Communications of the ACM
Student App Taps Computer Vision to See If Water is Safe to Drink
Credit: Getty Images
Water pollution leads to roughly 9 million premature deaths a year and 16% of all deaths worldwide. This motivated a pair of students, Ankit Gupta at the Thomas Jefferson High School for Science and Technology and Elliott Ruebush at the niversity of Maryland, to develop an AI-powered Android app capable of detecting water impurity. They claim their approach can determine if potential drinking water is contaminated with 96% accuracy in preliminary tests.
The researchers describe their work in "AquaSight: Automatic Water Impurity Detectiontilizing Convolutional Neural Network." The team's approach taps a convolutional neural network to quickly measure the turbidity of snapshots of water taken with a smartphone camera.
"People in environments without easy access to purified water would benefit from technology allowing them to determine to what extent potential drinking water appears contaminated," the coauthors write. They intend to make their mobile app publicly available in the Google Play Store and to build in functionality that will enable users to contact local governments when contaminated samples are identified.
From VentureBeat
View Full Article
No entries found