Skip to content

Implementation of the models studied in the paper: On the role of features in human activity recognition

Notifications You must be signed in to change notification settings

harkash/on-the-role-of-features-in-har

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 

Repository files navigation

on-the-role-of-features-in-har

Implementation of the models studied in the paper: On the role of features in human activity recognition.

Dataset

The preprocessed dataset can be downloaded from this link. Each of the five datasets (as .mat files) is available inside the corresponding folder. Please refer to data_loader.py for loading the data.

Details coming soon!

  • Pre-processed datasets
  • Autoencoder training and evaluation
    • Vanilla autoencoder
    • Convolutional autoencoder
    • Recurrent autoencoder
  • Supervised (DeepConvLSTM) network training
  • Trained models

About

Implementation of the models studied in the paper: On the role of features in human activity recognition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages