Original image

The Bats and the Bees

Original image

By Deeann Reeder, as told to Jed Lipinski

SOUTH SUDAN, 2013—On our way into the Bangangai Game Reserve, a protected area of lowland forest and glades, we pass an open-air bushmeat market. It looks like any African vegetable market, except the tables are lined with rows of blackened monkey arms, as well as bushbucks, dik-diks, even pangolins—an endangered species. Hunting has existed here for thousands of years, but lately it’s become a commercial enterprise, emptying the forest of primates. And because Bangangai is near the Democratic Republic of Congo, cross-border poaching is a problem. We set up our tents on a high, grassy plateau in the center of the reserve, lush tropical rainforest sloping away on all sides. As night falls, gunshots echo in the distance.

I’m a bat biologist at Bucknell University. I survey a broad range of bat species to identify reservoir hosts, which harbor potentially fatal diseases like Ebola. But I’m also interested in mammal biodiversity, conservation, and understudied ecosystems—all of which brought me to South Sudan. After decades of civil war, the region finally declared independence in 2011, making it the newest country on earth.

It was in Bangangai a year earlier that my colleagues and I discovered a rare species of vesper bat rarely ever seen. When we established that it was a different genus—based on its black wings and badger-like white stripes—we renamed it Niumbaha, meaning “rare” or “unusual” in Zande, the local language. The discovery highlights the country’s extreme biodiversity.

In the morning, we capture shrews, set up camera traps for larger mammals, examine footprints. Our team consists of two Smithsonian scientists, two African ecologists, a photographer, a South Sudanese camp manager and diplomat, and a recent Bucknell graduate with an interest in the immunology. Darrin, who keeps at least three knives on him at all times, captures specimens with a technique we call the “meat dog.” He attaches a rope to a few pounds of meat and drags it on the ground for miles. Carnivores follow the scent. We identify the tracks.

By day two, however, our luck starts to run out. Our water supply is depleted, and the team is dangerously dehydrated. It takes hours to filter water from the murky pond nearby, so our porters—known locally as “arrow boys”—rush to a nearby village to stock up. They return with a dozen cans, but the water inside reeks of diesel. We’re so thirsty we drink it anyway. As a diabetic, I’m prone to bladder and kidney infections. Drinking diesel is not advised!

But the bees are the real problem. They’re not aggressive, but they’re everywhere—a fact of life in the reserve. Over the next week, we catch three more Niumbahas, some gorgeous bats with translucent wings, and a mongoose. In the process, I sustain a critical mass of bee stings on my left ankle, which swells up like a puffer fish, and I develop a kidney infection. I get dizzy and nauseous. Each night, gunshots get closer.

As dusk falls, mammals convene to drink from the murky pond. One evening, I’m at the water’s edge, manning my bat net, when a rifle fires a hundred feet away. I freeze, pissed off. Darrin appears out of the darkness. “We’ve got to go,” he says. No one objects. In a confrontation with poachers, our white skin would protect us. But I can’t say the same for our African ecologists, one of whom is Ugandan. An anti-Ugandan feeling pervades South Sudan.

Courtesy of Bucknell University

The next morning, we pack everything and begin a four-hour retreat to base camp in Yambio, home of the conservation group Fauna & Flora International. The arrow boys are furious at the poachers for cutting their work short.

I refuse to go to another game reserve, explaining that I’m leery of poachers. Our contact suggests Bandala Hills, a 10-hour drive north on the western edge of Southern National Park. There, park rangers set up a perimeter around us. “For safety,” they say.

In Bandala, we catch a variety of mammals, including epauletted fruit bats, nose-leaf bats, and horseshoe bats. By now my swollen ankle is seriously infected and my blood sugar astronomically high. I can barely stand up. Despite regular insulin injections, I come down with diabetic ketoacidosis, a potentially life-threatening condition in which the blood starts to acidify. We evacuate a second time.

It all happens in a blur: the flight aboard the 20-seat medevac plane; the arrival on the tarmac in Juba, the capital city; the drive to the Unity Clinic. They run some tests and prescribe an antibiotic. I sleep for about a week. Finally, my husband arrives from the U.S. and drives me to the “family compound”—we own a mud hut in Kajo Keji, just south of Juba—to recuperate.

There’s a good reason certain parts of the world are poorly studied. Many of my colleagues think I’m insane for working in South Sudan. The atrocities caused by civil war canceled our latest trip. But I’m willing to take the risks. For me, conserving wildlife goes hand in hand with community development and conflict resolution. So everyone wins. Just keep the bees away from me.

This story originally appeared in mental_floss magazine. Subscribe to our print edition here, and our iPad edition here.

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
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
Why Your iPhone Doesn't Always Show You the 'Decline Call' Button
Original image

When you get an incoming call to your iPhone, the options that light up your screen aren't always the same. Sometimes you have the option to decline a call, and sometimes you only see a slider that allows you to answer, without an option to send the caller straight to voicemail. Why the difference?

A while back, Business Insider tracked down the answer to this conundrum of modern communication, and the answer turns out to be fairly simple.

If you get a call while your phone is locked, you’ll see the "slide to answer" button. In order to decline the call, you have to double-tap the power button on the top of the phone.

If your phone is unlocked, however, the screen that appears during an incoming call is different. You’ll see the two buttons, "accept" or "decline."

Either way, you get the options to set a reminder to call that person back or to immediately send them a text message. ("Dad, stop calling me at work, it’s 9 a.m.!")

[h/t Business Insider]