterproof is it? Will it survive an absent-minded trip in my washing machine after a muddy run?
it is waterproof for rain/snow/storm, but it is not built for swimming :-)
Would it be possible to have a future iteration that can survive the Scylla and Charybdis of washing machines?

I literally just remembered that I forgot to move my Nike+ sensor the last time I washed my shoes.

What challenges did you face (I am sure you did) to make this low cost?