CLOSE
Original image

The Big Squeeze: Scientist Catches Bear-Eating Snake in the Act

Original image

Burmese Python image via Shutterstock

Earlier this week a team of scientists from several universities and the US Geological Survey released a study documenting the dramatically declining numbers of small and medium-size mammals in Florida - including raccoons, opossums, white-tailed deer, bobcats, rabbits and foxes. These population drops all occur in the same areas where pythons and other large, non-native snakes have taken up residence after escaping from one stop or another in the wildlife trade supply chain.

Anyone who’s even heard only the most basic facts about constrictor snakes knows that they’re formidable predators and take down prey by grasping it in their powerful jaws, coiling their bodies around it, and squeezing until it suffocates. Devouring bunnies and possums isn't even the half of it, though. These big snakes aren’t shy about going after much larger, more dangerous game, too. Like men. And bears.

Skin of a 22.6-foot reticulated python, shot by Kekek Aduanan (in hat) on June 9, 1970. Photo by Thomas N. Headland

In the 1970s, anthropologist Thomas N. Headland lived with and studied the Agta Negritos, the indigenous people of the Philippines’ largest island. When Headland interviewed the Agta about their run-ins with the pythons that shared the rainforest with them, 15 of 58 men and 1 of 62 women said they’d been attacked by a python at least once. Two of the men had been attacked twice, and the interviewees could collectively remember six people who were killed by pythons, including a man whose son found the snake, cut it open and retrieved his father's body for a funeral (that snake is pictured above).

It Poked the Bear

In July 1999, conservation biologist Gabriella Fredriksson was monitoring a female Sun bear and her cub on the island of Borneo via radio collar. One morning, the collar’s signal indicated that the bear hadn’t moved for more than four hours, a sign that either the bear had died or the collar had come off. Fredriksson investigated and tracked the signal to the stomach of a 23 ft python curled up in the brush. The bulge of the adult bear could be clearly seen in the middle of the snake, and as the snake fled into a nearby stream when Fredriksson got too close, she could hear the sounds of the bear’s bones snapping. No sign of the cub was ever found.

The radio collar remained functioning, so Fredriksson tracked the snake over several weeks as it digested the bear. The snake was eventually captured, escaped, captured again and, when it hadn’t passed the radio collar out by October, the equipment was surgically removed. The snake was released into the wild soon after.

Granted, Sun bears are the smallest bear species and a little less fearsome than their cousins, feasting mainly on insects and fruit. It’s not nearly as impressive as a python eating a polar bear (ignore the improbability of that for a second and imagine how awesome that cage match would be). That said, they’re still not an animal that one attacks, kills and devours with ease. They’re sizable, have long, sharp curved claws, strong jaws and sharp teeth. Anecdotal evidence from Borneon residents suggests that tigers will take the occasional Sun bear, but this snake attack is one of only a few recorded instances of any bear species being preyed on by animals other than humans or other bears.

For more on Florida’s python problem, see the study and the coverage at Not Exactly Rocket Science, which has a great discussion in the comments about how unlikely it is that the pythons were so successful in establishing themselves in their new home.

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