Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys.
Adrià López-BaucellsLaura TorrentRicardo RochaPaulo E. D. BobrowiecJorge M. PalmeirimChristoph F. J. MeyerPublished in: Ecol. Informatics (2019)
Keyphrases
- trade off
- plant species
- bird species
- semi automatic
- training data
- combining classifiers
- support vector
- training set
- machine learning algorithms
- decision trees
- manual inspection
- classification systems
- test set
- response time
- error prone
- multiple classifier systems
- fully automated
- class labels
- training samples
- naive bayes
- training examples
- supervised classification
- classification models
- classification method
- feature selection
- predator prey
- underwater vehicles
- classification algorithm
- supervised learning