No description, website, or topics provided.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
GRCNN.py
LICENSE
README.md
models.py
utils.py

README.md

Grouped Convolutional Neural Networks

A simple tensorFlow implementation of the paper,

Grouped Convolutional Neural Networks for Multivariate Time Series, Subin Yi, Janghoon Ju, Man-Ki Yoon, and Jaesik Choi, 2017.

* Code for the Section 3.1 is included only and the Section 3.2 is not implemented here.

Dependencies

  • tensorflow>=1.0
  • numpy
  • scipy
  • pandas
  • matplotlib

Train & Test

You should have your data and cluster index in .csv files.
The data should be in (time_step, feature) shape where time_step is the length of the time series data and feature is the number of features.
The cluster should be in (feature) shape where each element has the index to the cluster in which the feature belongs to.

LICENSE

MIT License

Contacts

Subin Yi (yisubin0202@gmail.com)
Janghoon Ju (wnwkdgns@gmail.com)
Jaesik Choi (jaesik@unist.ac.kr)