Portuguese researchers have built software that accurately identifies up to 150 individual zebrafish almost 100 percent of the time by tracking their behavior, Defense One reports.
Gonzalo de Polavieja, principal investigator at the Collective Behavior Lab, along with his colleagues built idtracker.ai, where ai stands for artificial intelligence, or AI. Idtracker.ai is composed of two convolutional neural networks that identify and track individual animals within a group. Their results were published in the journal Nature Methods.
"The ultimate goal of our team is understanding group behavior," de Polavieja said. "We want to understand how animals in a group decide together and learn together."
The researchers extracted high-quality data from videos, including footage of the animals interacting in their enclosures. The network then identifies the individual animals during each crossing event.
The method was also used on fruit flies, but the results were less accurate, at 99.95 percent.
"I didn't believe we could reach those numbers; it was a surprise," de Polavieja said. "I thought there wouldn't be enough information in the images."
Four years ago, "we could track 10 animals back then," he added.