Planet Arduino

At Arduino Day, I talked about a project I and my collaborators have been working on to bring machine learning to the maker community. Machine learning is a technique for teaching software to recognize patterns using data, e.g. for recognizing spam emails or recommending related products. Our ESP (Example-based Sensor Predictions) software recognizes patterns in real-time sensor data, like gestures made with an accelerometer or sounds recorded by a microphone. The machine learning algorithms that power this pattern recognition are specified in Arduino-like code, while the recording and tuning of example sensor data is done in an interactive graphical interface. We’re working on building up a library of code examples for different applications so that Arduino users can easily apply machine learning to a broad range of problems.

The project is a part of my research at the University of California, Berkeley and is being done in collaboration with Ben Zhang, Audrey Leung, and my advisor Björn Hartmann. We’re building on the Gesture Recognition Toolkit (GRT) and openFrameworks. The software is still rough (and Mac only for now) but we’d welcome your feedback. Installations instructions are on our GitHub project page. Please report issues on GitHub.

Our project is part of a broader wave of projects aimed at helping electronics hobbyists make more sophisticated use of sensors in their interactive projects. Also building on the GRT is ml-lib, a machine learning toolkit for Max and Pure Data. Another project in a similar vein is the Wekinator, which is featured in a free online course on machine learning for musicians and artists. Rebecca Fiebrink, the creator of Wekinator, recently participated in a panel on machine learning in the arts and taught a workshop (with Phoenix Perry) at Resonate ’16. For non-real time applications, many people use scikit-learn, a set of Python tools. There’s also a wide range of related research from the academic community, which we survey on our project wiki.

For a high-level overview, check out this visual introduction to machine learning. For a thorough introduction, there are courses on machine learning from coursera and from udacity, among others. If you’re interested in a more arts- and design-focused approach, check out alt-AI, happening in NYC next month.

If you’d like to start experimenting with machine learning and sensors, an excellent place to get started is the built-in accelerometer and gyroscope on the Arduino or Genuino 101. With our ESP system, you can use these sensors to detect gestures and incorporate them into your interactive projects!

The installation of Dmitry Morozov (:: vtol: :)”Wave is my nature” exhibited at the Mars center in Moscow is focused on the concept of Wave as the basis of all audiovisual art:

The project draws from the theory of Wave–particle duality which considers the light to be a particle and a wave at the same time. In this case, the notion of the “wave” is uniform for the sound wave, light wave and a “tangible” kinetic wave with wide amplitude, physically presented in the space as stretched cables moved by a system of motors. The piece also refers to the topic of physical modeling of the wave processes which take place in various media and materials: “string”, “data flow”, “visualisation of sound”, “sonification of light” etc. In general, the installation can be viewed as a kinetic spacial light installation which reacts to the presence of audience and creates an autonomous sound and light composition.

The artist used led strips, servo motors, 2-channel sound system, ir motion sensors running on Arduino Mega and Arduino Uno:

Prankophone  is the new interactive installation by Dmitry Morozov (his amazing projects have been featured on this blog ).  This time he created  a sound object, a hybrid of synthesizer, telephone and logic module:

The main principle of the object’s functioning is as follows: depending on the current mode, the apparatus calls to random or pre-defined recipients and plays them algorithmic melodies created from their phone numbers. The speakers transmit both the synthesized sounds and the sound from answering person. The common sound layer is involving a random recipient who doesn’t suspect anything. The person who answers the phone can’t hear any other sounds except for the synthesized ones.

You can play with it in 4 different modes:

– Autonomous mode –  it generates the numbers by itself and tries to reach them, and play them the sounds.
– Manual mode – when you dial any number by pressing standard phone keys it gets automatically transformed into sounds.
– Keyboard mode – mode of dialing the number on the one-octave keyboard where 10 keys correspond to 10 digits.
– Live mode – the number is defined by any of the previous methods, but the sounds are reproduced not automatically but from the keyboard, thus the user may “communicate” through sound with the person who answered.
It runs on Arduino Mega and you can listen to its sounds on the following video:

There’s a mineral called pyrite with a interesting nickname, fool’s gold, because it has a superficial resemblance to gold and it’s by far the most frequently mineral mistaken for gold. Even if it’s pretty abundant, there’s a rare form of pyrite which is crystallised in radial shape (as unusual disc spherulites), taking the shape of a disc. The amazing fact is that the only deposit where pyrites of such morphology are found is in Illinois (USA) and the discs are dated around 300 million years ago!

Dmitry Morozov (aka ::vtol::), a media artist living in Moscow, had the chance to use a pyrite disc and created Ra,  a sound object / synthesizer running on Arduino Nano. Ra uses laser for scanning the irregularities of the surface of the disc and further transforms this data to produce sound:

This project originated as a result of an interesting set of circumstances – a pyrite disc was given to me as a gift by a mineral seller in Boulder city (USA). Upon hearing about my works, she asked to do something with such crystal, and refused to take payment for getting it. In the same period, I was reading articles on various ways of archiving and preservation of sounds from the first, historical sources of the recorded sound – wax discs and other fragile carriers. All technologies were based on the usage of lasers. Inspired by these projects, I set out to create a self-made laser sound reader which would be able to produce sound from various uneven surfaces, using minimal resources to achive it. Thus emerged the idea to construct an instrument using the pyrite disc and a self-made laser sound reader.

The production of the object was possible thanks to the commission of the Sound Museum in St.-Petersburg which now has Ra in its collection.

Check the bill of materials and other details on Dmitry’s website. Explore other projects by Dmitry featured on Arduino Blog.

There’s a mineral called pyrite with a interesting nickname, fool’s gold, because it has a superficial resemblance to gold and it’s by far the most frequently mineral mistaken for gold. Even if it’s pretty abundant, there’s a rare form of pyrite which is crystallised in radial shape (as unusual disc spherulites), taking the shape of a disc. The amazing fact is that the only deposit where pyrites of such morphology are found is in Illinois (USA) and the discs are dated around 300 million years ago!

Dmitry Morozov (aka ::vtol::), a media artist living in Moscow, had the chance to use a pyrite disc and created Ra,  a sound object / synthesizer running on Arduino Nano. Ra uses laser for scanning the irregularities of the surface of the disc and further transforms this data to produce sound:

This project originated as a result of an interesting set of circumstances – a pyrite disc was given to me as a gift by a mineral seller in Boulder city (USA). Upon hearing about my works, she asked to do something with such crystal, and refused to take payment for getting it. In the same period, I was reading articles on various ways of archiving and preservation of sounds from the first, historical sources of the recorded sound – wax discs and other fragile carriers. All technologies were based on the usage of lasers. Inspired by these projects, I set out to create a self-made laser sound reader which would be able to produce sound from various uneven surfaces, using minimal resources to achive it. Thus emerged the idea to construct an instrument using the pyrite disc and a self-made laser sound reader.

The production of the object was possible thanks to the commission of the Sound Museum in St.-Petersburg which now has Ra in its collection.

Check the bill of materials and other details on Dmitry’s website. Explore other projects by Dmitry featured on Arduino Blog.

[vtol] is quickly becoming our favorite technological artist. Just a few weeks ago he graced us with a Game Boy Camera gun, complete with the classic Game Boy printer. Now, he’s somehow managed to create even lower resolution images with a modified typewriter that produces ASCII art images.

As with everything dealing with typewriters, machine selection is key. [vtol] is using a Brother SX-4000 typewriter for this build, a neat little daisy wheel machine that’s somehow still being made today. The typewriter is controlled by an Arduino Mega that captures an image from a camera, converts it to ASCII art with Pure Data and MAX/MSP, then slowly (and loudly) prints it on a piece of paper one character at a time.

The ASCII art typewriter was recently shown at the 101 Festival where a number of people stood in front of a camera and slowly watched a portrait assemble itself out of individual characters. Check out the video of the exhibit below.