Sunday June 16, 2019

AI Technology Could Help Protect Water Supplies

Moving forward, the goal is an AI system to continuously monitor water flowing through a microscope for a wide range of contaminants and microorganisms

0
//
water
It's critical to have running water, even if we have to boil it, for basic hygiene. Pixabay

Researchers have developed a novel artificial intelligence (AI)-based software that could make monitoring at water treatment plants cheaper and easier and help safeguard public health.

The new technology is capable of identifying and quantifying different kinds of cyanobacteria, or blue-green algae, as a threat to shut down water systems when it suddenly proliferates.

“We need to protect our water supplies. This tool will arm us with a sentinel system, a more rapid indication when they are threatened,” said Monica Emelko, Professor at the University of Waterloo in Ontario, Canada.

The operational AI system uses software in combination with a microscope to inexpensively and automatically analyse water samples for algae cells in about one to two hours, including confirmation of results by a human analyst.

water
The new technology is capable of identifying and quantifying different kinds of cyanobacteria, or blue-green algae, as a threat to shut down water systems when it suddenly proliferates. Pixabay

The AI system would provide an early warning of problems since testing could be done much more quickly and frequently than current existing methods, said Alexander Wong, Professor at the varsity.

Moving forward, the goal is an AI system to continuously monitor water flowing through a microscope for a wide range of contaminants and microorganisms.

Also Read: Car Tyres May Purify Wastewater in Future

The researchers estimate it may take two to three years to refine a fully commercial sample testing system for use in labs or in-house at treatment plants. The technology to provide continuous monitoring could be three to four years away.

“It’s critical to have running water, even if we have to boil it, for basic hygiene,” Emelko said. (IANS)

Next Story

Adobe Training AI to Detect Images Edited Using Photoshop

Adobe's Photoshop software was originally released in 1990

0
The headquarters of Adobe Systems in San Jose, California
The headquarters of Adobe Systems in San Jose, California. Wikimedia

Adobe, along with researchers from the University of California, Berkeley, have trained Artificial Intelligence (AI) to detect facial manipulation in images edited using the Photoshop software.

At a time when deepfake visual content is getting commoner and more deceptive, the decision is also intended to make image forensics understandable for everyone.

“This new research is part of a broader effort across Adobe to better detect image, video, audio and document manipulations,” the company wrote in a blog-post on Friday.

On testing, it was found that while human eyes were able to judge the altered face 53 per cent of the time, the the trained neural network tool achieved results as high as 99 per cent.

Adobe, AI, Photoshopped
Adobe, along with researchers from the University of California, Berkeley, have trained Artificial Intelligence (AI) to detect facial manipulation in images edited using the Photoshop software. Pixabay

The tool also identified specific areas and methods of facial warping.

Adobe’s execution in detecting facial manipulation came just days after doctored videos of Facebook CEO Mark Zuckerberg and US Speaker Nancy Pelosi made the rounds on social media as well as news channels.

Also Read- Artificial Intelligence, Machine Learning Help Shrimp, Vegetable Farmers Reap Good Harvest

“This is an important step in being able to detect certain types of image editing, and the undo capability works surprisingly well. Beyond technologies like this, the best defence will be a sophisticated public who know that content can be manipulated, often to delight them, but sometimes to mislead them as well,” said Gavin Miller, Head of Research, Adobe.

Adobe’s Photoshop software was originally released in 1990. (IANS)