American researchers have created a technical tool aimed at recognizing and recreating different smells.
The system is powered by Artificial intelligence (Amnesty International). The tool was developed and tested by researchers at Google, universities, and the Monell Chemical Senses Center. team recently chest The results of their method and description of the process in an article in the post Proceedings of the National Academy of Sciences.
The researchers said odors, also called odors, are caused by molecules being released into the air. These molecules then enter our noses and are processed there by ‘sensory receptors’. These receptors send signals to the brain to help us recognize smells.
The team said odors are recognized in a similar way to how we identify and measure colors — using sensory maps. For example, maps – like the traditional color wheel – can display many different colors. These maps present color combinations and show how colors work mix With some.
But the researchers said that historically, “useful maps of odors have been missing.” This is because the molecules related to smell are more complex. They rely on more than Photon Particles are used to see colors.
In addition, the researchers said that while the human eye contains only three color receptors, the human nose has more than 300 olfactory receptors.
The scientists drew on previous research to produce a neural network model that aims to create a “map” to identify molecules related to smells. A neural network is a computer processing system designed to function like the human brain.
The Google AI team calls the newly developed tool the “master odor map”. The main purpose of the map is to “predict the odor properties of molecules,” according to the researchers He said.
Neural network models have also been trained to identify molecular Features There was a need to make correct odor predictions. The researchers report that the AI-powered map allows them to “predict and detect new odors and the molecules they produce”.
The team said their research indicates the presence of billions of potentially foul-smelling molecules, but not yet smelled. Since the mapping tool has been shown to recognize an odor molecule by its structure, “This guides us to discover new classes of odors…” He said.
For the experiments, the researchers said they collected the largest set of data ever on odor descriptions of different molecules.
For comparison purposes, they used people to identify the scents of 400 molecules using 55 different descriptions. The team said that when compared to definitions of human odor, the neural network model repeatedly performed better than humans.
The team said such a tool could be used in many different areas, including healthcare, food, and fragrance industries.
Researchers report that the tool can be used to help combat one of the world’s biggest health problems – diseases spread by insects. They said the system could measure how effective the molecule was at keeping mosquitoes away from humans.
The team said it has discovered a series of new molecules that can do this bodice Mosquitoes are at least as effective as DEET, a chemical commonly used in insecticides.
The researchers said the discovery could lead to the development of insect repellents that are less costly, longer-lasting, and safer than those containing Dethylene Terephthalate. Such repellents can be used to ‘reduce all over the world Dropp off from diseases such as malaria, potentially saving countless lives,” the team added.
I’m Brian Lynn.
Bryan Lynn wrote this story for VOA Learning English, based on reports from Google AI and PNAS.
The words in this story
Artificial intelligence – n. Develop computer systems with the ability to perform work that normally requires human intelligence
mix – Fifth. To mix two or more things together
Photon – n. 1 unit of light
Characteristic – n. A typical or remarkable adjective that makes a person or thing different from others
fragrance – n. sweet smell
bodice – Fifth. To force something unwanted
Dropp off -n. How often something happens
What do you think of this story? We want to hear from you. We have a new suspension system. Here’s how it works:
- 1. Type your comment in the box.
- 2. Under the box, you can see four pictures of social media accounts. It’s for Disqus, Facebook, Twitter, and Google.
- 3. Click on one image and a box will appear. Enter the login information for your social media account. Or you can create one on the Disqus system. It’s the blue circle with the letter “D” on it. It’s free.
Every time you come back to comment on the English language learning site, you can use your account and see your comments and responses to it. Our feedback policy is over here.