AcoustiCloud: A cloud-based system for managing large-scale bioacoustics processing. (September 2020)

• Record Type: Journal Article
• Authors: Brown, Alexander; Garg, Saurabh; Montgomery, James
• Is Part Of: Environmental modelling & software. Volume 131(2020)
• Publication Date: 2020-09
• Subjects: Bioacoustics -- System architecture -- Distributed computing -- Cloud computing -- Workflow management -- Big data; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2020.104778
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: There has been increasing interest in using automated bioacoustics analysis to monitor the environment. This involves using computational approaches to identify animals and other environmental phenomena from the sounds that they generate. The volume of data being recorded for bioacoustics analyses is increasing, as the scale of environmental surveys is increasing. This presents significant computational demands to perform analyses. These large-scale analyses cannot be performed at feasible speeds using traditional computing approaches. This research proposes AcoustiCloud : a system framework which represents bioacoustics processes as workflows and executes these across a Cloud-based system. It enables fast and efficient bioacoustics analysis for a variety of scenarios. The proposed system considers characteristics specific to bioacoustics processes resulting in fast execution times and high scalability. An implemented prototype is found to execute a bioacoustics workflow with 10 min of audio over 10 times faster than Pegasus, a widely used Workflow Management System. Highlights: An architecture for Cloud-based bioacoustics workflow processing is proposed. The architecture takes advantage of distinct properties of bioacoustics workflows. A prototype outperforms a similar generic system in testing and is scalable.