How People Get Hurt in All 50 States

Medical codes can get incredibly specific. When you go to the hospital, the doctor won’t just enter your diagnosis as “concussion” or “traffic accident”—you’ll go into the system as suffering from an “animal-drawn vehicle accident” or having been in an “unarmed fight or brawl.” The beauty of these medical codes is that you can track exactly how many people went to the hospital after crashing their horse-drawn buggy. The healthcare search site Amino recently did exactly that, finding out the causes of a disproportionate number of injuries in every state through health insurance claims.

Amino’s researchers combed through 244 million health insurance claims in its database between 2012 and 2016, looking for the injuries that stuck out in each state compared to the national average. Tennessee, for instance, sees 1.6 times more injury diagnoses related to motor vehicle crashes than the national average.

The data (larger image here) represents only injuries that were reported and recorded by doctors, so it’s possible that a ton of people get in fist fights in places other than New York but just don’t go to the doctor for it. The data is simplified so that the 3000 medical codes for physical injuries down are combined into 170 common terms, like calling all 38 types of contusions “bruising.”

Amino found that New York is home to over 10 percent of the medically documented fist fights (the aforementioned unarmed brawls). There were 35,000 New York fist fight injuries diagnosed during the period analyzed, compared to around 296,000 nationally. Indiana’s most disproportionately common injury is “struck by object.” Rural states like Montana, Wyoming, North Dakota, Idaho, and Nebraska were home to a disproportionate number of the 43,000 “animal-drawn vehicle accidents” across the country—with 1000 (two percent of the national total) taking place just in Nebraska. Hawaii sees far more patients after “near drowning” than other states, as you might suspect of a state surrounded by water.

The major question is, what’s happening to people’s faces in Louisiana? And why are Missouri’s animals so dangerous?

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
Here's How to Change Your Name on Facebook
Original image

Whether you want to change your legal name, adopt a new nickname, or simply reinvent your online persona, it's helpful to know the process of resetting your name on Facebook. The social media site isn't a fan of fake accounts, and as a result changing your name is a little more complicated than updating your profile picture or relationship status. Luckily, Daily Dot laid out the steps.

Start by going to the blue bar at the top of the page in desktop view and clicking the down arrow to the far right. From here, go to Settings. This should take you to the General Account Settings page. Find your name as it appears on your profile and click the Edit link to the right of it. Now, you can input your preferred first and last name, and if you’d like, your middle name.

The steps are similar in Facebook mobile. To find Settings, tap the More option in the bottom right corner. Go to Account Settings, then General, then hit your name to change it.

Whatever you type should adhere to Facebook's guidelines, which prohibit symbols, numbers, unusual capitalization, and honorifics like Mr., Ms., and Dr. Before landing on a name, make sure you’re ready to commit to it: Facebook won’t let you update it again for 60 days. If you aren’t happy with these restrictions, adding a secondary name or a name pronunciation might better suit your needs. You can do this by going to the Details About You heading under the About page of your profile.

[h/t Daily Dot]