I remember somebody was doing 3D-woven composites, possibly for spacecraft, some years ago..
This is essentially the same idea, but with nanotubes.
This suggests that weaving reinforcement tow through the layers of the layup would be structurally-significant, if it were done densely-in-pattern, enough..
In aerospace, maybe it'd be structurally significant ( aircraft have, iirc, only a 10% margin in structural-strength, though that may be just the aluminum semi-monocoque builds )
These tags should be smaller and cheaper, offloading tech to the scanners. Since a store uses lots of tags and only a couple scanners, this might make financial sense even if the scanners are more expensive as long as the tags are cheaper and enough of them are needed.
I read somewhere of a similar implementation using glitter mixed into clear nail polish. Take a close-up photo any time and visually compare with the original, no ML/AI model necessary
My problem is that "AI" is an overly broad term that leads people to conflate very different technologies. I just want people to use more specific language.
There's a corporate initiative where I work that we're going to offer AI in 2024. When I politely asked to expound on that, I was met with blank stares.
Like motherfucker do you realize even MS Teams uses AI for meeting transcription
The researchers noticed that if someone attempted to remove a tag from a product, it would slightly alter the glue with metal particles making the original signature slightly different. To counter this they trained a model:
The researchers produced a light-powered antitampering tag that is about 4 square millimeters in size. They also demonstrated a machine-learning model that helps detect tampering by identifying similar glue pattern fingerprints with more than 99 percent accuracy.
It's a good use case for an ML model.
In my opinion, this should only be used for continuing to detect the product itself.
The danger that I can see with this product would be a decision made by management thinking that they can rely on this to detect tampering without considering other factors.
The use case provided in the article was for something like a car wash sticker placed on a customers car.
If the customer tried to peel it off and reattach it to a different car, the business could detect that as tampering.
However, in my opinion, there are a number of other reasons where this model could falsely accuse someone of tampering:
Temperature swings. A hot day could warp the glue/sticker slightly which would cause the antitampering device to go off the next time it's scanned.
Having to get the windshield replaced because of damage/cracks. The customer would transfer the sticker and unknowingly void the sticker.
Kids, just don't underestimate them.
In the end, most management won't really understand this device well beyond statements like, "You can detect tampering with more than 99 percent accuracy!"
And, unless they inform the customers of how the anti-tampering works, Customers won't understand why they're being accused of tampering with the sticker.
We made a tag that can't be reliably and deterministically scanned so we also included a machine learning model that takes a good guess at it.
I just don't see how you could possibly rely on a black box model for anything important. You have no way to mathematically prove if there are collisions in the model output or not, and newer versions of the model can't be made backwards compatible. So if you have a database of thousands of these tags scanned, then they discover a critical vulnerability and provide a new model, you're SOL and everything you have is worthless.
Can you imagine your house doorknob had to think about the shape of your key before letting you in, and then have the possibility of just saying "No. Not today."?
If there were collisions in the output you'd see them while scanning those thousands of entries. And if they release a new model you can use it going forward and keep scanning the old items with the old one.
This happens in inventory sometimes, new technology comes out, you have to update asset tags.
Tell me you've never developed commercial security software without telling me. "If it works a few thousand times without collisions it should be reliable enough". That's not even good enough for tamper proof seals on medication and yogurt jars let alone applications that require the sender and recipient to use a dedicated tetrahertz scanner to validate.
Nobody said anything about security applications, lol. It's a proof of concept and you're getting all worked up over complete hypotheticals. Where did you even get the idea that it would have collisions within thousands?
In security applications you need to account for actors with a marked interest in causing a collision but in an inventory scenario you simply generate IDs randomly until you get one that's not a duplicate. There's no problem using a hash algorithm with collisions if the probability is small enough. There are tons of scientific labs using MD5, btw.
You'd have to read the article to know what they're getting at.
The use case provided was for businesses like a car wash that puts a sticker on a car windshield. The ML model would be able to detect if the customer attempted to transfer the sticker from one car to another.
A pretrained ML model to detect this is actually a very good use case.
However, I think the implimentation of this as an "anti-tampering detector" is a dangerous route to tread since there are other factors that need to be considered.
Cost is somewhat relative at this scale. THz is just unstable over any normally expected usable distances since they are . At this scale, I assume they are thinking more like NFC replacement tech maybe? It's definitely got more applications than just object tracking, but that seems to be it's first test.
It's updated RFID tags that are even harder to detect, and unlike the standard ones, require specialized technology to activate, so they get security through obscurity.
It has nothing to do with NFCs. Likely has a lot to do with the police state ID cards and vehicle tracking that the Bush Administation tried to implement in the late 2000s.
Plants are green specifically because the red and blue wavelengths of light are useful for breaking specific chemical bonds necessary for photosynthesis and as such are readily absorbed by the plant. The plant makes efficient use of the energy provided by only absorbing the wavelengths necessary for its processes. However, plants still absorb 90% of green light and green light holds the highest proportion of the energy radiated by the sun.
To be more clear, green light has too much energy. When plants absorb light it first enters a protein mesh containing pigments such as chlorophyll that function like an antenna or receiver for a range of wavelengths. The pigments then transfer the energy to a "reaction center" where it turns this electromagnetic energy into chemical energy (photosynthesis). This process is exceedingly efficient; almost all of the absorbed energy is converted into electrons the plants can use. However, this protein mesh antenna is not solid and is constantly moving. These movements affect how energy is absorbed and how it flows through the pigments. Think of diffraction in water. Fluctuation in the intensity of light can create noise in this process; a quick brush of shade or sudden increase of light intensity can decrease the efficiency of photosynthesis. For plants and really everything that lives, a steady input and output of energy is desirable. Not enough electrons making it to the reaction center causes energy failure while too much will cause general overcharging effects that can damage tissue. When the noise of this system fluctuates it makes it difficult for the plant to self regulate it's energy flow and could cause the plant to kill it's own tissue or essentially starve. So essentially, while absorbing all green light would provide the plant with more energy, it's not capable of handling this energy so plants evolved to limit their intake of green light.
However, this is not to say that green lights ability to efficiently evaporate water is not a factor in this evolutionary development, hell it's probable that these two things are heavily related. Green light might evaporate water so well because of some combination of its relatively high energy mixed with the size of its wavelength interacting with the hydrogen bonds between water molecules in a more efficient manner than other wavelengths of electromagnetic radiation.
news.mit.edu
Hot