Abstract
Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets. Numerous time-critical conservation needs may benefit from these methods. We developed and empirically studied a variety of deep neural networks to detect the vocalizations of endangered North Atlantic right whales (Eubalaena glacialis). We compared the performance of these deep architectures to that of traditional detection algorithms for the primary vocalization produced by this species, the upcall. We show that deep-learning architectures are capable of producing false-positive rates that are orders of magnitude lower than alternative algorithms while substantially increasing the ability to detect calls. We demonstrate that a deep neural network trained with recordings from a single geographic region recorded over a span of days is capable of generalizing well to data from multiple years and across the species’ range, and that the low false positives make the output of the algorithm amenable to quality control for verification. The deep neural networks we developed are relatively easy to implement with existing software, and may provide new insights applicable to the conservation of endangered species.
Highlights
Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets
Technological advances have led to development of detection methods such as environmental DNA1–3, cameras with infrared sensors and triggers[4,5], chemical sensors and satellite images[8]
To compare the performance of the deep nets to that of currently implemented algorithms, we measured precision, recall, and the number of false positives per hour generated by our neural networks and by the systems presented by participants in the DCLDE 2013 workshop
Summary
Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets. Technological advances have led to development of detection methods such as environmental DNA (eDNA)[1,2,3], cameras with infrared sensors and triggers (camera traps)[4,5], chemical sensors (electronic[6] and biological7) and satellite images[8] In both marine ecosystems and terrestrial ecosystems, passive acoustic systems have been used to detect and monitor taxonomic groups that communicate by sound. Machine learning has the potential to identify signals in large data sets relatively cheaply and with greater consistency than human analysts[26] Methods such as discriminant analysis[27], Gaussian mixture models[28], support vector machines[29], classification and regression trees[30], random forests[31], sparse coding[32], and deep learning[32,33,34,35,36] have been used in acoustic monitoring
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
