12092019What's Hot:

dem’s fighting echolocations

Bat chat: machine learning algorithms provide translations for bat squeaks

It turns out you don’t need to be Dr Doolittle to eavesdrop on arguments in the animal kingdom.

Researchers studying Egyptian fruit bats say they have found a way to work out who is arguing with whom, what they are squabbling about and can even predict the outcome of a disagreement – all from the bats’ calls.

“The global quest is to understand where human language comes from. To do this we must study animal communication,” said Yossi Yovel, co-author of the research from Tel Aviv University in Israel. “One of the big questions in animal communication is how much information is conveyed.”

Egyptian fruit bats, common to Africa and the Middle East, are social creatures. But the calls they make as they huddle together to roost are almost impossible to tell apart by human ear, all simply sounding aggressive. “Basically [it’s] bats shouting at each other,” said Yovel.

But, writing in the journal Scientific Reports, Yovel and colleagues describe how they managed to discern meaning within the squeaks.

The approach, they reveal, relied on harnessing machine learning algorithms originally used for human voice recognition. A form of artificial intelligence, machine learning algorithms are “trained” by being fed data that has already been sorted into categories, and then used to apply the patterns and relationships the system has spotted to sort new data.

The team spent 75 days continuously recording both audio and video footage of 22 bats that were split into two groups and housed in separate cages. By studying the video footage, the researchers were able to unpick which bats were arguing each other, the outcome of each row, and sort the squabbles into four different bones of contention: sleep, food, perching position and unwanted mating attempts.

The team then trained the machine learning algorithm with around 15,000 bat calls from seven adult females, each categorised using information gleaned from the video footage, before testing the system’s accuracy.

The results revealed that, based only on the frequencies within the bats’ calls, the algorithm correctly identified the bat making the call around 71% of the time, and what the animals were squabbling about around 61% of the time. The system was also able to identify, although with less accuracy, who the call was aimed at and predict the fallout of the disagreement, revealing whether the bats would part or not, and if so, which bat would leave.

The differences between the calls were nuanced. “What we find is there are certain pitch differences that characterise the different categories – but it is not as if you can say mating [calls] are high vocalisations and eating are low,” said Yovel.

The results, he says, reveals that even everyday calls are rich in information. “We have shown that a big bulk of bat vocalisations that previously were thought to all mean the same thing, something like ‘get out of here!’ actually contain a lot of information,” said Yovel, adding that analysing further aspects of the bats’ calls, such as their patterns and stresses, could reveal even more detail encoded in the squeaks.

Kate Jones, professor of ecology and biodiversity at University College, London described the findings as exciting. “It is like a Rosetta stone to getting into [the bats’] social behaviours,” she said of the team’s approach. “I really like the fact that they have managed to decode some of this vocalisation and there is much more information in these signals than we thought.”

With the approach based on the social sounds made between bats, Jones says the technique could be used to shed light on how other species of animals communicate.

“It could be that you could apply the same type of techniques to other species to figure out what they mean when they are interacting with each other,” she said. “So it could be that it opens up a different world of understanding what these communications are.”

teh guardian

Source: ONTD_Political

comments powered by HyperComments

More on the topic