Artificial intelligence could eventually help us understand when animals are in pain or showing other emotions – at least that’s what researchers recently published in the journal Science believe.
For example, the Intellipig system, developed by scientists at the University of the West of England in Bristol and the Scottish Rural College, examines photos of pig faces and notifies farmers of signs of pain, illness, or emotional distress.
And a team at the University of Haifa, which has developed facial recognition software that already helps people find lost dogs, is now training artificial intelligence to recognize signs of discomfort on the faces of animals that have 38% of facial movements similar to humans.
These systems rely on humans to do the initial work of determining the meanings of different animal behaviors (usually based on long-term observation of animals in different situations). But recently, a researcher at the University of São Paulo conducted an experiment using photos of horses’ faces before and after surgery, and before and after they took painkillers – training an AI system to focus on their eyes, ears, and mouth – and claims that it was able to learn on its own what signs might indicate pain, with an 88% success rate.
