Close Ad

The Spoon

Daily news and analysis about the food tech revolution

RFID

Tech From MIT Uses RFID to Reveal Food Contamination

Given the job I have, my parents like to tell me about food tech-related news they come across. Last night they were trying to explain a story from CBS This Morning that aired yesterday, but they had trouble relaying it. “It’s a scanner, you use it at the market… something about e. coli and…”

Intrigued, I found the report they were talking about. It’s no wonder they couldn’t explain it: the story was vague and provided almost no details as to how the technology works. So, for my parents and anyone else who saw the CBS Story and wanted a little more information, here are some details.

The technology in question is RFIQ (radio frequency IQ). Here’s a brief explainer from the MIT RFIQ research page:

Our system leverages RFID (Radio Frequency Identification) stickers that are already attached to hundreds of billions objects. When an RFID powers up and transmits its signal, it interacts with material in its near vicinity (i.e., inside a container) even if it is not in direct contact with that container. This interaction is called “near-field coupling,” and it impacts the wireless signal transmitted by an RFID. Our system, RFIQ, extracts features from this signal and feeds it to a machine learning model that can classify and detect different types of adulterants in the container.

You can read the full RFIQ paper.

According to the research overview, the technology can detect fake alcohol (like if methanol is mixed into a drink) with 97 percent accuracy, and tainted baby formula with 96 percent accuracy. In the CBS story, MIT Assistant Professor, Fadel Adib said RFIQ could be used for a broader set of applications including finding lead in water or e. coli on lettuce.

The bones of RFIQ sound akin to hyperspectral imaging, which studies how light reflects off objects to assess freshness, quality and foreign objects. But companies like ImpactVision and P&P Optica, which use hyperspectral imaging, don’t tout the technology as a way to detect foodborne illnesses.

The drawback to the RFIQ technology as it is envisioned now, is that in order for it to work, each item has to have a RFID sticker on it, and the user would have to carry around a small device that would plug into their phone to scan each item. This seems cumbersome and a big ask for food producers and consumers alike.

I’m sure Mr. Fadel and his team have thought about this and way beyond what I’m pondering. There is probably a more industrial grade solution that can be implemented in bulk throughout the supply chain. The RFIQ technology is still five years out from reaching the market anyway, so who knows what breakthroughs and advancements the MIT team will make by then.

For now, I’m just happy that there are researchers going about solving the problem of food contamination from different angles, and I’m happy to help fill in the blanks of my parents’ news watching.

Amazon Go Delays Public Opening Due To Tech Challenges

The Wall Street Journal reported yesterday that Amazon is delaying the public opening of its first fully automated grocery store known as Amazon Go. The store, which has only been open in beta to Amazon employees in the Seattle location, was supposed open at the end of this month. This is being pushed back, due to a few glitches involving tracking items and processing payments.

Amazon reported that it was experiencing technical problems with two key areas of its “Just Walk Out” technology – the company’s payment system was unable to handle or process payments when more than 20 people were in the store at a time. The system also struggled when an item was moved from its specific location on a shelf.

The traditional grocery store has been experiencing disruption for the last several years, with the rise of e-commerce giants like Amazon and Jet.com taking aim at consumer packaged goods (CPGs). Other rising stars like meal kit delivery subscriptions and grocery store delivery give consumers more options for fresh foods like produce and meat that don’t involve setting foot in a brick and mortar store.

But Amazon’s vision for the more convenient food store utilizes existing and emerging tech like connected sensors, machine learning, RFID tags and mobile payments to implement a cashier and checkout line-free experience for consumers. Not only does it create a streamlined door-to-door shopping event for the customer, but it cuts costs for the grocer – who in this case is Amazon – and could help impact the bottom line in a field where margins are shrinking.

And it’s clear why Amazon wants to build physical stores – as much as e-commerce is making grocers in North America rethink ways to attract customers with sales, fresh foods and produce and upgraded natural food and organic offerings, Nielsen’s 2017 research shows only 10% of consumers are currently shopping online for groceries. Amazon will need a multi-prong approach to remain competitive in grocery, especially when it comes to fresh foods and non-CPG items.

Amazon Go’s tech issues don’t seem major – but they are a good reminder that full-on grocery automation is hard. There are a lot of variables to consider, especially in a busy store, where customers are moving around, bumping into each other, moving merchandise without putting it back but not actually buying it. As a reminder to automation enthusiasts, earlier versions of what Amazon is trying to accomplish – self check-out kiosks – are still widely underused in grocery stores. And those of us who have used them know all too well that often, the light above the conveyer belt will inevitably blink when a customer has a problem, beckoning a store employee over.

So the future may be automated – but it’s not clear how seamless those shopping experiences will be, at least not yet. Amazon Go’s public opening and subsequent operations will certainly be telling.