Pigs are clearly intelligent animals, but like any other animal, they still have a communication barrier to understand all the signals given off by animals.

It is with this barrier in mind that a group of researchers from the University of Copenhagen reported on the development of an algorithm that is able to translate the emotional state of animals based on the lowing they emit. During the study, the researchers note that this system can be used to monitor the condition of animals on the farm in real time.

“Through this study, we demonstrate that animal sounds allow us to better understand their emotions. We are also proving that the algorithm can be used to decipher and understand the emotions of pigs, which is an important step towards improving animal welfare,” says the employee. Professor Elodie Brifer from the Department of Biology at the University of Copenhagen, who led the study.

In a previous study, it was found that high-frequency screams, in this case a scream, were associated with negative emotions, and low-frequency bellows were associated with positive or neutral emotions. But domestic pigs show a wide variety of vocal expressions, and this has led them to realize that between these two extremes there are many other sounds that have not yet been understood.

To fill this gap, a new study was launched and 411 animals were collected to conduct it, which during the study made a record 7414 sounds of different pigs. During the recording of each sound of the pig, cardiomonitoring and observation of the emotional state of the animal were carried out.

Result

Although the methodology used differed from the previous study, however, some results confirmed the observations of the previous study that associated high-frequency calls with negative emotional states and low-frequency calls with positive emotional states.

With the exception of two features revealed in the duration and speed of the amplitude modulation of the animal’s sound. For example: a pig could make a high-frequency sound, but if it was short and with little modulation, this could indicate a positive reaction, and not a negative one, as in the previous study.

“There are clear differences in how pigs cry when we look at positive and negative situations,” explains Elodie Brifer, author of the study from the University of Copenhagen. “In positive situations, the screams are much shorter, with little fluctuation in amplitude. In particular, the lowing starts loudly and gradually decreases in frequency.

Continuation after commercial

The collected data allowed the researchers to use a neural network to develop this algorithm, which could translate each of these emotional characteristics of the sounds. Based on this proof-of-concept study, they can now claim that this initial iteration of the algorithm is able to correctly interpret pigs’ emotions with 92% accuracy.

The app could still be developed for use, the researchers said, but Briter still emphasizes that hypothetically, the analytical study could be applied to other mammalian species, suggesting a way to translate the animals’ emotions.

“We trained the algorithm to decode pig grunts,” Briefer said. “Now we need someone who wants to turn the algorithm into an application that farmers can use to improve the welfare of their animals.”

Man who received pig heart transplant dies two months after surgery
The 57-year-old was operated on in January but the cause of death was not disclosed.

…..

Via: New Atlas Source: Scientific Reports.