Robust classification of animal tracking data

Mac Schwager, Dean M. Anderson, Zack Butler, Daniela Rus

Computers and Electronics in Agriculture, 2007

Abstract

This paper describes an application of the K-means classiﬁcation algorithm to categorize animal tracking data into various classes of behavior. It was found that, even without explicit consideration of biological factors, the clustering algorithm repeatably resolved tracking data from cows into two groups corresponding to active and inactive periods. Furthermore, it is shown that this classiﬁcation is robust to a large range of data sampling intervals. An adaptive data sampling algorithm is suggested for improving the efﬁciency of both energy and memory usage in animal tracking equipment.

BibTeX

@article{schwager_robust_2007,
  title = {Robust classification of animal tracking data},
  volume = {56},
  issn = {01681699},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S0168169907000026},
  abstract = {This paper describes an application of the K-means classiﬁcation algorithm to categorize animal tracking data into various classes of behavior. It was found that, even without explicit consideration of biological factors, the clustering algorithm repeatably resolved tracking data from cows into two groups corresponding to active and inactive periods. Furthermore, it is shown that this classiﬁcation is robust to a large range of data sampling intervals. An adaptive data sampling algorithm is suggested for improving the efﬁciency of both energy and memory usage in animal tracking equipment.},
  language = {en},
  number = {1},
  urldate = {2021-02-21},
  journal = {Computers and Electronics in Agriculture},
  author = {Schwager, Mac and Anderson, Dean M. and Butler, Zack and Rus, Daniela},
  month = mar,
  year = {2007},
  keywords = {machine learning, state estimation},
  pages = {46--59},
  month_numeric = {3}
}