Scripts to detect artifacts in EDA data
OpenEdge ABL Python
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
.DS_Store Accelerometer scripts Aug 26, 2016
.gitignore Initial Commit Aug 24, 2015
AccelerometerFeatureExtractionScript.py
EDA-Artifact-Detection-Script.py move file loading scripts into separate file Jan 14, 2016
EDA-Peak-Detection-Script.py Accelerometer scripts now work for E4 files Sep 2, 2016
LICENSE.txt Create LICENSE.txt Sep 14, 2016
README.md Accelerometer scripts now work for E4 files Sep 2, 2016
SVMBinary.p Initial Commit Aug 24, 2015
SVMMulticlass.p Initial Commit Aug 24, 2015
classify.py Initial Commit Aug 24, 2015
load_files.py Accelerometer scripts now work for E4 files Sep 2, 2016

README.md

eda-explorer

Scripts to detect artifacts and in electrodermal activity (EDA) data. Note that these scripts are written in Python 2.7.

Version 0.4

Please also cite this project: Taylor, S., Jaques, N., Chen, W., Fedor, S., Sano, A., & Picard, R. Automatic identification of artifacts in electrodermal activity data. In Engineering in Medicine and Biology Conference. 2015.

Required python packages:

  • numpy: 1.9.2
  • scipy: 0.14.0
  • pandas: 0.16.0
  • sklearn: 0.16.1
  • pickle
  • matplotlib: 1.3.1
  • imp
  • PyWavelets: 0.2.2
  • os

To run artifact detection from the command line:

python EDA-Artifact-Detection-Script.py

Note that PickleDirectory is the main directory

Currently there are only 2 classifiers to choose from: Binary or Multiclass

To run peak detection:

python EDA-Peak-Detection-Script.py

Descriptions of the algorithm settings can be found at http://eda-explorer.media.mit.edu/info/

To run accelerometer feature extraction:

python AccelerometerFeatureExtractionScript.py

This file works slightly differently than the others in that it gives summary information over periods of time.

Notes:

  1. Currently, these files are written with the assumption that the sample rate is an integer power of 2.

  2. Keep the "classify.py" and "SVMBinary.p" and "SVMMulticlass.p" files in the same directory.

  3. Please visit eda.explorer.media.mit.edu to use the web-based version