DIY Stride Analysis driven by Machine Learning to Compare the Next Generation of Running Shoes

 By Medium - 2020-12-24

Description

I wanted to try using machine learning to do a backyard experiment around analyzing running stride. I put together a setup with only my phone, a tripod, treadmill, my laptop, and a fast runner. My…

Summary

  • In a backyard experiment with an Olympic marathoner, the Nike Vaporfly NEXT% showed decreased upper body movement compared to a competing prototype and a regular running shoe I wanted to try using machine learning to do a backyard experiment around analyzing running stride.
  • The third shoe is a prototype made by Li-Ning to directly compete with the Next%.
  • Image by Author The mean distance traveled by the shoulder, wrist and elbow was less in the NEXT% when compared to the Pegasus.
  • The mean elbow distance when wearing the NEXT% was 4.0% less than when wearing the Pegasus (p < 0.001, highly significant).

 

Topics

  1. Ortho (0.44)
  2. Machine_Learning (0.09)
  3. NLP (0.04)

Similar Articles

Data Transformation: Standardization vs Normalization

By KDnuggets - 2021-03-14

Increasing accuracy in your models is often obtained through the first steps of data transformations. This guide explains the difference between the key feature scaling methods of standardization and ...