Original image

Frogs Use Storm Drains for Better Mating Calls

Original image

As humans take up ever more space and urbanize the untamed wilderness, the animals that call these places home have a tough choice to make: move on to someplace else or adapt to their new surroundings.

Staying put can be especially tricky for animals that rely on sound to communicate with each other and steer clear of danger. Brick walls and human-made noise can change the acoustic landscape and drown out their mating calls or mask the sounds of approaching predators. In Taiwan, plucky little frogs are making the most of things. Instead of letting human infrastructure get in their way, they’re putting it to use. 

In suburban and rural areas of Taiwan, it’s pretty easy to find open concrete drains alongside roads and foot paths. Their bottoms are often caked in mud and covered in plant litter. This makes them attractive to small animals as travelways, mating sites, and even living space. But the concrete walls can make conversation difficult by causing sounds to ricochet and echo. Animals listening for each other's calls “will hear not just the direct sound wave, but also reflected waves arriving at different times,” say a team of researchers at National Taiwan University in Taipei.

But there’s an upside to that, depending on who’s doing the talking. “In contrast, some signals (e.g., those with narrow frequency bandwidths) can potentially benefit from reverberations,” the researchers say in a new paper. “The reflected sound waves can make the signal higher in amplitude and longer.” Mientien tree frogs seem to have figured this out, and the males are often found perched in the drains letting out their high pitched mating calls to attract females. 

When the team compared the calls of the frogs in the drains with those that sat next to them on the ground, they found that the drain calls were louder and longer. The echoes caused by the concrete didn’t degrade the calls. Instead, the researchers say, the drains acted like “miniature urban canyons” and actually amplified the narrow-bandwidth calls.

While the researchers didn’t look at how female frogs responded to the calls in this study, they suspect that the drain-aided calls are just what they want to hear. Other research has shown that female frogs and other amphibians are more attracted to long, loud calls. 

Hanging out in drains isn’t all fun and frog flirting, though. It also presents some challenges. The first is that the shape of the drains and the shelter they provide attracts snakes that can hide in the muck and ambush unwary prey. Many of the frogs seem to get around this by perching on branches leaning against the drain walls so they’ve got a good view of their surroundings. 

Another problem is that the steep concrete walls can be difficult to maneuver. Mientien tree frog mating involves the female carrying the male away from his calling perch to a damp place to reproduce, and the females might have a hard time hauling the males out of the drain. Whether that leads a lot of females to abandon males in the drains without mating or even ignore drain callers in the first place remains to be seen. For now, at least, the drain-as-megaphone looks like a clever workaround for tree frogs looking for love. 

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