Automated peak detection method for behavioral event identification : detecting Balaenoptera musculus and Grampus griseus feeding attempts

• Published in: Animal Biotelemetry
• Main Authors: Sweeney, David A., Deruiter, Stacy L., McNamara-Oh, Ye Joo, Marques, Tiago A., Arranz, Patricia, Calambokidis, John
• Other Authors: Office of Naval Research, University of St Andrews. School of Mathematics and Statistics, University of St Andrews. Scottish Oceans Institute, University of St Andrews. Centre for Research into Ecological & Environmental Modelling
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2019
• Subjects: Blue whale; Detection; Lunge; Norm-jerk; Prey capture; Risso's dolphin; QH301 Biology; Signal Processing; Animal Science and Zoology; Instrumentation; Computer Networks and Communications; DAS; QH301; Calvin; Kuipers; Balaenoptera musculus
• Online Access: http://hdl.handle.net/10023/17477; https://doi.org/10.1186/s40317-019-0169-3

This project was supported by the U.S. Office of Naval Research (Grant No. N00014-16-1-3089). Tag deployments used here from the SOCAL-Behavioral Response Study were funded by the U.S. Office of Naval Research and Navy Living Marine Resources under multiple grants and contracts. Further funding was provided by the Kuipers Research Fellowship and the Calvin Alumni Association. TAM thanks partial support by CEAUL (funded by FCT—Fundação para a Ciência e a Tecnologia, Portugal, through the project UID/MAT/00006/2013). The desire of animal behaviorists for more flexible methods of conducting inter-study and inter-specific comparisons and meta-analysis of various animal behaviors compelled us to design an automated, animal behavior peak detection method that is potentially generalizable to a wide variety of data types, animals, and behaviors. We detected the times of feeding attempts by 12 Risso’s dolphins (Grampus griseus) and 36 blue whales (Balaenoptera musculus) using the norm-jerk (rate of change of acceleration) time series. The automated peak detection algorithm identified median true-positive rates of 0.881 for blue whale lunges and 0.410 for Risso’s dolphin prey capture attempts, with median false-positive rates of 0.096 and 0.007 and median miss rates of 0.113 and 0.314, respectively. Our study demonstrates that our peak detection method is efficient at automatically detecting animal behaviors from multisensor tag data with high accuracy for behaviors that are appropriately characterized by the data time series. Publisher PDF Peer reviewed