An important part of the study of southern resident killer whales finds them and quickly warns the experts to hunt out the pieces to send the boats to collect fecal samples or to better understand what the whales eat.
The underwater microphones used to locate whales are particularly useful when sight networks are ineffective at night or during weak weather. Computer algorithms play an increasing role in the analysis of hydrophone audio data, but human listeners can complete and develop these algorithms.
A research project, known as orcasound, has developed a web application that allows citizen scientists to listen to sounds from hydrophones near the San Juan Islands to identify deadly whales and other new sounds.
Scott Veirs, a Seattle-based bioacoustic and chief researcher for the Orcasound project, is organizing a new web application with the Canadian Acoustics Association's 2018 Acoustic Week in Canada and the 176th Meeting of the United States Acoustic Society. explain the value of citizen science. Victoria, Canada, November 5-9 at the Victoria Conference Center.
Citizen scientists have been useful in detecting whales and recognizing unusual activities such as the presence of other animals or the noise of transport traffic. He said the goal of Orcasound is to provide a cheap and user-friendly way for people interested in maritime life to participate in and participate in research. The question at the heart of the project also added how people who listen to the sound of the stream will organize and train the whales as better detectors. The Orcasound project also records audio data to both online and storage cloud servers by both human and algorithm to analyze later.
Each node in the network uses a cheap Raspberry Pi computer with additional audio hardware. Computers run Linux operating system and open source software to encode and send audio using standard data formats popularized by online video streaming services such as Linux. This maximizes browser compatibility and ease of use while minimizing costs. "We really want to make it easier for citizen scientists to listen to the signals," he said.
Future versions of the application will include a button that users can click when they hear something interesting, and this will help to add data to algorithms for later analysis. While there is a friendship competition between machines and people in this area, the Orcasound app aims to bring synergy between citizen scientists and sophisticated algorithms.
How can you reduce the impact of ship noise on the fish? Slow them down
Presentation # 2pAO1, "Orcasound application: An open-source solution for live ocean sound streaming for citizen scientists and cloud-based algorithms," will take place on Tuesday, November 6th, Tuesday at 1:00 am by Scott Veirs. Esquimalt room in Victoria Conference Center in Victoria, British Columbia, Canada. More information about the project can be found at www.orcasound.net.