CLOSE
Original image
ZooKeys

Why Won’t These Bugs Cross This Line?

Original image
ZooKeys

One of the most tightly-controlled borders in the world is a strip of forest in northwest Tasmania. It runs almost 125 miles and separates two areas by as little as 330 feet in some places. Those that live on one side of the border rarely, if ever, cross to the other. The border isn’t a geographical barrier or a wall, and it doesn’t separate political entities or ethnic groups. Rather, it’s an invisible line where two related species of millipedes meet, but don’t mix—and no one knows why. 

On the western side of the border lives Tasmaniosoma compitale, a 15 millimeter long, yellow-brown millipede. On the eastern side is T. hickmanorum, a similarly sized red-brown millipede in the same genus. Both species were named and scientifically described in 2010 by Bob Mesibov, a millipede specialist and research associate at the Queen Victoria Museum and Art Gallery in Launceston, Tasmania. He describes them and related species as a “head + 19 rings” (the head + 17 segments with limbs + 1 segment without legs + the telson, or end segment). Mesibov spent two years mapping the species’ ranges as preparation for further field studies. When all was said and done, he had an image of a very clear division that he could not explain.

Biogeographers, the scientists that study the spatial distribution of species, have a name for these cases where species meet, but overlap very little or not at all: parapatry. It’s very common with millipedes, and occurs with other invertebrates, some plants, and some vertebrates, like birds. Normally, parapatric boundaries follow some other natural boundary like a river or the edge of a climate zone. This millipede border, though, is the longest and narrowest of any that Mesibov has seen in Australian millipedes, and doesn’t have any apparent environmental or ecological cause. It rises from sea level at Tasmania’s north coast to some 700 meters in elevation and then drops back down to sea level. It crosses many of the island’s western coastal rivers and the headstreams of two major inland river systems in the area. It runs over different geological barriers and covers different soil and vegetation types and local climates. The border seemingly ignores the vast differences in topography, geology, climate, and vegetation that it covers, and maintains its sharpness for its whole length. 

Breach!

Strong as the border is, Mesibov did find places where each species had managed to cross over into the other’s territory. There’s an “island” of T. hickmanorum surrounded by T. compitale range that’s at least 15 square miles and maybe bigger—Mesibov hasn’t found its outer edge yet. There’s also a group of T. hickmanorum living several miles into T. compitale territory, where they might have been accidentally dropped by a cattle truck.

For now, Mesibov can only speculate that the border is the result of some biological arrangement between the two species, and its origin and the way it’s maintained are a mystery. It’s one that he’ll leave to other biologists to solve as he continues his regular research finding, naming, and describing millipedes new to science (he’s got 100+ under his belt, so far). 

Whoever takes up the border question will have their work cut out for them. Further mapping and investigation is hindered by the fact that parts of the border cross through pastures, farms and other private property, as well as unroaded and inaccessible wilderness. 

Original image
iStock // Ekaterina Minaeva
technology
arrow
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
quiz
arrow
Name the Author Based on the Character
May 23, 2017
Original image
SECTIONS
BIG QUESTIONS
BIG QUESTIONS
WEATHER WATCH
BE THE CHANGE
JOB SECRETS
QUIZZES
WORLD WAR 1
SMART SHOPPING
STONES, BONES, & WRECKS
#TBT
THE PRESIDENTS
WORDS
RETROBITUARIES