Skip to main content

Table 3 On-board runtime and storage requirement of four machine learning methods with full feature sets and simplified feature set

From: An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

 

SVM

RF

ANN

XGBoost

Runtime(ms)

 Full feature set

43.042

2.154

1.044

0.312

 Simplified feature set

34.628

0.186

0.826

0.134

Storage requirement(kB)

 Full feature set

185.684

164.808

10.764

24.3

 Simplified feature set

26.724

23.064

3.42

13.164

  1. SVM Support vector machine, RF Random forest, ANN Artificial neural network, XGBoost Extreme gradient boosting
Back to article page

Movement Ecology

ISSN: 2051-3933