eEecology Classification

Automatic classification of accelerometer data using a supervised learning approach.

5
mentions
1
contributor
Get started
71 commits | Last update: October 10, 2016

Cite this software

Choose a version:
[[ releases[selectedIndex].tag ]]
  • [[release.tag]]
DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a reference manager file format:
[[ fileFormats[selectedFileFormatIndex].displayName ]]
  • [[ format.displayName ]]
Download file

What eEecology Classification can do for you

  • Load annotated accelerometer points from MAT files (Matlab)
  • Load annotated GPS points from CSV files
  • Extract data features out-of-the-box or define your own
  • Train a model using annotated time series of accelerometer or GPS data
  • Supports tree learner and Random Forest models
  • Evaluate the trained model
  • Automatically annotate accelerometer data (or GPS) using a trained model
  • Visualize all steps in the browser

Data about whereabouts from birds can be gathered using a gps tracker with accelerometer from uva-bits and analysed using this tool. Often, we are not directly interested in the forces measured by the accelerometer. What we actually want to know is whether the bird was sitting, walking, foraging of flying. Assigning a behavior to data measurements is called annotation (or classification). This tool lets you train a model on a small annotated set, and then use the model to automatically annotate a larger dataset.

Read more
Tags
  • Machine learning
Programming Language
  • Java
  • JavaScript
  • HTML
  • MATLAB
License
  • GPL-3.0
Source code

Participating organizations

Mentions

1 Conference paper

1 Journal article

2 Presentations

1 Web page

Projects with eEecology Classification

Contributors

  • Christiaan Meijer
Contact person
Christiaan Meijer
Mail Christiaan

Information for page maintainers

OAI-PMH metadata:
OK
citation metadata:
error 429 resolving doi.
Show