Toward passive acoustic occupancy surveys of rare red uakari monkeys (Cacajao ucayalii): using automatic signal recognition and cluster analysis to organize signals?
Bowler, M.; Casinhas, I.; Moreno, D.; Mori, G.; Bricano, F.; Leon, J.; Gacheva, B.
Show abstract
We tested a workflow using a cluster analysis to develop a classifier to detect red uakari monkey calls using clustering and Hidden Markov Models, and Kaleidoscope viewer to review and discount false positives. We used recordings collected in a series of behavioral studies on a habituated group of red uakari monkeys on the Yavari-Miri River in the Peruvian Amazon as training data to develop the classifier and tested it on a passive acoustic survey at the same site where uakari distributions were known to us. We estimated detection probabilities for red uakaris and used an occupancy model to estimate habitat use to compare with use determined by behavioral research. We assessed a workflow for processing passive acoustic primate surveys that would eliminate false positives and demand minimal time and coding expertise from those implementing the analyses and reviewing audio recordings. These are key considerations in the design of landscape-scale PAM surveys for rare species.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- How do King Cobras move across a major highway? Unintentional wildlife crossing structures may facilitate movement. 94%
- How citizen science could improve Species Distribution Models and their independent assessment 93%
- Fine-scale coexistence between Mediterranean mesocarnivores is mediated by spatial, temporal and trophic resource partitioning 92%
Similar papers in this journal
- Far-reaching displacement effects of artificial light at night in a North American bat community 94%
- Spatial behaviors and seasonal habitat use of the increasingly endangered thick-billed parrot (Rhynchopsitta pachyrhyncha) 93%
- Use of object detection in camera trap image identification: assessing a method to rapidly and accurately classify human and animal detections for research and application in recreation ecology 93%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.