Researchers at the University of California, Los Angeles created a cheap, portable device that uses artificial intelligence (AI) to recognize and classify common airborne allergens.
The portable device was designed to recognize five common allergens: Bermuda grass pollen, oak tree pollen, ragweed pollen, Aspergillus spore and Alternaria spore, according to a recent article published in ACS Photonics. By using deep learning, the system achieved a 94 percent classification accuracy when classifying particles into allergen types.
“Because the device is controlled wirelessly, it could potentially be carried by unmanned vehicles such as drones, which would allow scientists to monitor sites that would otherwise be dangerous or difficult for humans to reach,” a press release from UCLA stated. “The technology could also be used in a network of sensors covering a wide area, which would enable scientists to create maps of pollen, spore and microbe density.”
The device was relatively cheap to create, costing the researchers about $200 in parts. It also weighs less than 600 grams, or two pounds.
The device brings in air and traps particles on a sticky surface that’s then lightened by a laser to create a hologram, the university stated. An image sensor chip then scans the hologram and sends the data to a remote service. The device then uses AI, powered by a neural-network, to clean the image and run it through an algorithm to break down into sections. A second neural network then classifies the particles into allergen types.
Adults typically breathe in between 100 and 1,000 bioaerosols, like pollen, spores and toxins, each minute, and the particles can trigger allergies, asthma and other diseases once inhaled, according to UCLA. While current methods for identifying bioaerosols are outdated, this new device provides an opportunity for scientists classify the particles automatically.