HACKSTER.IO PRESENTS
POWERED BY
Throughout the last year, we hosted monthly activities for developers to take their skills to the edge with the Edge Impulse platform for a chance to win prizes. Check out the activities we hosted below and find resources that showcase the endless possibilities of using Edge Impulse in your projects.
Keyword spotting, otherwise known as wake word detection, is a form of voice recognition that allows computers to listen for and respond to specific words. In keyword spotting, a device listens for a keyword or phrase and triggers an action based on what is spoken. Review the resources below to gain a better understanding of this popular technology and learn how to train a device to recognize your own keyword or phrase.
The Raspberry Pi Pico is a low-cost development board that use a microcontroller (Cortex-M) processor. The Pico (and brand-new Pico W) are low-power, small devices that have more modest capabilities than a regular Raspberry Pi, but excel when it comes to size, battery life, and ease of prototyping. With 264kB on-chip SRAM and 2MB on-board flash, the Pico can even run lightweight tinyML models for basic sensor-driven AI workloads.
The Arduino Nano 33 BLE Sense is one of the most feature-packed Arduino boards, with a built-in temperature sensor, accelerometer, gyroscope, and microphone (and more). This makes it a great platform for building monitoring and sensing projects and devices. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the Edge Impulse Studio.
The ESP32 is a small, low cost microcontroller with bluetooth and WiFi connectivity, making it ideal for IoT products and applications. It's dual-core processor is strong enough to run TinyML models, opening up endless possibilities for building smart sensors, wearables / health devices, basic vision applications, and more.
The Espressif ESP-EYE development board based on Espressif's ESP32 chip is fully supported by Edge Impulse. The ESP-EYE is equipped with a 2-Megapixel camera and a microphone making it perfect for image recognition and audio processing applications.
In most cases, data is the most important factor in creating a successful TinyML project. Sure, hardware selection, power, and connectivity matter too, but without good training data, your model likely won’t be accurate enough to perform it’s intended function out in the world!
The team at Sony has created a small but powerful microcontroller board that is ready to run Edge Impulse machine learning models. With 6 Arm Cortex-M4 cores, 1.5 mb of RAM, GPS, camera input, onboard audio, and plenty of expansion options for sensors, WiFi, cellular and more, the Spresense can be used in a wide variety of projects.
Many times, we focus on performing machine learning locally on-device, with no need for internet connectivity. This reduces latency, simplifies projects, and can sometimes reduce costs. However, some projects do require connectivity to the cloud in order to set a status, update a dashboard, log an activity or event, or allow a user to interact with a device.
When deploying smart devices in certain environments your available space and power requirements may be limited. The Silicon Labs xG24 Developer Kit is a sensor-rich platform for prototyping AIoT devices, able to run TinyML models on just a coin-cell battery. With a dedicated AI accelerator, 6 onboard sensors, BLE, and a compact board, the xG24 can fit in tight places and capture a wealth of environmental information.
Edge Impulse makes it easy for beginners to add machine learning to their projects, using friendly hardware from companies like Arduino and Raspberry Pi. But, leveraging edge AI is becoming a common practice in many enterprises and industries too - helping to improve operations, reduce machine downtime, improve healthcare, and make existing products smarter.
The TI SK-TDA4VM is a versatile Edge AI computer vision platform to help you build robots, smart cameras, quality control, and other vision-based applications quickly and easily. Fully supported by Edge Impulse, it's simple to build a machine learning model, and deploy it to the board.
Everyone is eligible to complete activities and learn about Edge Impulse. However, you are only eligible to win or be awarded prizes if:
Winners will be announced on this page within 5 business days after a quiz is closed. Winners will also be contacted via the email used when submitting their quiz.
The prize fulfillment process will take up to 8 weeks after winners have been announced. You will receive an email when your prize is shipped. If you need to make any changes to your address during that time, please contact us at events@hackster.io.
No, Hackster will ship all the prizes and will cover the taxes/customs fees associated with shipment.
If you have any questions regarding this giveaway, please contact us at events@hackster.io.
Find upcoming events, workshops, and more!
Hackster, an Avnet Community © 2022
Keyword spotting, otherwise known as wake word detection, is a form of voice recognition that allows computers to listen for and respond to specific words. In keyword spotting, a device listens for a keyword or phrase and triggers an action based on what is spoken. There are many applications for keyword spotting including home automation, customer support services and more. Review the resources below to gain a better understanding of this popular technology and learn how to train a device to recognize your own keyword or phrase.
For our first challenge, we'd like you to teach a device to recognize the phrase, “Take it to the Edge”! We have a simple guided walkthrough at studio.edgeimpulse.com/evaluate that will help you along the way.
Follow the steps below to complete this activity and be entered into our giveaway to win a Syntiant TinyML board and Edge Impulse swag. This activity can be completed using a pc, mobile phone or any Edge Impulse supported device.
Video: Build Your Own ML-Powered Keyword Spotting Model in 30KB RAM
Learn the steps required to build a real TinyML model that responds to your voice. No pretrained models, no already created datasets, and no fixed keywords. You'll learn how to collect data from one of our fully supported development boards or your mobile phone, how to train an ML model, and how to deploy this back to your device where the model classifies audio in realtime.
Prefer to read through a tutorial rather than watch a video? Check out the written tutorial version of this demo "Responding to your voice" at the link below.
Get started with Edge Impulse by reading through the docs. In the Edge Impulse docs you'll find user guides, tutorials and API documentation.
Use machine learning to build a system that can recognize when a particular sound is happening—a task known as audio classification.
Learn how you can add turn signals on your bicycle and use Edge Impulse with an Arduino Nano BLE to warn others which direction you are going by using "left" and "right" keywords.
Edge Impulse Swag
Terms and Conditions
Official Terms and Conditions
These are the Official Terms and Conditions (“Terms”) that govern the relationship between Hackster.io, an Avnet community ("Administrator"), Edge Impulse ("Sponsor") and you (the “Entrant”) in relation to this developer program (“Take It to the Edge”). No purchase necessary to enter or win. Void where prohibited. A purchase of any kind does not increase your chance of winning.
TAKE IT TO THE EDGE DETAILS:
Take It to the Edge will start at 9AM Pacific Time (“PT”) on June 16, 2022 and end at 11:59 PT on March 26, 2023 (the “Giveaway Period”), subject to entry periods as outlined in the “ENTRY PERIODS” section below.
ENTRY PERIODS:
Activity Entry Period Dates:
Activity 1: June 16, 2022 - July 3, 2022
Activity 2: July 11, 2022 - July 24, 2022
Activity 3: August 15, 2022 - August 28, 2022
Activity 4: September 12, 2022 - September 25, 2022
Activity 5: October 10, 2022 - October 23, 2022
Activity 6: November 14, 2022 - November 27, 2022
Activity 7: December 12, 2022 - January 1, 2023
Activity 8: January 16, 2022 - January 29, 2023
Activity 9: February 20, 2023 - March 5, 2023
Activity 10: March 20, 2023 - April 2, 2023
Winner Announcement Periods:
Activity 1: Week of July 4, 2022
Activity 2: Week of July 25, 2022
Activity 3: Week of August 29, 2022
Activity 4: Week of September 26, 2022
Activity 5: Week of October 24, 2022
Activity 6: Week of November 28, 2022
Activity 7: Week of January 2, 2023
Activity 8: Week of January 30, 2023
Activity 9: Week of March 6, 2023
Activity 10: Week of April 3, 2023
ELIGIBILITY:
Take It to the Edge is open only to persons who are at least thirteen (13) years of age or older at the time of entry. Employees, and members of their immediate family or household, of Hackster.io, Avnet, Edge Impulse, and any other individuals engaged in the execution or administration of Take It to the Edge are not eligible to participate. Take It to the Edge is subject to all federal, state, and local laws and regulations. By entering, you indicate your full and unconditional agreement to, and acceptance of these Terms and the decision of the Administrator, which are final and binding in all respects. Winning a prize is contingent upon fulfilling all requirements set forth. US export regulations prohibit the export of goods and services to Cuba, Iran, North Korea, Sudan, or Syria, therefore residents of these countries are not eligible to participate. In addition, residents of Belarus, Russia, and Ukraine, as well as any individual on any sanctioned or restricted list published by any governmental agency or the United Nations may participate in Take It to the Edge activities for educational and engagement purposes but are not eligible to win or be awarded prizes.
HOW TO ENTER:
Visit https://events.hackster.io/take-it-to-the-edge during the Entry Period and fill out the quiz form. Entrant must fill out the form in its entirety, including country of residence, name and email. Then, click the “SUBMIT” button in order to receive one (1) entry into Take It to the Edge. Registration requires Participants to create a new, free Hackster user account or use their existing account. The Participant will be identified through their Hackster user profile URL.
Entrants are limited to 1 entry. Any attempt by any Entrant to obtain more than one entry by using multiple/different identities, email addresses, and/or any other methods will void that Entrant’s entries and that Entrant may be disqualified. No mechanically or programmatically reproduced entries are permitted. Administrator is not responsible for late, misdirected entries or failed internet connections.
WINNING/ODDS:
Entrants are asked to submit information in a quiz form on the main event landing page. On the winner announcement period listed in the “ENTRY PERIODS” section, all Prize Winners will be selected in a random drawing from among all eligible entries received during the respective Entry Period. Odds of winning a prize are dependent upon the total number of eligible entries received during the respective Entry Period. There is a limit of one (1) entry per Entrant per Entry Period. For each Entry Period, three (3) prize winners will be selected. Non-winning eligible entries from previous Entry Periods will not roll over to subsequent Entry Period winner selection.
In the event that the prize winner is disqualified for any reason, even if the disqualified prize winner’s name may have been publicly announced, Administrator shall have no liability or obligation to such individual.
Administrator reserves the right not to award all Prizes if, in its sole discretion, it receives an insufficient number of eligible and qualified submissions. Prize awards are subject to verification of eligibility and compliance with the terms of these Official Terms and Conditions.
PRIZES:
There will be a total of ten (10) Entry Periods during the Giveaway Period. For each Entry Period, three (3) prize winners will be selected from among all the eligible entries received during the activity’s Entry Period. There is a limit of one (1) prize per Entrant, per household. Prize winners agree that all prizes are provided “as is”, and the Administrator makes no warranty, representation or guarantee regarding any prize, including but not limited to its quality, condition, merchantability or fitness for a particular purpose. No transfer, substitution, or cash redemption of prizes is permitted, except at Administrator’s sole discretion or as otherwise provided in these Official Terms and Conditions. Administrator reserves the right to substitute a prize of equal or greater value if prize becomes unavailable due to reasons beyond the control of the Administrator. Winning a prize constitutes permission for Administrator and its agencies to use prize winners' names, addresses (city & state/province/territory) in order to fulfill the prize, regardless if the prize is virtual or physical.
If you are a potential winner, we may require you to sign an Affidavit of Eligibility, Liability/Publicity Release. You are advised to seek independent counsel regarding the possible tax implications of accepting a prize. The Administrator will not provide additional tax documentation. If you are a potential winner and you are 18 or older but are considered a minor in your place of legal residence, we may require your parent or legal guardian to sign all required forms on your behalf. If you do not complete the required forms as instructed and/or return the required forms within the time period listed on the winner notification message, we may disqualify you and select a runner-up. The Administrator is responsible for any federal, state and local taxes necessary when shipping Prizes, if applicable.
NOTIFICATION:
All prize winners will be notified by email (the “Email Notification”). The Email Notification will be sent to the Prize Winners by events@hackster.io. Prize winner must respond to the Email Notification within five (5) business days of such Email Notification sent, by providing contact and shipping information required for prize fulfillment. If: (a) a prize winner fails to respond to the Email Notification within five (5) business days of the Email Notification; (b) any Email Notification is returned as undeliverable; or (c) the Administrator determines, in its sole reasonable discretion, that the prize winner has breached these Terms and/or is not eligible in accordance with these Terms, that prize winner will be disqualified and the prize will not be awarded. All prize winners consent to use of his/her name, video, biographical information, and submitted form information in advertising worldwide without additional compensation. All Prizes will be awarded approximately six (6) to eight (8) weeks after receipt of the required information in Email Notification.
GENERAL RULES OF PARTICIPATION:
By participating in Take It to the Edge and to the fullest extent permissible by law, Entrants and Prize Winners release the Administrator from any and all liability, damages or causes of action (but named or described) with respect to or arising out of participation in Take It to the Edge, and/or the receipt or use/misuse of the prizes awarded, including, without limitation, liability for personal injury, death or property damage. By participating in Take It to the Edge, Entrants agree to be bound by these Terms and the decisions of the Administrator, which are final in all respects and not subject to appeal. Administrator reserves the right permanently to disqualify any Entrant it reasonably believes has violated these Terms. Winning a prize constitutes permission for Administrator to use prize winners' names, survey form content, and/or videos for purposes of advertising and publicity, in connection with Take It to the Edge, without further compensation, unless prohibited by law. Administrator may prohibit an Entrant from participating in Take It to the Edge or winning a prize if, in its sole discretion, Administrator determines that the Entrant is attempting to undermine the legitimate operation of Take It to the Edge by cheating, hacking, deception, or other unfair playing practices or intending to annoy, abuse, threaten or harass any other Entrants or the Administrator. If for any reason Take It to the Edge cannot be conducted as planned, including, but not limited to, by reason of infection by computer virus, bugs, tampering, unauthorized intervention, fraud or any other causes beyond the reasonable control of Administrator which corrupt or affect the administration, security, fairness, integrity or proper conduct of Take It to the Edge, then Administrator reserves the right at its sole discretion to cancel, terminate, modify or suspend Take It to the Edge and randomly draw winners from those entries received up to the cancellation/suspension date.
NO LIABILITY:
By participating and to the fullest extent permissible by law, Entrants agree to release, discharge, indemnify and hold harmless the Administrator and each of its respective officers, directors, employees, representatives and agents (the “Released Parties”) from and against any claims made by winners, Entrants, or any other third parties, related in any way to the operation of Take It to the Edge as well as any other claims, damages or liability due to any injuries, damages or losses to any person (including death) or property of any kind resulting in whole or in part, directly or indirectly, from acceptance, possession, misuse or use of any prize or participation in any Take It to the Edge-related activity or participation. All prizes offered “as is” and with no additional warranties.
PRIVACY NOTICE:
If not stated otherwise in these Terms, personal information collected from Entrants about Entrants will be incorporated in computerized files belonging to the Administrator and used where applicable in accordance with the respective privacy policy and in accordance with all applicable data protection and privacy laws. Collection and use of Entrants' personal information in conjunction with participation in Take It to the Edge shall be governed by the Administrator’s Privacy Policy, accessible at www.hackster.io/privacy and/or Sponsor’s Privacy Policy, accessible at https://docs.edgeimpulse.com/page/.
By entering Take It to the Edge, for the purposes of administration you:
(a) consent to the Administrator handling your entry and your personal information; and
(b) you grant the Sponsor all similar rights and authorizations that you have granted to the Administrator in these Terms.
By signing up to receive marketing updates from the survey Administrator and survey Sponsor, you consent to share your personal information with the Administrator and Sponsor.
Take It to the Edge shall not be published without permission of the Administrator.
There are many applications for keyword spotting including home automation, customer support services and more. Review the resources below to gain a better understanding of this popular technology and learn how to train a device to recognize your own keyword or phrase.
Teach a device to recognize the phrase, “Take it to the Edge”! We have a simple guided walkthrough at studio.edgeimpulse.com/evaluate that will help you along the way.
Follow the steps below to complete this activity and be entered into our giveaway to win a Syntiant TinyML board and Edge Impulse swag. This activity can be completed using a pc, mobile phone or any Edge Impulse supported device.
Video: Build Your Own ML-Powered Keyword Spotting Model in 30KB RAM
Learn the steps required to build a real TinyML model that responds to your voice. No pretrained models, no already created datasets, and no fixed keywords. You'll learn how to collect data from one of our fully supported development boards or your mobile phone, how to train an ML model, and how to deploy this back to your device where the model classifies audio in realtime.
Prefer to read through a tutorial rather than watch a video? Check out the written tutorial version of this demo "Responding to your voice" at the link below.
Get started with Edge Impulse by reading through the docs. In the Edge Impulse docs you'll find user guides, tutorials and API documentation.
Use machine learning to build a system that can recognize when a particular sound is happening—a task known as audio classification.
Learn how you can add turn signals on your bicycle and use Edge Impulse with an Arduino Nano BLE to warn others which direction you are going by using "left" and "right" keywords.
Edge Impulse Swag
Use the resources below to learn about the Raspberry Pi Pico, and how when combined with Edge Impulse, it can make an impact across a wide variety of topics like sustainability and environment, health, industry, energy, and more.
For July's challenge, read the two projects below to learn about various applications that can be built with the Pico or Pico W and Edge Impulse, then take a short quiz to show us what you learned! Quiz participants will be entered in the drawing to win July's prize bundle - a Raspberry Pi Pico, Grove Starter Kit for the Pico and Edge Impulse Swag.
Documentation
Learn how to connect Raspberry Pi's RP2040 to Edge Impulse, by flashing the latest firmware and using the Edge Impulse CLI to configure the device.
Project Tutorials
Pen + pineapple = Pineapplepen. What about Pico + Machine Learning?
An intelligent device for seniors which detects falls and sends emergency alert messages with location information using a cellular network.
Using machine learning to build a gesture recognition system that runs on a tiny microcontroller, the RP2040.
Raspberry Pi Pico runs Edge Impulse’s Sensor Fusion software to read data from gas, temperature, and humidity sensors and tells you if your food is burning.
Find more projects featuring Edge Impulse and Raspberry Pi Pico on Hackster.io.
Raspberry Pi Pico
Seeed Studio Grove Starter Kit for the Pico
Edge Impulse Swag
Use the resources below to learn about the Raspberry Pi Pico, and how when combined with Edge Impulse, it can make an impact across a wide variety of topics like sustainability and environment, health, industry, energy, and more.
For July's challenge, read the two projects below to learn about various applications that can be built with the Pico or Pico W and Edge Impulse, then take a short quiz to show us what you learned! Quiz participants will be entered in the drawing to win July's prize bundle - a Raspberry Pi Pico, Grove Starter Kit for the Pico and Edge Impulse Swag.
Documentation
Learn how to connect Raspberry Pi's RP2040 to Edge Impulse, by flashing the latest firmware and using the Edge Impulse CLI to configure the device.
Project Tutorials
Pen + pineapple = Pineapplepen. What about Pico + Machine Learning?
An intelligent device for seniors which detects falls and sends emergency alert messages with location information using a cellular network.
Using machine learning to build a gesture recognition system that runs on a tiny microcontroller, the RP2040.
Raspberry Pi Pico runs Edge Impulse’s Sensor Fusion software to read data from gas, temperature, and humidity sensors and tells you if your food is burning.
Find more projects featuring Edge Impulse and Raspberry Pi Pico on Hackster.io.
Raspberry Pi Pico
Seeed Studio Grove Starter Kit for the Pico
Edge Impulse Swag
The Arduino Nano 33 BLE Sense is one of the most feature-packed Arduino boards, with a built-in temperature sensor, accelerometer, gyroscope, and microphone (and more). This makes it a great platform for building monitoring and sensing projects and devices. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the Edge Impulse Studio.
We've chosen two Hackster projects that show off the power of Edge Impulse on Arduino. Read the projects below to learn about voice control and digit recognition applications using the Arduino Nano 33 BLE Sense and Edge Impulse, then take a short quiz to show us what you learned and for a chance to win August's prize bundle.
Use the resources below to learn about the Arduino Nano 33 BLE Sense, and how you can use it with Edge Impulse to build a wide variety of projects covering sustainability and the environment, health, industry, energy, and more.
Documentation
how to connect an Arduino Nano 33 BLE Sense to Edge Impulse, by flashing the latest firmware and using the Edge Impulse CLI to configure the device.
Other Project Tutorials
BABL leverages tinyML to distinguish a baby's cry from other noise, preventing false alarms, and alerting parents only when needed.
TinyML implementation to identify running water tap sound and once heard one, a buzzer + LED timer is triggered.
A fun and simple project that uses tinyML to detect and respond to dog barks.
How do you tell the difference between a fall and a sudden movement? Train a machine learning model to detect when a fall occurs.
Find more projects featuring Edge Impulse and the Arduino Nano 33 BLE Sense on Hackster.io.
Edge Impulse Swag
The ESP32 is a small, low cost microcontroller with bluetooth and WiFi connectivity, making it ideal for IoT products and applications. It's dual-core processor is strong enough to run TinyML models, opening up endless possibilities for building smart sensors, wearables / health devices, basic vision applications, and more.
The Espressif ESP-EYE development board based on Espressif's ESP32 chip is fully supported by Edge Impulse. The ESP-EYE is equipped with a 2-Megapixel camera and a microphone making it perfect for image recognition and audio processing applications.
Learn More >>
Follow the steps below to get acquainted with Edge Impulse and the ESP32’s capabilities using the Edge ML platform. Then take a short quiz for a chance to win September's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Sign up for an Edge Impulse account at studio.edgeimpulse.com/signup.
Review the projects below & complete the quiz.
Gesture Classification with ESP32 and TinyML
ESP32-CAM: TinyML Image Classification - Fruits vs Veggies
Documentation
Announcing Official Support for Espressif ESP-EYE (ESP32)
Getting Started with Edge Impulse on Espressif ESP-EYE (ESP32)
Add Sight to Your ESP32
Learn how to flash the latest firmware and use the Edge Impulse CLI to configure the ESP32.
More Project Tutorials
Edge Driving Monitor
Driving Monitor that tracks the driver's blind spots with a warning system created with an ESP32 CAM and powered by Edge Impulse.
Use an ESP-32 Cam and an Edge Impulse model to take photos of your avian friends visiting your solar-powered bird feeder!
Find more projects featuring Edge Impulse and ESP32 on Hackster.io
Edge Impulse Swag
In most cases, data is the most important factor in creating a successful TinyML project. Sure, hardware selection, power, and connectivity matter too, but without good training data, your model likely won’t be accurate enough to perform it’s intended function out in the world!
Understanding the significance of data in TinyML models is extremely important. Get acquainted with the critical role data plays in an Edge Impulse project by reading through the two official Edge Impulse Docs below. Learn how to upload, label, augment, and split up your data, then take a short quiz for a chance to win an Arduino Portenta H7 + Vision Shield in October’s prize bundle.
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Sign up for an Edge Impulse account at studio.edgeimpulse.com/signup.
Review the documents below & complete the quiz.
See how data is split for train/test set & the data distribution for each class in your dataset.
Explore your dataset, find outliers or mislabeled data, and label unlabeled data.
Documentation
Create Active Learning Pipelines with Data Sources and Data Explorer Features
Better Organize Your ML data with New Filters and Batch Operations
Data Augmentation
Project Tutorials Featuring Edge Impulse with the Arduino Portenta H7
A TinyML model using Arduino Portenta and Edge Impulse to predict the anomalous operation in Industrial machineries like Pump, valves & fans.
A low power vision-based sewer faults detection device using a tinyML neural network to produce highly accurate sewer faults classification.
As the name suggests, this device classifies the cloud into six different categories using TinyML.
Find more projects using Edge Impulse on Hackster.io
Edge Impulse Swag
The team at Sony has created a small but powerful microcontroller board that is ready to run Edge Impulse machine learning models. With 6 Arm Cortex-M4 cores, 1.5 mb of RAM, GPS, camera input, onboard audio, and plenty of expansion options for sensors, WiFi, cellular and more, the Spresense can be used in a wide variety of projects.
This is your chance to get up to speed on the Sony Spresense and it’s TinyML capabilities. Review two projects that make great use of Edge Impulse running on the Spresense and the getting started guide below, then take a short quiz for a shot at winning a Spresense of your own as part of November's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Sign up for an Edge Impulse account at studio.edgeimpulse.com/signup.
Review the three resources below & complete the quiz.
Free Car Parking Monitoring Device
Remote Leak Monitoring with AI Detection and Alerting
Sony's Spresense Getting Started Guide
Quiz closes November 27, 2022 at 11:59PM PT.
Documentation
Other Project Tutorials
Using AI and IoT to Help Grow Food in Remote Greenhouses
Use embedded ML on low-power microcontrollers to analyze crops in greenhouses without power & send the results over LPWAN networks
Using Sony Spresence & EI, turns analog oil tank meter into digital, realtime update on the app help delivery company optimize operation.
Using computer vision on a Sony Spresense to count traffic in a bicycle lane.
Estimating plant growth parameters for high throughput phenotyping using regression and EdgeImpulse on low power Sony Spresense under 0.35A!
Find more projects featuring Edge Impulse and Sony Spresense on Hackster.io.
Edge Impulse Swag
Many times, we focus on performing machine learning locally on-device, with no need for internet connectivity. This reduces latency, simplifies projects, and can sometimes reduce costs. However, some projects do require connectivity to the cloud in order to set a status, update a dashboard, log an activity or event, or allow a user to interact with a device.
We're highlighting two example projects that use Edge Impulse plus Blues Wireless to send data to the cloud. Review the projects below to better understand how you can leverage connectivity in your own projects, then take a short quiz about what you learned to be entered for a chance at winning a Blues Wireless Starter Kit as part of December's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Sign up for an Edge Impulse account at studio.edgeimpulse.com/signup.
Review the three resources below & complete the quiz.
Appliances Identifier Smart Energy Meter
Running Faucet Alert System with Blues Wireless
Quiz closes January 1, 2023 at 11:59PM PT.
Documentation
Sending Inference Data to the Cloud with the Notecard
Getting Started with Edge Impulse on Blues Wireless Swan
Edge Impulse Review of Audio Classification
Routing Data to Cloud Tutorials
Blues wireless offers Routing Data to Cloud tutorials that walk you through routing Notecard data to a variety of big clouds and IoT platforms.
Other Project Tutorials
Learn how to add the IoT and TinyML to analog sensors with the Raspberry Pi, Edge Impulse, and the Notecard.
Learn how to create a prototype of a roadside litter detection device that maps trash in cities using Blues Wireless and Edge Impulse.
Will guide you to build a cellular based predictive maintenance monitoring device with Blues Notecard, Edge Impulse, Qubitro & Wio Terminal.
Build an anomaly detection ML model with Edge Impulse based on thermal images, with data sent over cellular to the cloud via the Notecard.
Find more projects featuring Edge Impulse and Blues Wireless on Hackster.io.
Edge Impulse Swag
*Version awarded is based on winners locations
When deploying smart devices in certain environments your available space and power requirements may be limited. The Silicon Labs xG24 Developer Kit is a sensor-rich platform for prototyping AIoT devices, able to run TinyML models on just a coin-cell battery. With a dedicated AI accelerator, 6 onboard sensors, BLE, and a compact board about the size of two postage stamps, the xG24 can fit in tight places and capture a wealth of environmental information.
To better understand the Silicon Labs xG24 Developer Kit and it’s capabilities, we're highlighting two example resources that make great use of Edge Impulse running on the board. Review the resources below, then take a short quiz about what you learned to be entered for a chance at winning an xG24 in January's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Review the two resources below & complete the quiz.
Project: Occupancy Sensing - SiLabs EFR32MG24
Tutorial: Object detection - SiLabs xG24 Dev Kit
Use the resources below to learn more about the Silicon Labs xG24 Dev Kit and how to get started collecting data, building and training tiny machine learning models, and deploying these models to the xG24 Dev Kit directly from the Edge Impulse Studio.
Documentation
Announcing Official Support for the Silicon Labs xG24 Dev Kit
Getting Started with SiLabs xG24 Dev Kit
Setting up your EFR32xG24 Kit
xG24 Dev Kit User's Guide
MG24 Demo
Learn more about Silicon Labs' cost-effective, feature-rich, prototype and development
platform based on the EFR32™ Wireless Gecko System-on-Chip in the official xG24 Dev Kit User's Guide.
Other Project Tutorials
Explore more projects making use of Silicon Labs hardware including the xG24’s very-capable predecessor, the Thunderboard Sense 2.
Take an existing Edge Impulse model built for the Thunderboard Sense 2, and prepare it for use on the SiLabs xG24 board.
Use Edge Impulse to train a model for detecting gestures with the onboard accelerometer.
Edge Impulse based TinyML model using Audio data acquisition to predict the vehicle failures like faulty drive shaft, Brake pad noises.
Edge Impulse Swag
Edge Impulse makes it easy for beginners to add machine learning to their projects, using friendly hardware from companies like Arduino and Raspberry Pi. But, leveraging edge AI is becoming a common practice in many enterprises and industries too - helping to improve operations, reduce machine downtime, improve healthcare, and make existing products smarter.
This month we are asking you to think “big-picture”, and imagine ways that edge AI could benefit your industry, organization or products. Gather some ideas from the projects below featuring machine learning use cases for industrial applications, then take a short quiz about what you learned to be entered for a chance to win a Nordic Thingy:53 developer kit in February's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Review the two resources below & complete the quiz.
Surface Crack Detection and Localization w/ Seeed reTerminal
Gelāre: Depth-sensing & EdgeImpulse powered Assistive-Robots
Quiz closes March 5, 2023 at 11:59PM PT.
Documentation
Use Case: The New AI-Powered Grid
Use Case: ML-Powered Agricultural Robotics
RAM-1: The World’s Smartest Powerline Monitoring System.
Edge Impulse machine learning models are helping a UK-based robotics startup record crop trials while providing precise irrigation levels to help quantify the best-growing conditions for the crops.
READY Robotics Demo
Predictive Maintenance Webinar
Other Project Tutorials
A TinyML model using Arduino Portenta and Edge Impulse to predict the anomalous operation in Industrial machineries like Pump, valves & fans.
An attempt to identify location just using sound, similar to how humans do it just by listening.
Sample data from a BLDC motor controller and apply machine learning to receive predictive maintenance alerts.
A prototype smart device that alerts the wearer with haptic feedback if emergency vehicles or car horns are detected.
Find more projects featuring Edge Impulse on Hackster.io.
Edge Impulse Swag
The TI SK-TDA4VM is a versatile Edge AI computer vision platform to help you build robots, smart cameras, quality control, and other vision-based applications quickly and easily. Fully supported by Edge Impulse, it's simple to build a machine learning model, and deploy it to the board.
For our final activity of Take It to the Edge with Edge Impulse, check out the two projects below to get acquainted with the features and capabilities of the SK-TDA4VM, and learn how one community member used machine learning with the TI board to create a smart factory. Then take a short quiz about what you learned to be entered for a chance to win your own TI SK-TDA4VM Starter Kit in March's prize bundle!
Join the Edge Impulse community at hackster.io/EdgeImpulse.
Review the two projects below & complete the quiz.
Getting Started with the TI SK-TDA4VM Development Kit
Smart Factory with TI TDA4VM
Quiz closes Monday, April 3, 2023 at 11:59PM PT.
Documentation
Other Project Tutorials
Use Computer Vision on a TI TDA4VM to Deter Shoplifting
Find more projects featuring Edge Impulse on Hackster.io.
Edge Impulse Swag