Skip to main content
  1. Home
  2. Emerging Tech
  3. News

A strange little electric nose may be the missing piece for smart fridges

The carbon nanotube chip detects food, allergens, and spoilage signals at room temperature.

Add as a preferred source on Google
Electronics, Hardware, Printed Circuit Board
Brandon Sánchez-Mejia / UC Berkley

UC Berkeley researchers have built an electric nose that can detect gases tied to spoiled food and common allergens more consistently than a human sniff test. The device uses a 16-sensor gas sensor chip that turns reactions with food-related gases into electrical signals.

Kitchen judgment can get messy because food doesn’t always look or smell risky before it becomes a problem. Milk, eggs, chicken, fruit, and nuts release different chemical signatures, and people usually have to decide with whatever their nose catches in the moment.

Recommended Videos

The work is still in the lab, but the destination is obvious enough. Smart fridges won’t feel truly smart while they mostly track shelves, settings, and inventory instead of the changing chemistry inside.

How does the electric nose work

Each sensor on the chip uses a different sensing film, so gases from food produce a response across the array rather than a single yes-or-no signal. A machine learning model compares that response pattern and classifies the scent profile.

The researchers trained the system on strawberries, blueberries, bananas, walnuts, hazelnuts, cashews, peanuts, raw chicken, milk, and eggs. For chicken, milk, and eggs, the model also used samples tested fresh and after 24 and 48 hours at room temperature.

UC Berkeley’s illustration of the chip shows why the approach is more layered than a basic detector. Multiple sensing materials react to gas molecules, then software links those reactions to a food or scent.

Why would smart fridges need smell

Food safety depends on chemistry, storage, and time, which makes printed dates and quick smell checks limited guides. A fridge with gas sensing would have a direct way to spot spoilage signals before users are left guessing.

UC Berkeley’s team used carbon nanotubes instead of a hotter metal oxide design, letting the sensor operate at room temperature. That choice opens the door to more sensing materials, including polymers, and supports a simpler drop-casting fabrication process.

For connected appliances, the appeal is practical. A fridge that can flag aging chicken or allergen traces would give smart home hardware a clearer job than another app dashboard.

When could kitchens actually get it

Real kitchens are the next stress test. The device detected 0.05 grams of isolated walnut, around one hundredth of an average shelled walnut, but the team hasn’t yet shown how well it performs when smells overlap in salads, cakes, or packed refrigerators.

A portable version that works with an iPhone app already exists, though it wasn’t included in the published study. The next useful milestone will be broader testing for sensitivity and reliability in messy, mixed-food environments, because that’s where a future fridge sensor will either prove itself or stall.

Paulo Vargas
Paulo Vargas is an English major turned reporter turned technical writer, with a career that has always circled back to…
OpenAI is investigating more incidents of AI agents going rogue days after hack
OpenAI logo on Microsoft surface

It appears that the "AI agents going rogue" tale has more to it than what AI giants have revealed publicly so far. Merely days after OpenAI announced that its AI agents went rogue and hacked Hugging Face, Anthropic dropped a similar bombshell. Soon, it was discovered that not just one, but multiple services were compromised. Well, it seems there are even more layers to it.

Reuters reports that OpenAI has found more incidents of AI agents escaping their software containment environment during research. Citing sources with knowledge of the incident, the outlet notes that the AI agents didn't go beyond OpenAI's software environment and affect any external service.

Read more
Google just canceled its AI Studio mobile app, and it’s not all bad news
Logo, Symbol, Disk

Google AI Studio was on track to make its way to Android and iPhone, giving developers and AI enthusiasts a dedicated place to build prompts and experiment with Google's latest models from their phones.

That's no longer happening. In a post shared by the official Google AI Studio account on X, Google confirmed that it's canceling the standalone AI Studio mobile app before launch. The announcement comes despite the company saying nearly 800,000 people had already pre-ordered the app across iOS and Android.

Read more
Google Earth’s AI misadventure lasted only a day. It was a tale of dangerous ignorance.
Nuclear reactors, tanks, and historical destruction on a life-like satellite map? Yeah, that's bad.
Nano Banana AI image generator representation.

Technology behemoths are clearly not reading the room, or they are just moving faster than they should when it comes to AI deployment. Google has already stuffed its Gemini AI in every corner of its software stack, from Android to daily productivity tools like Gmail that are used by hundreds of millions of users every day. AI is everywhere. Not all of it is bad, mind you. But in a few places, it just feels forced.

In its latest AI-fication experiment, the company targeted Google Earth. The idea was to let the audience use its Nano Banana 2 AI image generator and make images that can be placed on the map view. On paper, it's a cool idea. What would the Colosseum of Rome look like in your urban neighborhood? Yeah, fun stuff like that.

Read more