Original image
gravitytank / Project Pasteur

How Good Design Can Save Lives

Original image
gravitytank / Project Pasteur

Lately the news has been full of outbreaks of diseases that could have been prevented by vaccination. Using an interactive map you can explore outbreaks of whooping cough, measles, mumps, and other vaccine-preventable diseases across the world—including the United States, where access to vaccines should be quite easy. The map is based on news stories, and you can click on each point to read the story backing it up.

Just one example: in 2013, the U.S. saw 189 cases of measles, more than triple the typical 60 cases per year. The reason? Many kids are not being vaccinated.

The United States has a proud history of inventing vaccines and keeping our kids healthy. When Jonas Salk invented the first polio vaccine, children were given Polio Vaccine Cards that recorded the dates it was delivered. These cards served as a record (and a reminder) that protection from polio required multiple rounds of dosing (by 1962 the oral "Sabin vaccine" was favored, and delivered in three doses). But childhood vaccinations went far beyond polio; kids who traveled were vaccinated against a laundry list of wild diseases, and those records were often kept with the child's passport. These days, the vaccination schedule is rather complex. (Fun test: look at that schedule and try to figure out whether you've received all of those vaccinations. I can only point to a few that I know for sure I have received—I'd have to go back through a pile of medical files to track down the rest. Now multiply this problem by every living person and you see the scale of the issue.)

Today in the U.S., most doctors use electronic records to keep track of things like vaccination (though the CDC offers a paper record you can use if you wish). But in much of the world, paper immunization records kept by parents are still the standard—even though they must track a dozen or more vaccines, often delivered in multiple doses with specific time intervals in between. Paper records are cheap, portable, and require no electricity. What's more, a paper record can have extra information printed on it, like instructions on how to care for a baby and when to expect certain milestones on growth and development. But some of these strengths are also weaknesses: paper can be ruined by a little rain; text about childcare is useless to the illiterate; and a small bit of paper is easy to lose or forget. If the record is ruined, lost, or misused, that really can be life-threatening. While immunization programs are succeeding around the world, there's still room for improvement.

Here's an example of an immunization card used in Bolivia, which has successfully fought rotavirus via vaccination:

Image courtesy of National Immunization Card Repository.

And here's one introduced in 2010 in the United Republic of Tanzania (which began using several important new vaccines in 2012):

Image courtesy of National Immunization Card Repository.

Enter the Records for Life Contest, a challenge in which designers were asked to rethink and redesign these paper records. (More details in this PDF.) The solution space was broad, and more than 300 teams submitted new designs. The grand prize went to Project Pasteur, designed by members of the consultancy gravitytank. While 10 other winning designs have interesting characteristics, Project Pasteur includes some truly transformative design features.

To me, Project Pasteur's most exciting feature is the inclusion of a child's photograph on the front of the folder containing the health record. By giving parents a photograph, the health record is turned into a keepsake, and something that is likely to be displayed rather than tucked away somewhere. Further, Pasteur uses icons with minimal text to explain basic childcare information, and a simple chart to explain which diseases are covered by which vaccines. In other words, the design shows the benefits of vaccination rather than simply telling a parent they're important. You can learn much more about Project Pasteur in this slideshow:

For a look at another top-ten finalist, check out The Picture of Health by Trip O’Dell and Umberto Fusco.

All of the designs in the Records for Life challenge are still prototypes. The next step is to work with health officials in developing nations to find the best features of each design, creating new health records that can be tested—and help save children's lives around the world.

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