Quantified self for sports performance

presentation for first SF quantified self meetup

Transcript

1. A quantitative approach to
   athletic performance
   Sebastian Ortiz
   

   View Slide

2. Overview
   • What I’ve been tracking and why
   – Weight (withings, DIY scale)
   – Calorie/food intake (fatsecret)
   – Experiments (meal timing, iso-caloric IF)
   • Some tools I have used along the way
   – Pandas,matplotlib
   – D3
   – Numerous OAuth accessible APIs
   • Extras
   – Video tracking of skills
   – Devices for instantaneous feedback
   

   View Slide

3. Weight tracking (1st iteration)
   • DIY wireless scale
   – 24 bit AD7799 ADC
   – RN41 bluetooth serial module
   – At90usb162 microcontroller
   – Power switching logic (battery life 9-10 months)
   

   View Slide

4. DIY wireless scale
   

   View Slide

5. View Slide

6. High-tech assembly techniques
   

   View Slide

7. Why measure?
   • Consciously/subconsciously change behavioral
   patterns
   • Discover long term trends
   • Quantify effectiveness of actions
   

   View Slide

8. Subconscious effects
   • Tracking weight even without consciously
   trying to alter it results in measurable change.
   

   View Slide

9. View Slide

10. Long term trends
    

    View Slide

11. Experiment (meal timing)
    

    View Slide

12. pandas
    • Perfect for time series data
    • Aligns/resamples unequally sampled time
    series for comparison
    • Rolling window functions for visualizing trends
    • Nice similarities to R, dataframe,etc.
    

    View Slide

13. matplotlib
    • Easy to use, mature state of development
    • Integrates seamlessly with pandas
    

    View Slide

14. d3.js
    • Can produce pretty results
    • Simple compared to raw SVG, but still fairly
    involved compared to matplotlib
    

    View Slide

15. API hacking
    • Withings
    • Fatsecret
    • Fitbit
    • Instagram
    • Flickr
    • Python code available here:
    – https://github.com/trtg
    – Writeups (in progress) at my octopress blog here:
    • http://trtg.github.com/
    • Older projects here: http://www.keyboardmods.com
    

    View Slide

16. Realtime feedback
    • http://www.keyboardmods.com/2012/01/gy
    mnastics-tap-swing-trainer.html
    

    View Slide

17. Questions?
    

    View Slide