Seeed Studio teamed up with Hackster.io to challenge the global engineering community to develop scalable, plug-and-play and easy-to-deploy solutions aimed at providing open-source development tools and alleviating some of the planet's biggest challenges.
Participants of the “IoT Into the Wild Contest for Sustainable Planet” combined Grove sensors with Internet of Things (IoT), artificial intelligence (AI) and edge computing to come up with novel ways to support sustainability. Over 100 entries ranged from monitoring greenhouse gasses around paddy fields to studying the migration of vulnerable species in the wild.
Partners of this challenge included: Project 15 from Microsoft, Zambezi Partners, Edge Impulse, Fab City Foundation, Institute for Advanced Architecture of Catalonia (IAAC), the Paradise International Foundation, Nova Labs and Helium Network.
Here are some of the winning entries, noteworthy for their innovation, potential to scale and utility.
EXCELLENT SUSTAINABLE & SCALABLE PROJECT AWARD
EARLY DETECTION OF ALGAE BLOOM
The award winners used sensor data and machine learning (ML) at the edge to detect early signs of harmful algae blooms and notify residents about local water conditions.
Harmful algae blooms—a phenomenon caused when some types of algae that produce toxins grow out of control—can wreak havoc on aquatic ecosystems and harm people and pets.
The inventors, Sashrika Das and her father, Mithum Das, built their device using a Wio Terminal, a microcontroller-based, fast prototyping tool, equipping it with multiple sensors to detect the presence of algae in water. Designing an alert system involves capturing and comparing many types of sensor readings. They used the Edge Impulse development kit to design a TinyML model, enabling machine learning at the edge.
To train the model to predict water conditions based on captured sensor values, they collected a variety of water samples as an initial dataset—with plans to add to it in the future. The device took readings hourly from TDS (total dissolved solids), turbidity and pH sensors. They use the TinyML model to classify the algae level as normal, warning or dangerous. The data transmits to the AWS cloud over the Helium Network using a LoRa module connected to the Wio Terminal. A RESTful API was also developed to allow third parties, such as town halls and public health agencies, to subscribe to the data.
As part of the contest’s grand prize offering, Seeed Studio is working with the creators to prototype and test a version of their solution using the Wio WM1110 Dev Kit with the intention of adding it to the Seeed Co-Create Licensing Program, potentially making it available through Seeed's official store.
INNOVATIVE & CREATIVE PROJECT AWARD
MONITORING OF ILLEGAL SAND MINING
We are running out of ways to legally mine wet sand without disturbing the coastline. So, in many third-world countries, sand is being supplied to industry through illegal means harmful to environment.
To stop illegal sand mining, the contest participants knew that governments needed a new way to identify and track the activity.
Enter MonSand, a device designed to detect illegal sand mining using vision AI. The solution captures photos and audio at suspected illegal mining sites and makes inferences about the type of equipment in use. This solution successfully leverages new edge-based machine learning developed by the inventor with existing IoT technologies available to everyone.
Inventor Raunak Singh trained a YOLOv5s model on visual classes such as excavators and dump trucks, then deployed the model on the Wio Terminal using the Grove Vision AI Module. With the Wio Terminal’s internal microphone, he also recorded volume levels. The AI module infers what type of machinery is present and the audio level indicates if it is operating. The results flow through the Helium Network to Google Sheets. After meeting preset thresholds, the solution uses the Google Sheets SMS extension to send a text message, advising stakeholders of potentially illegal mining activity.
INNOVATIVE & CREATIVE PROJECT AWARD
AI-DRIVEN TREE DISEASE IDENTIFIER WITH EDGE IMPULSE AND MMS
Due to climate change and excessive deforestation, trees and plants are becoming more susceptible to contagious diseases. Most tree diseases are fungal, brought on by drought, high carbon dioxide levels, overcrowding, and damage to stem or roots.
This project uses all the elements of the Seeed Studio SenseCAP K1100 kit, including the Wio Terminal and AI Vision Sensor, along with a LattePanda 3 Delta 864 SBC. The Wio Terminal logs environmental data captured using the Grove CO2 temperature and humidity sensors. Every five minutes, the Wio Terminal sends a command to the LattePanda 3 Delta via serial communication to capture tree images or run the object detection model.
Inventor Kutluhan Aktar leveraged Twilio’s API to set up a free, virtual phone number and send the images with its detected bounding boxes via multimedia messages (MMS). They gathered training data and assembled it into three categories: stem, branch and leaf. The data uploaded to Edge Impulse and classified by tree part created a FOMO (faster objects, more objects) detection model. Then, they deployed the application on the LattePanda3 Delta to run the model directly.
"Contagious fungal diseases due to deforestation and industrial wastewater in my hometown inspired me to create a budget-friendly and accessible solution," he said.
The solution when deployed remotely monitors trees in their natural environment. Kutluhan housed all hardware in a custom-made, 3D-printed enclosure designed with a forest theme.
Recent wildfires have restricted Kutluhan from using his local forest to improve the dataset. However, he is building a new project iteration that supports more biodiverse forests.
Hackster.io, an Avnet community, is the world's fastest-growing developer community for learning, programming and building hardware. With a global network of 2 million-plus innovators, hundreds of technology partners and 36,000-plus open-source projects, Hackster hopes to facilitate the creation of solutions that make the world a smarter, more connected place. Hackster.io and sister community, element14, run many design challenges throughout the year, featuring some of the newest and most innovative components and technologies.
ABOUT THE AUTHOR
Vice President, Americas Marketing
Avnet Americas Marketing Vice President Jessica Tangeman leads the Hackster team as its CEO. She’s a creative enthusiast and enjoys connecting innovators with the world while exploring opportunities for Avnet’s global supplier network.