Artificial city

Artificial intelligence could end food recalls

Food recalls can be seriously harmful, even fatal, to consumers and the economy. But artificial intelligence could change all that.

Before taking a bite of a crisp, sweet apple – the kind that makes juice run down your chin – have you ever stopped to wonder how it got so perfect?

Rigorous food safety and dozens of special eyes from the moment it’s picked to the moment it’s placed atop the mound other perfect specimens in the grocery store corral may have something to do with it .

“I think we’ve come to a point, as consumers, where we want consistency in certain products,” says Rickey Yada, dean of lands and food systems at UBC.

“If you buy a bag of apples, you hope they’re all…similar in color, all the same shape, and you don’t have bad apples.”

But even with various people and systems in place to maintain that sense of perfection, every now and then a bad apple goes unnoticed.

This is when food safety becomes a health concern. Just last year, the US Centers for Disease Control and Prevention reported that an outbreak of listeria bacteria in deli meats resulted in 12 hospitalizations and one death.

But according to a new study by Yada and his colleagues, such serious or fatal incidents could soon be a thing of the past with the use of artificial intelligence (AI) in food production.

Currently, the study explains, most food safety errors are discovered through lagging indicators, otherwise known as incidents that occur after production.

“In the past…when a food incident was identified, it was usually an after-treatment,” Yada said. “So people would report that they had gotten sick from eating certain foods, and then food sleuths would come in to try and identify which specific food was the culprit.”

After a recall of a certain food was issued, Yada said the repercussions of it go far beyond a few customers’ stomach aches. He said the economy can be hit by multiple sick workers and a company’s reputation can be badly damaged.

But with AI, it is possible to turn these lagging indicators into leading indicators and identify a dangerous product before it leaves the hands of the producer.

How it works?

Through various tools such as image analysis and product scanning, AI’s data-driven approach can help food producers identify issues before they enter the consumption phase , says the study.

Imagine there’s a row of 20 apples traveling along the production line, Yada says. At one point, they pass an AI sensor looking for consistency and if a bad apple is identified, it is removed from the line within seconds.

“Part of the AI ​​modality is trying to take all these different inputs, integrate them, but do it in real time,” Yada said. “So that we get the quality assessment of this product right away.”

With AI’s ability to integrate information and mimic the human brain, Yada said he was confident the system could help identify food safety issues on a higher level.

Not only will this food safety-focused AI be responsible for picking out a bad apple or two, but it’s also capable of monitoring human behavior for nuanced reactions to certain products.

This is done through image analysis, Yada says. Analyzing the facial reactions or body language of workers interacting with products on the line could allow the AI ​​to alert those monitoring its algorithm that something is wrong with a product.

If a worker seems hesitant to decide whether a product should stay on the processing line, such as a bruised or discolored apple, the AI ​​will be able to detect it.

“Hesitation is often a gift you’re not quite sure of. And that would be fed into the algorithm to say, “Oh, wow, maybe this product needs to be looked at more carefully because it might be defective,” Yada said.

“The decision would be made on the spot that perhaps there should be a secondary review on this product.”

However, even with the possibility of AI improving the work of humans, Yada said he doesn’t think machines will ever reach the point of total takeover.

“Will we ever get to this point? I do not know. Maybe. We are getting closer,” he said.

“But will we ever have that [transition] where robots using artificial intelligence will replace humans? I think there are signals that humans pick up on that machines probably won’t.

The unifying effect of food security

With the swashbuckling nature of the food systems industry, Yada says he wouldn’t be surprised if AI was already being used by some companies, unbeknownst to the public.

But even though many companies are quite secretive about their production methods to keep recipes, such as the combination of oils used to fry potato chips, Yada says food safety is one of the topics that almost every company can follow.

“Food safety is one of those universal issues that I think if food companies were to share, they would share around food safety because it’s in their best interests at every level,” he said. declared.

Yada said that with this new research, he hopes food companies can become safer in their production of safe foods. Especially with the impending effects of climate change on global food systems and the possibility of more global supply chain issues.

Even local BC food co-ops, Yada hopes, could one day share the cost of this new technology to ensure people have access to safe food in their own country or province.

“Our universal goal is to make sure that we have a safe product and that we can actually process it as quickly as possible,” he said.