Classification of large acoustic datasets using machine learning and crowdsourcing: Application to whale calls

Abstract

Vocal communication is a primary communication method of killer and pilot whales, and is used for transmitting a broad range of messages and information for short and long distance. The large variation in call types of these species makes it challenging to categorize them. In this study, sounds recorded by audio sensors carried by ten killer whales and eight pilot whales close to the coasts of Norway, Iceland, and the Bahamas were analyzed using computer methods and citizen scientists as part of the Whale FM project. Results show that the computer analysis automatically separated the killer whales into Icelandic and Norwegian whales, and the pilot whales were separated into Norwegian long-finned and Bahamas short-finned pilot whales, showing that at least some whales from these two locations have different acoustic repertoires that can be sensed by the computer analysis. The citizen science analysis was also able to separate the whales to locations by their sounds, but the separation was somewhat less accurate compared to the computer method.

A Tale of Two Crowds: Public Engagement in Plankton Classification

“…Citizen science has long been an effective outreach and data collection tool for marine ecologists (e.g., coral reef monitoring, Pattengill-Semmens and Semmens, 2003), assessing invasive species (Delaney et al, 2008), tracking marine debris (Smith and Edgar, 2014), and categorizing whale calls (Shamir et al, 2014). For our project "Plankton Portal, " we partnered with Zooniverse (www.zooniverse.org), one of the major hubs for online citizen science projects.…”

“…Previous discussions about working with "big" ecological data have focused largely on cyber-infrastructure capabilities, data management (Michener and Jones, 2012;Gilbert et al, 2014), and the need for datadriven approaches (Kelling et al, 2009). While novel analytical techniques such as machine learning and crowd-sourcing for processing large and complex ecological data sets are increasingly reported in the terrestrial literature (Kelling et al, 2013;Peters et al, 2014), marine examples are limited (Wiley et al, 2003;Dugan et al, 2013;Millie et al, 2013;Shamir et al, 2014). Given this paucity and the need to use "big" biological oceanography and marine ecology data for rapid assessment of ocean health and adaptive management of ecosystems, we present here an evolution of approaches applied to the problem of efficiently classifying tens of millions of images of individual plankters generated by ISIIS.…”

Authentic computer science undergraduate research experience through computational science and research ownership

“…However, the proportion of female students is completely different when considering the student-authored papers published so far. Out of 27 student-authored papers published so far, about 25% were authored by female students [47,42,26,43,24,50,10], much higher than the proportion of female student in the entire student population, which is ∼9%. That proportion remains consistent also among the papers that are currently under review.…”

“…Before the implementation of the program none of the undergraduate students submitted papers to peer-reviewed journals or conferences. After the first year of the program two papers were published [47,42], three papers in 2013 [36,13,39], seven in 2014 [14,43,17,11,26,46,21], six in 2015 [8,24,35,22,15,27], and seven in 2016 [23,38,41,45,40,50,10].…”

“…Since 2011 we had four student research projects [42,14,43,23] featured on the premier national and international popular press (e.g., NBC News, Fox News, CBS, NPR, Discovery Channel, Scientific American, The Atlantic, etc'), including press interviews with the students about their research. The exposure through the mainstream media elevated the research experience to a new level of pride and excitement for the students, their friends, and their families.…”