Using Machine Learning to predict the type of exercise from movement data
NEW: Architekkt - Swift Dependecy Graph Visualizer for your iOS or macOS Codebase. Check it out on Architekkt.io
Check out my blog post.
Exermote is a fitness app prototype, which is capable to detect Burpees, Squats and Situps and to count related repetitions. The exercise recognition is done with Convolutional LSTM Neural Networks.
It will take some time until .gif is loaded. Have a look on youtube for the raw video with sound.
The project is divided into following steps:
Checkout links for further documentation.
Testmote was released to the AppStore as a side product of this project.