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.
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.
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!
Is there a cool Internet of Things idea that you’ve wanted to try out with your Arduino, but just haven’t had time for? Building a network that integrates multiple sensors and boards into one cohesive application can be time-consuming and difficult. To make it a bit easier, Temboo just introduced new Machine-to-Machine programming that lets you connect Arduino and Genuino boards running locally in a multi-device network to the Internet. Now, you can bring all the power and flexibility of Internet connectivity to Arduino applications without giving up the benefits of using low power, local devices.
Our friends at Temboo now support three M2M communication protocols for Arduino boards: MQTT, CoAP, and HTTP. You can choose which to use based on the needs of your application and, once you’ve made your choice, automatically generate all the code you need to connect your Arduinos to any web service. You can also save the network configurations that you specify, making it easy to add and subtract devices or update their behavior remotely.
With Temboo M2M, you can program flexible distributed device applications in minutes. From monitoring air quality and noise levels in cities to controlling water usage in agricultural settings, networked sensors and devices enable all sorts of powerful IoT applications. You can see it all in action in the video below, which shows how they built an M2M network that monitors and controls different machines working together on a production line.
A few months have passed from the launch of the internal betatesting of Arduino Create. We are finally ready to open up the number of people who can use and experiment with this online platform. Today each betatester currently in the program has received 5 invites to get other Arduino tinkerers on board, we have also added about 100 people who tried the platform during Maker Faires and other events, or expressed interest online.
Most importantly we have a public waiting list for anyone who wants to try Arduino Create before hand and give us feedback. You can SIGN UP here, the first 100 people will receive an invite right away, we will add the other subscribers as the betatesting unfolds.
The Arduino Create Editor has most of the Arduino Desktop IDE features, it is a fully functional Editor, and you can start developing your projects on it right away. We are really close on having everything delivered in HTTPS, we are working hard to add the Library Manager and support for all the Certified and AtHeart boards. Next in our roadmap is including a Sharing feature and a Chrome OS plugin.
As already said in the past, we are always going to provide our community with a offline solution, so don’t worry
When you use Arduino Create for the first time you will be prompted to install a plugin (agent). While your Sketchbook and the apps are hosted in the Cloud, the plugin will locally check the USB ports on your computer. The plugin detects if any board has been connected, if you are uploading a sketch, or you are using the Serial Monitor. The Arduino Create agent is open-source, and available for Mac, Windows and Linux! If you find it interesting you can contribute to it or fork it to use it in your projects.
We are currently working on a brand-new tutorial platform, Arduino Create Projects, in collaboration with Hackster.io. We are planning to release it at the beginning of 2016. Arduino users will finally have a place where they can share their own projects and include step by step guides, schematics and layout references, pictures, videos, the code they wrote, and useful links and comments. We can’t wait to share it with you all so stay tuned!
A few months ago, I published post about DPA .NET Class. This article describes simple, but effective library used for DPA handling by MCU (UART interface). Published library is independent on the MCU family, but it was written for 32-bit ARM processors with Cortex-M3 core and GNU C compiler.
Library consists of two files:
We are pleased to announce that KiCad has finally made a 2015 release branch. The 2015 stable release of KiCad will start from version 4.0.0. Currently we are in the release candidate phase and as such BZR 6188 is now known as 4.0.0 RC1.
The 4.0 branch can be found here: KiCad 4.0 Branch
The RC1 branch has been packaged as a archive available here: KiCad 4.0.0 RC1 Archive
The new GUI translations can be found in the kicad-i18n repository on github.