bbruhh/sensors2018cnnhar

TensorFlow implementation of Sensors 2018 paper: Divide and Conquer-based 1D CNN Human Activity Recognition Using Test Data Sharpening

Divide and Conquer-based 1D CNN Human Activity Recognition Using Test Data Sharpening

This is the code for the Sensors 2018 paper Divide and Conquer-based 1D CNN Human Activity Recognition Using Test Data Sharpening by Heeryon Cho and Sang Min Yoon.

Requirements

Our code runs with:

• Ubuntu 16.04
• NVIDIA GeForce GTX 960
• TensorFlow version 1.5.0
• Python 2.7.12

Downloading Data

Please download the following two Human Activity Recognition benchmark datasets from the UCI Machine Learning Repository.

• OPPORTUNITY Activity Recognition Data Set
• Human Activity Recognition Using Smartphones Data Set

Citation

If you find this useful, please cite our work as follows:

@article{ChoYoon_2018Sensors,
  author    = {Heeryon Cho and Sang Min Yoon},
  title     = {Divide and Conquer-Based 1D {CNN} Human Activity Recognition Using 
               Test Data Sharpening},
  journal   = {Sensors},
  volume    = {18},
  number    = {4},
  pages     = {1055},
  year      = {2018},
}