Application of a semi-automated vocal fingerprinting approach to monitor Bornean gibbon females in an experimentally fragmented landscape in Sabah, Malaysia

Clink, Dena J.; Crofoot, Margaret C.; Marshall, Andrew J.

doi:10.1080/09524622.2018.1426042

Cited by 30 publications

(35 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few years, major improvements in automated species detection algorithms have transformed the way big data are analysed (e.g. Clink, Crofoot, & Marshall, ; Knight et al, ; Wrege et al, ). Different methods of machine learning (e.g.…”

Section: Discussionmentioning

confidence: 99%

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

et al. 2020

View full text Add to dashboard Cite

With one million animal species at risk of extinction, there is an urgent need to regularly monitor threatened species. However, in practice this is challenging, especially with wide‐ranging, elusive and cryptic species or those that occur at low density. Here we compare two non‐invasive methods, passive acoustic monitoring (n = 12) and camera trapping (n = 53), to detect chimpanzees Pan troglodytes in a savanna‐woodland mosaic habitat at the Issa Valley, Tanzania. With occupancy modelling we evaluate the efficacy of each method, using the estimated number of sampling days needed to establish chimpanzee absence with 95% probability, as our measure of efficacy. Passive acoustic monitoring was more efficient than camera trapping in detecting wild chimpanzees. Detectability varied over seasons, likely due to social and ecological factors that influence party size and vocalization rate. The acoustic method can infer chimpanzee absence with less than 10 days of recordings in the field during the late dry season, the period of highest detectability, which was five times faster than the visual method. Synthesis and applications. Despite some technical limitations, we demonstrate that passive acoustic monitoring is a powerful tool for species monitoring. Its applicability in evaluating presence/absence, especially but not exclusively for loud call species, such as cetaceans, elephants, gibbons or chimpanzees provides a more efficient way of monitoring populations and inform conservation plans to mediate species‐loss.

show abstract

Section: Discussionmentioning

confidence: 99%

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Here we utilize an existing dataset of recordings of calls from Northern gray gibbon Hylobates funereus females recorded at five different sites in Malaysian Borneo to investigate the effectiveness of unsupervised clustering techniques to distinguish between individual females. Bornean gibbon females have a high degree of vocal individuality (Clink et al., 2017; Clink, Crofoot, & Marshall, 2018; Clink, Grote, et al., 2018), and supervised techniques have been shown to effectively discriminate 33 females with over 98% accuracy (Clink, Crofoot, & Marshall, 2018). Our main goal was to compare affinity propagation clustering (Frey & Dueck, 2007) with two other commonly used unsupervised clustering approaches: K ‐medoids (Kaufman & Rousseeuw, 1990) and Gaussian mixture model‐based clustering (Fraley & Raftery, 2002).…”

Section: Introductionmentioning

confidence: 99%

Unsupervised acoustic classification of individual gibbon females and the implications for passive acoustic monitoring

Clink

Klinck

2020

Methods Ecol Evol

Self Cite

View full text Add to dashboard Cite

Passive acoustic monitoring (PAM) has the potential to greatly improve our ability to monitor cryptic yet vocal animals. Advances in automated signal detection have increased the scope of PAM, but distinguishing between individuals—which is necessary for density estimation—remains a major challenge. When individual identity is known, supervised classification techniques can be used to distinguish between individuals. Supervised methods require labelled training data, whereas unsupervised techniques do not. If the acoustic signals of individuals are sufficiently different, the number of clusters might represent the number of individuals sampled. The majority of applications of unsupervised techniques in animal vocalizations have focused on quantifying species‐specific call repertoires. However, with increased interest in PAM applications, unsupervised methods that can distinguish between individuals are needed. Here we use an existing dataset of Bornean gibbon female calls with known identity from five sites on Malaysian Borneo to test the ability of three different unsupervised clustering algorithms (affinity propagation, K‐medoids and Gaussian mixture model‐based clustering) to distinguish between individuals. Calls from different gibbon females are readily distinguishable using supervised techniques. For internal validation of unsupervised cluster solutions, we calculated silhouette coefficients. For external validation, we compared clustering results with female identity labels using a standard metric: normalized mutual information. We also calculated classification accuracy by assigning unsupervised cluster solutions to females based on which cluster had the highest number of calls from a particular female. We found that affinity propagation clustering consistently outperformed the other algorithms for all metrics used. In particular, classification accuracy of affinity propagation clustering was more consistent as the number of females increased, and when we randomly sampled females across sites. We conclude that unsupervised techniques may be useful for providing additional information regarding individual identity for PAM applications. We stress that although we use gibbons as a case study, these methods will be applicable for any individually distinct vocal animal.

show abstract

“…However, this traditional monitoring approach is labour-intensive and is only conducted for discrete survey periods. Gibbons are therefore prime candidates for passive acoustic monitoring and recent studies have used data collected in this way to model occupancy (Vu & Tran, 2019) and to discriminate between individuals using spectral features (Clink, Crofoot, & Marshall, 2019;Zhou et al, 2019). All of these studies, however, have relied on an initial manual extraction of calls.…”

Section: Introductionmentioning

confidence: 99%

Automated detection of Hainan gibbon calls for passive acoustic monitoring

Dufourq

Durbach

Hansford

et al. 2020

Preprint

View full text Add to dashboard Cite

1AbstractExtracting species calls from passive acoustic recordings is a common preliminary step to ecological analysis. For many species, particularly those occupying noisy, acoustically variable habitats, the call extraction process continues to be largely manual, a time-consuming and increasingly unsustainable process. Deep neural networks have been shown to offer excellent performance across a range of acoustic classification applications, but are relatively underused in ecology.We describe the steps involved in developing an automated classifier for a passive acoustic monitoring project, using the identification of calls of the Hainan gibbon (Nomascus hainanus), one of the world’s rarest mammal species, as a case study. This includes preprocessing - selecting a temporal resolution, windowing and annotation; data augmentation; processing - choosing and fitting appropriate neural network models; and postprocessing - linking model predictions to replace, or more likely facilitate, manual labelling.Our best model converted acoustic recordings into spectrogram images on the mel frequency scale, using these to train a convolutional neural network. Model predictions were highly accurate, with per-second false positive and false negative rates of 1.5% and 22.3%. Nearly all false negatives were at the fringes of calls, adjacent to segments where the call was correctly identified, so that very few calls were missed altogether. A postprocessing step identifying intervals of repeated calling reduced an eight-hour recording to, on average, 22 minutes for manual processing, and did not miss any calling bouts over 72 hours of test recordings. Gibbon calling bouts were detected regularly in multi-month recordings from all selected survey points within Bawangling National Nature Reserve, Hainan.We demonstrate that passive acoustic monitoring incorporating an automated classifier represents an effective tool for remote detection of one of the world’s rarest and most threatened species. Our study highlights the viability of using neural networks to automate or greatly assist the manual labelling of data collected by passive acoustic monitoring projects. We emphasise that model development and implementation be informed and guided by ecological objectives, and increase accessibility of these tools with a series of notebooks that allow users to build and deploy their own acoustic classifiers.

show abstract

Application of a semi-automated vocal fingerprinting approach to monitor Bornean gibbon females in an experimentally fragmented landscape in Sabah, Malaysia

Cited by 30 publications

References 57 publications

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

Unsupervised acoustic classification of individual gibbon females and the implications for passive acoustic monitoring

Automated detection of Hainan gibbon calls for passive acoustic monitoring

Contact Info

Product

Resources

About