Contest Winners: Machine Learning On All Kinds Of Gadgets

With nearly sixty exciting entries, the Train All the Things contest, presented in partnership with Digi-Key, has drawn to a close and today we are happy to share news of the winning projects. The challenge at hand was to show off a project using some type of Machine Learning and there were plenty of takes on this theme displayed.

Perhaps the most impressive project is the Intelligent Bat Detector by [Tegwyn☠Twmffat] which claims the “ML on the Edge” award. His project, seen above, seeks not only to detect the presence of bats through the sounds they make during echolocation, but to identify the type of bat as well. Having been through a number of iterations, the bat detector, based on Nvidia Jetson Nano and a Raspberry Pi, can classify several types of bats, and a set of house keys (for a “control”). It’s also been impeccably documented and serves as a great example of how to get into machine learning.

The Soldering LIghtsaber takes the “ML Blinky” award for using machine learning in the microcontroller realm. This clever use of the concept seeks one thing: destroying the wait times for your soldering iron to heat up. It takes time to make temperature readings while the iron heats up, if you can do away with this step it speeds things up greatly. By sampling results of different voltages and heating times, machine learning establishes its own guidelines for how to pour electricity into the heating element without checking for feedback, and coming out the other side at the perfect temperature.

Rounding up our final two winners, the AI Powered Bull**** Detector claims the “ML on the Gateway” award, and
Hacking Wearables for Mental Health and More which won in the “ML on the Cloud” category.

The idea behind our illuminated poop emoji project is to detect human speech and make a judgement on whether the comment is valid, or BS. It does this by leveraging a learning set of comments that have previously been identified as BS and making an association with the currently uttered words.

Wearables for mental health is a wonderful project that was previously recognized in the 2018 Hackaday Prize. Economies of scale have made these wearables quite affordable as a way to add a sensor suite to behavior analysis. But of course you need a way to process all of the sensor data, a perfect task for a cloud-based machine learning application.

All four winners received a $100 gift code to Tindie. Don’t forget to check out all of the other interesting projects that were entered in this contest!

Tell Time Contest Winners: Clocks To Knock Your Socks Off

The results are in and the Tell Time Contest was a spectacular showing of creativity. Five winners and a number of runners-up have have been chosen based on craftsmanship, functionality, and creativity.

The one that’s going to steal your heart is Fetch: A Ferrofluid Display. Pitting the force of gravity against electromagnetism, this project manages to wrangle a liquid into the segments of a display and the animations used to change between numbers are fascinating. It’s a wickedly complicated system and the gang over at Applied Procrastination did a great job of documenting the research and development that went into building this open source marvel. Has anyone tried to replicate it? We’d love to hear from you in the comments!

Mechanical movements date back to the transition away from sundials and hourglasses, but these two modern takes on “clockwork” prove there’s still plenty of room for creativity. The first is a plotter that uses two servo motors and a UV LED to draw hours and minutes on a phosphorescent material.

The second is both minimal and a stunning mastery of a traditional clock mechanism. TORLO uses the voice coil from a hard drive to move the gears. It’s 3D-printed and does it all in plain sight, superb!

Fans of the Alien franchise will immediately recognize this insect-like “facehugger”, the second stage of a developing Xenomorph. Embracing the tradition of the Cuckcoo clock, at the top of the hour a “Chestburster” pops through the chest of the bust to mark the passage of time. Creepy but well executed.

The flip-dot display uses a beautiful home-etched circuit board to keep things tidy inside of the case. Of course the question with these displays is always “where did you get the flip dots?”. This panel is on it’s second life after serving a tour of duty as a bus info sign.

Runners Up and Eight Score of Entries

Congratulations to all of our runners-up in the Tell Time contest. It was a tight field with 160 total entries, each of them a fascinating take on the simple, yet very complex practice of watching the seconds tick away. Add this to your weekend bucket list as you’ll certainly get lost in the details of many of these projects.

These Projects Bent Over Backward To Win The Flexible PCB Contest

Back in March, the call went out: take your wiggliest, floppiest, most dimensionally compliant idea, and show us how it would be better if only you could design it around a flexible PCB. We weren’t even looking for a prototype; all we needed was an idea with perhaps a sketch, even one jotted on the legendary envelope or cocktail napkin.

When we remove constraints like that, it’s interesting to see how people respond. We have to say that the breadth of applications for flex PCBs and the creativity shown in designing them into projects was incredible. We saw everything from circuit sculpture to wearables. Some were strictly utilitarian and others were far more creative. In the end we got 70 entries, and with 60 prizes to be awarded, the odds were ever in your favor.

Now that the entries have been evaluated and the winners decided, it’s time to look over the ways you came up with to put a flexible PCB to work. Normally we list all the winners in our contest wrap-ups, but with so many winners we can’t feature everyone. We’ll just call out a few of the real standout projects here, but you really should check the list of winning projects to see the full range of what this call for flexibility brought out in our community.

Continue reading “These Projects Bent Over Backward To Win The Flexible PCB Contest”

Repairs You Can Print Contest: Meet The Winners

Six weeks ago, we asked you to show us your best 3D printed repairs for a chance to win $100 in Tindie credit and other prizes. You answered the call with fixes for everything from the stuff everyone has, like zippers and remotes, to the more obscure stuff, like amazing microscopes scavenged from dumpsters.

It was hard to whittle down the entries we received into the top 20 because you came up with so many awesome fixes. A few of them had us thinking hard about the definition of repair, but are brilliant in their own way.

So without further ado, we are pleased to announce the winners of our Repairs You Can Print contest. We also want to give honorable mention to those projects that wowed us with ingenuity.

Continue reading “Repairs You Can Print Contest: Meet The Winners”

Coin Cell Hacks That Won The Coin Cell Challenge

It’s amazing what creative projects show up if you give one simple constraint. In this case, we asked what cool things can be done if powered by one coin cell battery and we had about one hundred answers come back. Today we’re happy to announce the winners of the Coin Cell Challenge.

Continue reading “Coin Cell Hacks That Won The Coin Cell Challenge”

1 KB Challenge: And The Winners Are…

The 1 kB Challenge deadline has come and gone. The judges have done their work, and we’re ready to announce the winners. Before you jump down to find out who won, I’d like to take a moment to say thanks to everyone who participated. We had some incredible entries. To say that judging was hard is quite an understatement. Even [Eben Upton], father of the Raspberry Pi got in on the action. He created a new helicopter game for the classic BBC Micro. Look for writeups on the winners and many of the other entries in the coming weeks.

Grand Prize

brainfckThe grand prize goes to [Jaromir Sukuba] for Brainf*cktor. [Jaromir] went above and beyond this time. He created a computer which can be programmed in everyone’s favorite esoteric programming language. Brainf*cktor uses 1019 bytes of program memory in [Jaromir’s] PIC18F26K22. You can write, execute and edit programs. [Jaromir] ran into a bit of a problem with his LCD. The character tables would have thrown him over the 1 kB limit. Not a problem – he designed his own compressed character set, which is included in the 1019 bytes mentioned above. All the clever software takes physical form with a homemade PCB, and a case built from blank PCB material. Best of all, [Jaromir] has explained his software tricks, as well as included a full build log for anyone who wants to replicate his project. All that hard work will be rewarded with a Digi-Comp II kit from EMSL.

First Prize

mosFirst prize goes to [Dumitru Stama] with M0S – CortexM0 RTOS in 1024 bytes. Operating systems are complex beasts. Many of our readers have toyed with the Linux Kernel. But writing a real-time OS from scratch? That’s quite an undertaking.  [Dumitru] didn’t shy away from the challenge. He designed a Real-Time Operating System (RTOS) for ARM processors, written completely in ARM thumb assembly instructions. This is no bare-bones executive. M0S has a rich list of features, including preemptive task scheduling, mutexes, and inter-process communication. [Dumitru] even gave us memory allocation with an implementation of malloc() and free(). The OS was demonstrated with a NUCLEO-F072RB board from ST-Micro.

[Dumitru] didn’t just drop a GitHub link and run. He documented M0S with seven project logs and a 37-minute long video. The video uses electronic whiteboard drawings to clearly explain all the internal workings of the operating system, as well as how to use it.

[Dumitru] is the proud new owner of a Maker Select 3D printer V2!

Second Prize

1klaserSecond prize goes to [Cyrille Gindreau] with 1K Challange Laser. Vector lasers generally take lots of memory. You have to manage galvanometers, laser drive, and perform all the magic it takes to convert a set of vectors to lines drawn in space. The project uses 912 bytes of program and initialized data memory to command an MSP430 to draw an image.

Proving that flattery will get you everywhere, [Cyrille] picked the Hackaday logo as the subject. The Jolly Wrencher is not exactly simple to convert to vector format, though. It took some careful optimizations to come up with an image that fit within 1 kB. [Cyrille] wins a Bulbdial Clock kit from EMSL.

Third Prize

tinygamesThird prize goes to [Mark Sherman] with tinygames. Video games have been around for awhile, but they are never quite this small. [Mark] coaxed the minuscule Atmel ATtiny84 to play Centipede with only 1024 bytes of program memory. Even the BOM is kept small, with just a few support components. Control is handled by an Atari 2600 compatible joystick. Video is black and white NTSC, which is demonstrated on a period accurate CRT. [Mark] generates his video by racing the electron beam, exactly the same way the Atari 2600 did it.

[Mark] will take home a Blinkytile kit from Blinkinlabs.

Final thoughts

First of all, I’d like to thank the judges. Our own [Jenny List], [Gerrit Coetzee], [Pedro Umbelino], [Bil Herd], and [Brian Benchoff] worked hard with me in judging this contest. I’d also like to thank our community for creating some amazing projects. The contest may be over, but these projects are now out there for others to build, enjoy, and learn from.

I’ve wanted to organize this contest since [Jeri Ellsworth] and [Chris Gammell] took on the 555 contest way back in 2011. The problem is creating a set of rules that would be relatively fair to every architecture. I think 133 entries to this contest proves that we found a very fair set of constraints. It is safe to say this won’t be the last 1 kB Challenge here at Hackaday, so if you have ideas for future editions, share them in the comments!

Dtto Explorer Modular Robot Wins 2016 Hackaday Prize

Dtto, a modular robot designed with search and rescue in mind, has just been named the winner of the 2016 Hackaday Prize. In addition to the prestige of the award, Dtto will receive the grand prize of $150,000 and a residency at the Supplyframe Design Lab in Pasadena, CA.

This year’s Hackaday Prize saw over 1,000 entires during five challenge rounds which asked people to Build Something that Matters. Let’s take a look at the projects that won the top five prizes. They exemplify the five challenge themes: Assistive Technologies, Automation, Citizen Scientist, Anything Goes, and Design Your Concept. dtto-main-image-cropped

Dtto — Explorer Modular Robot

Grand Prize Winner ($150,000 and a residency at the Supplyframe Design Lab): Dtto is modular robot built with 3D printed parts, servo motors, magnets, and readily available electronics. Each module consists of two boxes, rounded on one side, connected by a bar. The modules can join with each other in many different orientations using the attraction of the magnets. Sections can separate themselves using servo motors.

Dtto is groundbreaking in its ability to make modular robots experimentation available to roboticists and hobbiests everywhere by sidestepping what has traditionally been a high-cost undertaking. While it’s easy to dismiss this concept, the multitude of different mechanisms built from modules during testing drives home the power of the system.


Affordable Reflectance Transformation Imaging Dome

Second Place ($25,000): Reflectance Transformation Imaging is a method of photographing artifacts multiple times with a fixed camera location but changing lighting locations. When these images are combined into an interface after the fact, it allows for different textures, surface features, and material properties to be observed. Currently there are no commercial version of hardware available for this technique.


Laser Cut Optics Bench

Third Place ($10,000): An optics bench is a series of jigs used to hold and precisely align elements for optical experiments. Traditionally this meant highly specialized equipment starting in the tens-of-thousands of dollars. But schools, hackerspaces, and individuals don’t need top-of-the-line equipment to begin learning about optics. The project has designed holders for salvaged optics and the ancillary materials to conduct experiments, and even includes a standardized carrying case design.


A New High Accuracy Tilt Sensor

Fourth Place ($10,000): This is a reimaging of a Linear Variable Differential Transformer (LVDT). Traditionally, tilt sensors based on LVDTs are built like a small tube with an iron core that can slide from one end to the other as the tube is tilted. This new sensor turns the tube into a hollow ring, and replaces the iron core with ferrofluid (a liquid with the properties of metal). What results is a brand new sensor with properties unavailable in previous tilt sensors.



Fifth Place ($5,000). Stepper motors are known for accurate movement, but they are often used as open loop systems and prone to lose track of position either from missed steps or outside interference. Mechaduino adds a high accuracy magnetic encoder to any of several commonly available stepper motors, closing that loop and adding functionality. This includes positional awareness, but goes for beyond to velocity and torque control, and user interaction.