Artificial intelligence helps us to interpret the verses of animals

Artificial intelligence helps us to interpret the verses of animals

By Dr. Kyle Muller

Whatever your opinion on what comes generically (and often improperly) called “artificial intelligence”, it is out of doubt that it is radically changing the way of doing research: an I is able to rapidly analyze a huge amount of data and give them a sense, something that we humans requires much more time.

Do you want an example? A group of researchers from the University of Copenhagen trained a model of Machine Learning to recognize and interpret the verses of seven different animal speciesidentifying if they are expressing positive or negative emotions. Their results are published in the magazine IRCHIENCE.

The study of the verses. The study focused on Seven different species of ungulates: cows, wild boars, goats, horses, sheep, pigs (i.e. the home subspecies of the wild boar) and przewalski horses (a kind of wild horse distant from the domestic one). The team used thousands of recordings of vocalizations of these animals, and “meal” them to a model of machines learning, which identified a series of acoustic indicators related to the emotional aspect of the verse.

In simpler words, the IA studied the verses of the seven species and has learned to recognize some characteristics that are indicative of a particular emotional state: how long the vocalization lastsfor example, how much energy He puts the animal to produce it, to which frequency it emits it …

Sad or happy? The result is that the IA developed by the University of Copenhagen has learned to understand when a horse, or a pig, or a cow … is emitting a “positive” verseand when instead he is expressing some stresswith a precision that touches 90%. According to the authors, this will make it possible to identify in a short time an animal that is suffering, and act accordingly for its well -being (it is no coincidence that most of the species studied are tame).

Universal model. Another interesting detail of the study is that the IA has revealed that the acoustic patterns of vocalizations of these seven species are universal: The characteristics that indicate a positive or negative verse are more or less the same in all the animals studied. The model of IA will now be made public, in the hope that other research bodies begin to exploit it to study even more deeply the way in which certain species communicate their emotions.

Kyle Muller
About the author
Dr. Kyle Muller
Dr. Kyle Mueller is a Research Analyst at the Harris County Juvenile Probation Department in Houston, Texas. He earned his Ph.D. in Criminal Justice from Texas State University in 2019, where his dissertation was supervised by Dr. Scott Bowman. Dr. Mueller's research focuses on juvenile justice policies and evidence-based interventions aimed at reducing recidivism among youth offenders. His work has been instrumental in shaping data-driven strategies within the juvenile justice system, emphasizing rehabilitation and community engagement.
Published in