Communications of the ACM
Pic-Scanning AI Estimates City Air Pollution From Mass of Photos
A new app can estimate air quality by analyzing a large number of photos of a city.
Credit: ChinaFotoPress via Getty Images
A research team at Nanyang Technological University in Singapore has designed an application to estimate air quality by analyzing a large number of photos of a city.
The images will be checked against air-quality data and the information will be used to train a machine-learning algorithm to learn to estimate the level of pollutants in the air.
The goal is to provide people with real-time estimates of the air quality in their neighborhoods.
The researchers say smartphones would offer a cost-effective solution over the use of air-pollution sensors.
The AirTick project tested the prototype app on 100 users in November, and plans to roll it out to the public this year.
"Any camera-enabled mobile device installed with AirTick can become an air-quality sensor," says Pan Zhengxiang, the graduate student at Nanyang who created the app.
The AirTick project plans to present its work at the Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence in Phoenix.
From New Scientist
View Full Article - May Require Free Registration
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found