[HN Gopher] Turning AirPods into a fitness tracker
       ___________________________________________________________________
        
       Turning AirPods into a fitness tracker
        
       Author : cleverbit
       Score  : 117 points
       Date   : 2024-05-03 17:16 UTC (2 days ago)
        
 (HTM) web link (richarddas.com)
 (TXT) w3m dump (richarddas.com)
        
       | lazerjesus wrote:
       | is the app going to be released?
        
         | zackify wrote:
         | I was expecting to see the download link in the post too!
        
           | cleverbit wrote:
           | Thanks! I'll post it soon, stay tuned!
        
         | ulf-77723 wrote:
         | +1 for release. Strava Sync would be great - but keep it simple
        
           | cleverbit wrote:
           | Simple is the hardest thing. I'll look into Strava Sync and
           | see what I can do!
        
         | cleverbit wrote:
         | I was curious to see if there'd be interest, but I'll open
         | source the code and release the app soon!
        
           | _Microft wrote:
           | If you are planning to submit this here then you can do a
           | ,,Show HN:" post which makes it clear that this is something
           | you created yourself.
        
             | cleverbit wrote:
             | Will do, and thanks for the tip! The more you know! ;)
        
       | photonbucket wrote:
       | Feels like something Apple might want to do a first-party version
       | of
        
         | cleverbit wrote:
         | thanks
        
       | _Microft wrote:
       | Is this data that could be fed into the Health app (type of
       | training, time of training, repetitions, duration of training)?
       | The Health app is relatively picky about what sports are
       | supported though...
        
         | cleverbit wrote:
         | That's a great idea. HealthKit doesn't track anything at the
         | granularity of the number of reps, and while it doesn't have a
         | workout type specifically for pushups, this could probably be
         | classified as Strength Training. I'll add it!
        
           | _Microft wrote:
           | Maybe there are other exercises with similar motion (squats?)
           | that you would like to support as well? Great idea to use
           | these sensors and I also like the idea of providing audio
           | feedback btw.
        
             | ok_dad wrote:
             | A cool complex one would be burpees.
        
               | cleverbit wrote:
               | Love it! Yeah great idea!
        
       | ttul wrote:
       | I'd love to see whether you could tease out heart rate and
       | respiration from this data. If you already wear an Apple Watch or
       | Fitbit, that data is continually collected. Shoving everything
       | into a time series model with enough samples might do the trick.
        
         | cleverbit wrote:
         | I'll see what I can do, thanks for the feedback!
        
       | dameyawn wrote:
       | Train AI had some time ago added AirPods (in addition to Apple
       | Watch and phone) to their automated workout tracking:
       | https://trainfitness.ai/
        
       | w10-1 wrote:
       | I've considered using CoreMotion data from AirPods to recognize
       | at least yes/no head-shaking, but mainly targeting a vigorous
       | shake in order to mute without hands or voice. An open-source
       | example would be a great starting-point!
        
       | kejaed wrote:
       | Thanks for this, I've wondered if AirPods data could help me
       | track if I'm grinding my teeth, I'll dig in now!
        
       | riffic wrote:
       | there's a whole lot of compute in those little cans. the case
       | does too if I'm not mistaken.
        
         | cleverbit wrote:
         | The amount of engineering that goes into these things is truly
         | phenomenal, as highlighted by the CT scans done by Lumafield -
         | check it out here:
         | https://youtu.be/kRpIg23qGY8?si=r2t8_8VHVCwkDDLP
        
       ___________________________________________________________________
       (page generated 2024-05-05 23:00 UTC)