Read the article here:

Introducing Deep Learning and IoT to First-Year Engineering Students with MATLAB

l

On Friday, October 26, 2018, the University of Louisiana at Lafayette opened its doors to over 900 students participating in Science Day. This is a campus-wide event where high school students throughout Louisiana come to visit university’s various science departments. Our department, the College of Computing and Informatics, put on four demos for students to partake in.

The Association of Computing Machinery – Women (ACM-W) club, an organization dedicated to increasing the number of women in tech, decided we should do something different than the previous year for our demo. Our organization’s advisor, Dr. Sonya Hsu, gave us the idea to try a Deep Learning and IoT, Internet of Things demo presented at Grace Hopper Celebration of Women in Computing this past September by the team from MathWorks. With the help from the MathWorks GHC team and colleagues, we were able to put on this spectacular demo at the Science Day at the University of Louisiana. You can read about the GHC 18 Deep Learning and IoT workshop here on this blog.

We gathered all of the required tips from Anoush Najarian of MathWorks, configured all of our laptops, and put together an informal and interactive presentation. And we had our students very entertained! They really enjoyed taking photos of the fruit (and sometimes themselves) in order to see how and which objects were classified. Students kept taking photos until their fruit was correctly labeled, seeing how holding the object in a certain position or light would affect the MATLAB program’s answer.

We did notice that with smaller groups, it was easier to help everyone and keep control of the room. This made the demonstrations and feedback sessions a lot more educational: in larger groups, most people could not get most of their questions answered in the allotted time. But, the interactive segment of the demo did make up for it.

Meanwhile, the MathWorks team in Boston could keep up with what we’re doing by looking at the data collected on ThingSpeak and analyzing it with MATLAB – that’s IoT in action!

This was an amazing outreach opportunity for our organization that could not have been executed without the help of the MathWorks team! The positive feedback and help really made this an enjoyable experience for my team, and we hope to partner with MathWorks in the future.

You too are welcome to use our GHC 18 Deep Learning and IoT workshop materials, and share your thoughts in the comments! Check out the work of awesome women in engineering and science we have been highlighting with the #shelovesmatlab hashtag!

Setting up the Sensor

This project uses the ESP-based NodeMCU as an IoT gateway to forward sensor data to ThingSpeak. The NodeMCU is essentially a microcontroller and a Wi-Fi device that costs less than $10 US. The humidity sensor that is used in this project is the DHT11. This a very common sensor used to monitor temperature and humidity. The sensor either comes in a 4 pin or 3 pin package. The NodeMCU is programmed with the Arduino IDE using the code in Douglas’ tutorial or GitHub.

Using ThingSpeak Metadata

Douglas uses the metadata setting within a ThingSpeak channel to store condition ranges. This allows you to adjust settings in your online analytics code without redeploying new code. Each ThingSpeak channel has a metadata setting. You can store arbitrary text data that can be used in your MATLAB Analysis code. To load your channel’s metadata into MATLAB, use the webread function and add metadata=true to the ThingSpeak API Read Data request.

indoorChannelData = webread(strcat('https://api.thingspeak.com/channels/', ...
                                    num2str(indoorChannelID), ...
                                    '/feeds.json?metadata=true&api_key=', ...
                                    indoorChannelReadKey));

Using MATLAB for Condition Monitoring

Douglas uses MATLAB on ThingSpeak to determine the proper condition. This is a common requirement in complex IoT systems. This example could be a good starting point for building a condition monitoring system for industrial maintenance applications. You use MATLAB to determine the target humidity using a polynomial fit over the lookup data.

lookupFit = polyfit(humidityLookup(:, 1), humidityLookup(:, 2), length(humidityLookup) - 1);
optimalHumidity = polyval(lookupFit, curTempOut);

humidityDiff = curHumidity - optimalHumidity;

Using IFTTT for Alerts

Often you want to get notifications when a certain condition is met. Douglas shows you how to use IFTTT to send push notification directly to your phone. In this project, MATLAB is determining the condition and then interfaces with the IFTTT API to send the push notification. To send push notifications via IFTTT, use the webwrite function in MATLAB.

webwrite(strcat('https://maker.ifttt.com/trigger/', makerEvent, ...
                '/with/key/', makerKey), ...
                'value1', stateMsg, ...
                'value2', char(timeSinceChange, 'hh:mm'));

All of the MATLAB code can be deployed on ThingSpeak and scheduled to be executed periodically without having this on your desktop computer. The complete Smart Humidity Sensor project tutorial is available on Hackster.io. Feel free to discuss on the MATLAB Maker Community.

Statistics and Machine Learning Toolbox

Signal Processing Toolbox

When you are logged into ThingSpeak using your MathWorks Account, you can use functions from the following toolboxes if you are licensed to use them:

The Top 10 Internet of Things Countries*

1. United States
2. India
3. Germany
4. United Kingdom
5. Italy
6. Brazil
7. France
8. Poland
9. Canada
10. Spain

*According to ThingSpeak Usage Stats

The project uses a Raspberry Pi 2 and USB webcam acting as a sensor. The webcam picks up traffic flowing in both directions. Once the algorithm for detecting cars is modeled in Simulink, the algorithm gets deployed on the Raspberry Pi. The Raspberry Pi sends the raw data to ThingSpeak on regular basis where it is analyzed using the MATLAB Analysis app on ThingSpeak.

After sending to ThingSpeak, Eric created a MATLAB Analysis app to calculate the daily traffic-volume on ThingSpeak Channel 51671. Now that the data is public, others could use this processed data within apps such as Waze to optimize directions using analyzed traffic flows.

Check out the article for the complete project details and all of the code to get your Raspberry Pi + ThingSpeak analysis project started.

Hackaday.com wrote an article about Vegard’s soldering iron connected to the Internet of Things. Here’s what they had to say:

The data pushes out to the ThingSpeak server which handles pushing data out to the bigger network, and data representation (like the cool Google gauge…). The best part: [Vegard] gets a phone notification when he accidentally leaves his soldering iron on. How perfect is that?

That looks a lot like our desks… wires, microcontrollers, pliers, cutters, Wi-Fi modules, and soldering irons. And now, the soldering iron is on the Internet of Things.

[via Vegard Paulsen / Hackaday.com]

Greg built the project out of necessity to help his plants suffering from “localized drought”. Let’s hope his plants get proper watering and that other ThingSpeak users can quickly and easily build this project. Thanks for sharing!

[via Instructables]

“We switched to SSD drives for all of our database servers,” said Lee Lawlor, Lead Engineer of ThingSpeak. “All of the upgrades are live and available to the entire ThingSpeak Community!”

The improvements decreased response time dramatically and improved large data set retrieval by ten times.

The idea is that it is frustrating waiting for luggage at the airport and wondering where it is and why it is not on the baggage carousel. With this project, you can track luggage from start to finish. The advantages are not only for the traveler, the airlines could track luggage as well and get quality statistics for each airport. And, the base system has many applications outside of travel such as the Automotive Industry.

Chris explains the project really well on his blog and with a YouTube video.

As more and more users create TweetControls, the service started slowing down. We have enhanced how the service works and now you get instant TweetControls!

In an Instragram video sending a Tweet and changing the CheerLights color, you will see that there is little delay between sending the Tweet and executing the control command to change the colors on his Christmas tree.

Learn more about TweetControl on ThingSpeak Docs.

We keep hearing about how many Billions and Billions of things there will be connected. Just think about how much data that they will create! Yep, it’s Big Data, or even, Bigger Data. ThingSpeak is the only open data platform specifically designed for the Internet of Things available ‘in the cloud’ or on your own network to capture and distribute data from things.

A new homepage for ThingSpeak

When we look out into the Cosmos, we see Billions and Billions of stars and keep a fond memory of Carl Sagan in our hearts. As we connect this planet, we can’t but think of the scale and the magnitude that IoT will bring. Using this inspiration, we launched the new ThingSpeak.com!

Carl Sagan said, “We have lingered long enough on the shores of the cosmic ocean, we are ready at last to set sail for the stars.” We believe the same about the Internet of Things! Let’s get going!

Mi Humidor de Cigarros conectado a Internet por medio de un Arduino

We want to send a special thanks to powermik, oiotoshi, sekjal, and akinsgre for contributing new code and reporting bugs.

All of the latest code is available on GitHub, so start building your own Internet of Things today!

Duke says,

“A demo of how to use ThingSpeak (an IOT web site) with a Gadgeteer Gas Sensor Device. Data from the sensors are displayed in real time on ThingSpeak and using some of ThingSpeak’s cool features the Gas Sensor device can send out Tweets for Alert and Alarm conditions.”

Another awesome part of this project is that it uses .NET Micro Framework library, μPLibrary 1.8, created by [paolopat]. This library makes it really easy to tap into ThingSpeak web services by embedded devices. It’s great to see different parts of the project coming together from multiple ThingSpeak users. We appreciate the creative combinations and the efforts that you are putting into your projects. Thanks!

For more information, check out the live sensor readings on the project’s ThingSpeak Channel and download the complete source code at Codeshare.

[via >TinyCLR Forums]

Since the project release, there has been much activity. A part from CheerLights being discussed on blogs like MAKE and Lifehacker, the community has created some interesting bits of tech that extend the project further than lights. So if you don’t have a way to connect your lights together with CheerLights, you can connect your mobile phone, browser, and web sites together by subscribing to the CheerLights feed. Right now you can check the latest CheerLights color with an Android App created by @ChrisLeitner. Another really neat thing is a browser plugin for Chrome designed by Josh Crumley. So, in the top corner of your web browser you can see the latest color in an unassuming way. It’s a little reminder that we are connected.

To join CheerLights, all you have to do is build something that subscribed to the CheerLights ThingSpeak Channel or access the data using JSON and XML. You can also use the apps, browser plugins, or web widgets to see the colors. Visit the CheerLights website hosted on Tumblr for details on making a controller with Arduino, ioBridge, or Digi’s ConnectPort.

To control CheerLights, just send a Tweet to @CheerLights and mention a color.

Just think when you send this Tweet that you are updating 1000’s of lights, apps, browsers, and widgets all at the same time.

Spread some cheer…

[via MAKE / Lifehacker / CBC / ioBridge Projects]

We have created a new ThingSpeak Sketch for Arduino 1.0 that you can use for the Arduino and Ethernet Shield or the Arduino Ethernet all-in-one. All you have to do is add your ThingSpeak Write API Key to the sketch, upload to the Arduino, and connect to your network. The sketch includes automatic network configuration with DHCP, domain name resolution using DNS, a watchdog / reset function to keep the Arduino online, and a function to update ThingSpeak Channels. The new sketch has been running without hiccup in our lab for few weeks. We hope that you get the same reliability. Go ahead and copy, transform, and combine…

View Arduino 1.0 –> ThingSpeak Sketch on GitHub

Over the past few months of getting ThingSpeak to full speed, we have been inspired by the outpouring of projects and interaction with the open hardware community. So far, we announced integration with openPICUS which allows developers to create a completely open source wireless solution for the Internet of Things. There are many more announcements coming soon…

Come join us at the Open Hardware Summit!

Sponsorship opportunities are still available. Check out OpenHardwareSummit.org for more information.

[via Twitter]

The mashup community ProgrammableWeb indexed the ThingSpeak API and the ThingSpeak Chart API. We entered the category of “Other”. Just imagine what web developers will create now that they have the Internet of Things at their fingertips.

[via ProgrammableWeb]

[Elad Salomons] of OptiWater noticed that his house water pressure was 9 bars and this set him on a collision course with the Internet of Things. In his research he discovered ioBridge and ThingSpeak. He was able to connect sensors to the web, visualize the data, and come up with a few ah-ha’s in the process.

Elad is enjoying the process so much that he wanted to share the learning experience with you. He has created a contest based on some sensor data he has collected. You can look at the data and download historical data over at his Water Simulation blog to see if you can explain the correlations. You have until June 30, 2011 to figure it out. Visit Elad’s blog for more information or look him up on Twitter. $100 to learn something? That’s awesome!

[via Water Simulation / ioBridge]

I’ve been following the concept of an “Internet of Things” for a few years now and it’s definitely something else that’s heating up! Whether as citizens as sensors or being able to ‘Google your keys‘ bridging the technology most of us take for granted now, the Internet, into the physical realm holds tremendous promise.

However, we know there’s more to it then running an Ethernet cable to your car, or plugging in your teddy bear. The networks we take for granted now, despite their vast capabilities, weren’t designed for this new wave of connectivity. This is especially apparent with the coming exhaustion of IPv4 (an estimated 5 days remaining at the time of this writing)!

Considering all the new protocols, tools, and interfaces that need to be created, I find it fascinating to watch how people are integrating technology into their every-day lives, and it’s surprising how many cool ways these are put to use. As we increasingly rely on connected devices, or come up with new ways to integrate existing systems, will we truly have control or do we risk being locked into the betamax of our generation?

Guys like Bruce Sterling are famous for tracking the future and guys like Linux Torvalds are famous for creating it, or at least the tools people use to build it. What do you see on the horizon, and what will you invent to make it so?

We’re excited to have you here at ThingSpeak to help us make this reality our own.