2020
DOI: 10.1371/journal.pone.0230319
|View full text |Cite
|
Sign up to set email alerts
|

Description and classification of echolocation clicks of Indian Ocean humpback (Sousa plumbea) and Indo-Pacific bottlenose (Tursiops aduncus) dolphins from Menai Bay, Zanzibar, East Africa

Abstract: Passive acoustic monitoring (PAM) is a powerful method to study the occurrence, movement and behavior of echolocating odontocetes (toothed whales) in the wild. However, in areas occupied by more than one species, echolocation clicks need to be classified into species. The present study investigated whether the echolocation clicks produced by small, at-risk, resident sympatric populations of Indian Ocean humpback dolphin (Sousa plumbea) and Indo-Pacific bottlenose dolphin (Tursiops aduncus) in Menai Bay, Zanzib… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
9
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 12 publications
(9 citation statements)
references
References 53 publications
0
9
0
Order By: Relevance
“…While it is likely that the addition of other call types would improve classification 28 , 35 , the BANTER classifier presented here demonstrates belugas and narwhals can be classified by clicks alone. Echolocation is increasingly being incorporated into PAM classification programs 28 , 74 , 80 , 86 and is specifically gaining traction for monitoring belugas 16 , 19 , 33 . Noise from ice floes, vessels, or industrial activities below 40 kHz can mask lower frequency social calls (e.g., Lammers et al .…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…While it is likely that the addition of other call types would improve classification 28 , 35 , the BANTER classifier presented here demonstrates belugas and narwhals can be classified by clicks alone. Echolocation is increasingly being incorporated into PAM classification programs 28 , 74 , 80 , 86 and is specifically gaining traction for monitoring belugas 16 , 19 , 33 . Noise from ice floes, vessels, or industrial activities below 40 kHz can mask lower frequency social calls (e.g., Lammers et al .…”
Section: Discussionmentioning
confidence: 99%
“…We used a Random Forests (RF) classification model 73 to classify belugas and narwhals using echolocation click parameters. RF has demonstrated to be an effective approach for bioacoustic studies 74 76 as it is unaffected by nonparametric data and can accommodate many correlated variables. An RF model consists of many individual decision trees; each of these trees uses a random subset of samples and predictors.…”
Section: Methodsmentioning
confidence: 99%
“…In other words, studies that investigate the occurrence or distribution of individuals in a population, when the presence/absence data are sufficient, can use recordings at low frequencies. However, it is necessary to highlight, when the goal is to analyse acoustic parameters of clicks or identify different dolphins' species, it is recommended to record, as much as possible, all clicks frequency ranges [ 51 , 65 ]. Also, one should consider the soundscape of the study area, thinking about possible solutions to the acoustic data analysis.…”
Section: Discussionmentioning
confidence: 99%
“…While it is likely that the addition of other call types would improve classification 28,35 , the BANTER classifier presented here demonstrates belugas and narwhals can be classified by clicks alone. Echolocation is increasingly being incorporated into PAM classification programs 28,74,80,86 and is specifically gaining traction for monitoring belugas 16,19,33 . Noise from ice floes, vessels, or industrial activities below 40 kHz can mask lower frequency social calls (e.g., Lammers et al 34 and Halliday et al 87 ).…”
Section: Discussionmentioning
confidence: 99%
“…We used a Random Forests (RF) classification model 73 to classify belugas and narwhals using echolocation click parameters. RF has demonstrated to be an effective approach for bioacoustic studies [74][75][76] as it is unaffected by nonparametric data and can accommodate many correlated variables. An RF model consists of many individual decision trees; each of these trees uses a random subset of samples and predictors.…”
Section: Methodsmentioning
confidence: 99%