johnkeefe.net

Shadoopy. Dango. Ray-Bella. Figgie.

If I told you those were names of actual dogs in New York City, would you believe me?

They're not. They were generated by a machine-learning algorithm mimicking dog names after it "studied" a list of 81,542 dogs registered in NYC.

The experiment, which took just a few hours Saturday, was something I've wanted to try since I saw the playful, awesome work of Janelle Shane and her experiments using neural networks to generate paint colors, guinea pig names and Harry Potter fan fiction.

I happened to have some free time, and decided to give it a shot. Along the way I:

• built, in mere minutes, a computer in the cloud powerful enough for machine learning
• made and played with a recurrent neural network
• learned a little more about machine learning
• had a lot of fun

The program generated lots of names, including many that existed in the original data. Once I filtered those out, I had almost 400 computer-created, mostly plausible dog names. Here are some of my favorites:

Rotson
Dudly
Lenzy
Murta
Cookees
Geortie
Dewi
Chocobe
Sckrig
Booncy
Cramp
Dango
Ray-Bella
Santha
Coocoda
Satty
Bronz
Shadoopy
Mishtak
Figgie
Grimby
Phince
Bum-Charmo
Soma
Blant
Snowflatey

If you'd like to geek out about how I did this, read on. You can do it, too.

Read more »

You can put Alexa in a Raspberry Pi, and that is pretty cool.

Alexa is Amazon's intelligent agent, like Siri for your living room. Standing nearby, you speak to it with a question or a command, and it responds verbally.

Normally Alexa lives inside a $180 device called an Amazon Echo, or the new $50 Echo Dot. But Emily Withrow at Northwestern University's KnightLab told me it was possible to put the Alexa code inside a cheap Raspberry Pi hobby computer. And I happened to have an old Pi lying around.

So I gave it a whirl!

Read more »

Several friends recently planned a party for maker, e-textiler and all-around awesome person Liza Stark — and I wanted to celebrate her with blinkies appropriate for the occasion.

The event was to take place in a rented house with a porch overlooking a slice of woods.

I decided to fill the trees with digital fireflies.

Read more »

How hot is a Harlem apartment?

We're trying to find out.

There are now DIY sensors in about 20 apartments, measuring the indoor heat and humidity -- in the middle of a heat wave.

It's the latest sensor journalism project from WNYC's Data News Team, in a collaboration with blog AdaptNY, community group WEACT and observation platform ISeeChange. 

And this week we worked with maker space HackManhattan, which hosted a soldering party to build more sensors.

Read more »

A summer of tinkering has culminated with a conductivity and temperature sensor that texts its data from inside a Gatorade bottle.

The contraption consists of a Riffle, which is an Arduino-like board designed to fit through the mouth of a water bottle and a Fona cell-phone board. And a bottle.

The plan is to submerge several of these along a stretch of the Monongahela River as part of a sensor-journalism class at West Virginia University. It’s a work in progress, but you can [see how things are going]. My job was to build a working conductivity sensor that would report its findings live. Here are the components and how I made it go.

Update: We actually deployed some of these sensors in a river!

Read more »

I always considered circuit boards like this something you bought, not something you made.

Not any more.

I actually helped to make the board in the picture above. And it was awesome fun.

The board is designed to monitor the conductivity (and, possibly, contamination) of water in lakes and streams, with the wonderful feature that it fits through the mouth of a regular water bottle. It’s called Riffle and it is the brainchild of Don Blair, who’s working with Public Lab and the MIT Center for Civic Media. This week I had the honor of working with Don at MIT.

Read more »

Visualizing one’s heartbeat is just cool. I’ve been into the idea since I learned that signals sent by the Polar heart monitor straps joggers use can be detected with a cheap device.

I’ve made a heartbeat hoodie, which was a lot of fun. But in the end, a bright, flashing sweatshirt starts to annoy the people around you. Now I’m working toward a more wearable wearable, one that changes subtly as my heart beats faster or slower.

This week I took a step on the way to that wearable by getting three LEDs — blue, green and yellow — to light up according to my heart rate. A calm heartbeat and blue glows, a little faster and you get green and really fast lights the yellow one.

Read more »

We have a moderately successful family fish tank: The fish seem to survive, the plants do not.

(Also we’re really good at growing algae, and may start feeding it to the children.)

With a coding problem, you Google it and get several excellent solutions. With a fish tank problem, you Google it and get several excellent solutions that contradict each other.

So the excellent solution we’ve chosen to make the plants happy is to add carbon dioxide to the tank. Plants need it, and one of my favorite in-store tanks uses it. So it's settled.

I thought I’d need to pick up a heavy tank of CO₂, like when I rented a tank of helium.

Turns out you can coax yeast to make it for you. This Instructable describes how, and is what I used to make ours.

Read more »

The same week we got details about the new Apple Watch, my Nike Fuelband died.

That got me thinking about what I really want — and don't want — on my wrist, and whether I could build something that fit my needs exactly.

So expect a few #MakeEveryWeek weeks devoted to iterations of a fitness watch. This is one of them.

My Fuelband had a clock, which I used for timing my midweek runs of about 20 minutes (don't judge). But I had to keep checking my wrist, and pressing a button in the band, to see if time was up.

I really wanted something to simply tell me when 20 minutes was up. So that's what I made.

Read more »

This is a snapshot of my town — taken yesterday.

It is crazy-amazing that I can get an image from space on my computer in damn-near real time.

The camera is Landsat 8, a U.S. Geological Survey satellite with a dozen sensors on it. I got an introduction to using satellite imagery at the NICAR 2015 Conference in Atlanta last week, so I thought I’d give it a whirl for this week’s #MakeEveryWeek.

I wondered if I could see from space the lovely thaw we had the past couple of days, with highs hitting near 60.

Read more »