Researchers are training AI to interpret animal emotions
Author - Mansur Ismagulov
The Tech AI
Get the key points in seconds - a short summary from The Tech AI.
Intellipig systems and other AI solutions analyze animal photographs to identify signs of pain or discomfort. The University of Haifa's software accounts for a 38% overlap in facial movements between animals and humans, while the system from the University of São Paulo identifies pain in horses with 88% accuracy, focusing on the eyes, ears, and mouths.
The Intellipig system, developed by researchers from the University of Bristol in western England and Scotland's Rural College, analyzes pig photos and alerts farmers to signs of pain, illness, or emotional distress.
A team from the University of Haifa, which developed facial recognition software already used to find lost dogs, is now training AI to recognize signs of discomfort on faces that are 38% similar to human facial movements.
These systems rely on humans who perform the initial work of defining the meaning of various animal behavior patterns. A researcher from the University of São Paulo conducted an experiment using photos of horse muzzles before and after surgery, as well as before and after receiving painkillers, training the AI system to focus on their eyes, ears, and mouths. The system was able to independently identify which signs could indicate pain with 88% accuracy.
Source: TechCrunch
The Tech on Telegram Follow The Tech on Telegram
Keep up with the latest technology and startup news.