[ad_1]
A crucial part of the study of southern resident killer whales is to find them and quickly alert experts so that they send boats to collect stool samples or fragments of prey to better understand what the whales eat.
Hydrophones, underwater microphones used to locate whales, are particularly useful at night or in bad weather when the observation networks are ineffective. Computer algorithms play an increasing role in the analysis of audio data from hydrophones, but human listeners can complement and improve them.
A research project called Orcasound has developed a web-based application that will allow citizen citizens to listen to live audio recordings from hydrophones near the San Juan Islands to identify killer whales and other innovative sounds. .
Scott Veic, a Seattle-based bioacoustian and principal investigator of the Orcasound project, will describe the new web application and the value of citizen science at the 176th meeting of the Acoustical Society of America, which is held concurrently with Acoustical Society's Canadian Acoustical Society Acoustic Week in Canada November 5-9 at the Victoria Conference Center in Victoria, Canada.
Scientific citizens have been helpful in detecting whales and detecting unusual activities, such as the presence of other animals or the noise generated by shipping. The goal of Orcasound is to provide an inexpensive and user-friendly way for people interested in studying and conserving marine life to participate in research, Veirs said. The question at the heart of the project, he added, is how to organize and train people who listen to audio streaming so that they better detect whales. The Orcasound project also records audio data on cloud-based online storage servers for later analysis by both humans and algorithms.
Each node in the network uses an inexpensive Raspberry Pi computer with additional audio hardware. Computers run the Linux operating system and free software to encode and send audio using standard data formats made popular by online video streaming services such as YouTube. This minimizes costs while optimizing browser compatibility and ease of use. "We want to make it very easy to listen to signals for citizen scientists," Veirs said.
Future versions of the application will have a button that users can click on when they hear something of interest, which will help annotate the data for later analysis by the algorithms. While there may be some friendly rivalry between machines and humans in this area, the Orcasound application aims to create a synergy between citizen scientists and sophisticated algorithms.
Explore further:
How to reduce the impact of the noise of transport vessels on fish? Slow them
More information:
Presentation # 2pAO1, "Orcasound Application: An Open Source Solution for Broadcasting Live Ocean Sound for Citizen Scientists and Cloud-Based Algorithms", from Scott Veirs will take place on Tuesday, November 6th at 1:00 pm. in the Esquimalt Room at the Victoria Conference Center in Victoria, British Columbia, Canada. More information about the project is available on www.orcasound.net
Source link
