Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

Artificial Intelligence to Predict if Something Stinks

image-62

(via bit.ly/2i1BEHt)

German scientists are creating an Artificial Intelligence system that can predict whether a certain molecular structure will result in something stinky.

Backed by a Volkswagen Foundation’s grant of £80,000, a team of chemists at FAU university have set out to solve an age-old problem: the awful smell that is often let out from new things— especially plastic objects and packaging materials.

To achieve that, researchers at the Computer Chemistry Center are developing CLINGON—aka Computer Linguistics of Olfaction— an AI system able to gauge whether  certain molecule arrangements are bound to beget unpleasant odours.

‘”We will be spending most of our time working at the computer, not in the laboratory,” Thilo Bauer, one of the researchers behind the CLINGON project, said in a statement .

The team has put together an archive containing information about how molecular structure is linked with certain olfactive outputs.

“We use computer linguistics for this purpose. It’s similar to processing language; the programme is supposed to understand odour molecules as a sentence in which the molecule fragments represent the words. The combination of the fragments determines the meaning of the sentence, or in our case, the smell,” Bauer added.

He and his colleagues are looking to use the application to slash times spent on current trial-and-error tests for odours. Apart from staving off stenches, researchers explains, the technique could also be used to deliberately bring about specific aromas.

“In the cosmetics industry many thousands of molecules are synthesised and tested for their scent every year. Only a few of them ever make it onto the market,” said Bauer. “Our programme could help to make the development of new products more effective and resource-efficient.”

Image via bit.ly/2i1BEHt

SHARE THIS ARTICLE:
BY SHACK15

Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter