Real-time bioacoustics monitoring and automated species identification

Abstract

Traditionally, animal species diversity and abundance is assessed using a variety of methods that are generally costly, limited in space and time, and most importantly, they rarely include a permanent record. Given the urgency of climate change and the loss of habitat, it is vital that we use new technologies to improve and expand global biodiversity monitoring to thousands of sites around the world. In this article, we describe the acoustical component of the Automated Remote Biodiversity Monitoring Network (ARBIMON), a novel combination of hardware and software for automating data acquisition, data management, and species identification based on audio recordings. The major components of the cyberinfrastructure include: a solar powered remote monitoring station that sends 1-min recordings every 10 min to a base station, which relays the recordings in real-time to the project server, where the recordings are processed and uploaded to the project website (). Along with a module for viewing, listening, and annotating recordings, the website includes a species identification interface to help users create machine learning algorithms to automate species identification. To demonstrate the system we present data on the vocal activity patterns of birds, frogs, insects, and mammals from Puerto Rico and Costa Rica.

Species-specific audio detection: a comparison of three template-based detection algorithms using random forests

“…Some of the recordings were acquired using the Automated Remote Biodiversity Monitoring Network (ARBIMON) data acquisition system described in Aide et al (2013), while others were acquired using the newest version of ARBIMON permanent recording station, which uses an Android cell phone and transmits the recorded data through a cellular network. All recordings have a sampling rate of 44.1 kHz, a sampling depth of 16-bit and an approximate duration of 60 s (±.5 s) The locations in Puerto Rico were the Sabana Seca permanent station in Toa Baja, the Casa la Selva station in Carite Mountains (Patillas), El Yunque National Forest in Rio Grande and Mona Island (see Fig.…”

“…Passive acoustic monitoring (PAM) can contribute to this need because it facilitates the collection of large amounts of data from many sites simultaneously, and with virtually no impact to the fauna and environment (Brandes, 2008;Lammers et al, 2008;Tricas & Boyle, 2009;Celis-Murillo, Deppe & Ward, 2012). In general, PAM systems include a microphone or a hydrophone connected to a self powered system and enough memory to store various weeks or months of recordings, but there are also permanent systems that use solar panels and an Internet connection to upload recordings in real time to a cloud based analytical platform (Aide et al, 2013).…”

“…Web-based applications have been developed to facilitate data management of these increasingly large datasets (Aide et al, 2013;Villanueva-Rivera & Pijanowski, 2012), but the biggest challenge is to develop efficient and accurate algorithms for detecting the presence or absence of a species in many recordings. Algorithms for species identification have been developed using spectrogram matched filtering (Clark, Marler & Beeman, 1987;Chabot, 1988), statistical feature extraction (Taylor, 1995;Grigg et al, 1996), k-Nearest neighbor algorithm (Han, Muniandy & Dayou, 2011;Gunasekaran & Revathy, 2010), Support Vector Machine (Fagerlund, 2007;Acevedo et al, 2009), treebased classifiers (Adams, Law & Gibson, 2010;Henderson, Hildebrand & Smith 2011) and template based detection (Anderson, Dave & Margoliash, 1996;Mellinger & Clark, 2000), but most of these algorithms are built for a specific species and there was no infrastructure provided for the user to create models for other species.…”

Autonomous recording units in avian ecological research: current use and future applications

“…Another type of advance in bioacoustic processing is the development of an automated monitoring network that combines hardware and software to record sound in the field and send the recordings to a data server in real time for processing, and it includes tools for data management and automated species recognition (Aide et al 2013). Advances in bioacoustic processing will no doubt continue to improve the efficiency of processing large volumes of acoustic recordings.…”

The Soundscape Approach for the Assessment and Conservation of Mediterranean Landscapes: Principles and Case Studies

“…Other software (such as ARBIMON) can learn to automatically recognize certain species calls or songs, even among intense choruses (Aide et al, 2013). New procedures and algorithms are in the process of being produced to enable the acoustic complexity of an environment to be understood in detail.…”