Original image
Intel's Flickr

5 Really Ambitious Science Fair Projects

Original image
Intel's Flickr

Borrowing from Thomas Edison, science fair genius is 99 percent perspiration (the sweaty night-before-it’s-due kind) and 1 percent inspiration. And posterboard. But for every high-schooler scrambling to put together a hasty paper mache volcano, there’s a Conrad Farnsworth, a Wyoming high school senior who once built a working nuclear reactor in his dad’s garage—only one of 15 high school students in the world to successfully do so.

In salute to science aficionados going above and beyond “What popcorn pops the most?” projects, here’s a look at five other utterly impressive science fair projects.

1. Anna Simpson: Chemical-Detecting Robot

Courtesy of Intel's Flickr

When it comes to building LEGO cars, bigger is always better. Unless, of course, you’re Anna Simpson, who constructed an autonomous robot that can sweep and detect for hazardous chemicals using Lego pieces and a sensor. The six-inch long robot netted the then-San Diego high school student the Senior Division crown at the 2009 California State Science Fair. To quote Simpson (and paraphrase crowds of kids who flocked to check out her creation): “Wow! And I made that of LEGOs!”

2. Daniel Burd: Plastic-Eating Microbe

Courtesy of ChaCha

Most 16-year-olds’ ideas of “decomposition” are that turkey sandwich that’s been sitting in their locker since Spring Break. But Burd, an Ontario native, won the Canada-Wide Science Fair in 2008 by developing a process that cut the time it takes a plastic bag to decompose from 20 years to three months, thanks to a microbe he discovered. The inspiration for the project? Getting flooded by plastic bags while doing chores.

3. Jonah Kohn: Music for the Hearing Impaired

San Diego native Jonah Kohn won the 13-14 age group (he was 14) at the 2012 Google Science Fair with an invention that helps people suffering from hearing loss listen to music. The self-proclaimed music lover—the project’s name, Good Vibrations, is pilfered from the Beach Boys’ songbook—schemed up a “multi-frequency tactile device” that attaches to parts of the user’s body, translating sound frequencies to certain degrees of tactile stimulation: pretty much making the whole body into one big speaker. That’s music to anyone’s ears.

4. Ryan Garner and Amanda Wilson: Antarctic Submersible 

Courtesy of

Calling $5000 a shoestring budget isn’t totally fair—except when you’re two high school students building a camera-equipped underwater rover, that is. But the Santa Barbara duo kept things relatively inexpensive by building the rover—dubbed M’RAJE—using mostly using “off-the-shelf” materials in 2007. M’RAJE took the plunge later that year, making 10 successful dives in freezing Antarctic waters, where it is still being used for climate change research. Pronounced “mirage,” the rig borrows the first initials from Wilson, Garner, and their technicians for its moniker.

5. Ryan Patterson: Sign Translator

High school student Patterson was flipping burgers in his hometown of Grand Junction, Colo., in 2001 when inspiration struck. Remembering some deaf customers needing a translator to get their order right, the 17-year-old developed a glove that translates American Sign Language into letters on a computer screen—a invention that won him $200,000 at 2001’s Intel International Science and Engineering Fair. Patterson got the inventing bug early. As a toddler, he carried around an electrical cord instead of a blanket.

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image