Nordic Thingy:53 with Edge Impulse TinyML Solution

Table of contents

RoadTest Goals

Test the out of box experience of the product as an easy-to-use IoT protyping platform. Examine the documentation, getting started guides, and other documentation. Perform an unboxing of the product. After you review the hardware, experiment with the Edge Impulse ML solution that has been integrated directly on the Thingy:53.

Take This Fun Quiz for a chance to Win 1 of 5 Nordic Thingy:53s. Terms.

Take the Quiz

Hardware Description
The Nordic Thingy:53 is an easy-to-use IoT prototyping platform. It makes it possible to create prototypes and proofs-of-concept without building custom hardware. The Thingy:53 is built around the nRF5340 SoC, Nordic’s flagship dual-core wireless SoC. The processing power and memory size of its dual Arm Cortex-M33 processors enables it to run embedded machine learning (ML) models directly on the device.

The nRF Edge Impulse app enables users to connect their Nordic Thingy:53 to their Edge Impulse studio account through a mobile device. It allows them to wirelessly transfer sensor data over Bluetooth LE to the mobile device and upload it to the cloud for training and download trained ML models to the Thingy:53 for deployment and inferencing. The app also acts as the GUI for viewing inferencing results from a running ML model.

The Bluetooth Low Energy (LE) radio allows updating firmware and communication over Bluetooth LE, and the radio also supports other protocols like Bluetooth mesh, Thread, Zigbee, and proprietary 2.4 GHz protocols. The Thread protocol compatibility also makes it a great choice when developing products for the new Matter ecosystem. Matter is a standardized application layer for connected home applications, using the Internet Protocol (IP) as the network layer.

The Thingy:53 also includes many different integrated sensors, like environmental-, and color and light sensors, accelerometers, and a magnetometer, which all can be taken advantage of without additional hardware. It is powered by a rechargeable Li-Po battery with a 1350 mAh capacity that can be charged via USB-C. There is also an external 4-pin JST connector compatible with the Stemma/Qwiic/Grove standards for hardware accessories.

Every Thingy:53 comes pre-installed with the firmware to work with the nRF Edge Impulse app for iOS and Android. Also released with the Thingy:53 is the nRF Programmer app for updating the device firmware directly over the air from a mobile device.

Key Features
• Battery powered prototyping platform for Matter and machine learning on the nRF5340 SoC
• Support for multiple wireless standards, Bluetooth LE, Bluetooth mesh, Thread, Zigbee
• Environmental sensor for temperature, humidity, air quality and air pressure
• Color and light sensor
• Low-power accelerometer and 6-axis inertial measurement unit (IMU)
• Buzzer and PDM microphone
• Connector for additional external boards and accessories
• USB-C rechargeable 1350 mAh Li-Po battery
• nRF Edge Impulse mobile app for embedded machine learning
• nRF Programmer mobile app for easily flashing firmware on the go

nRF Edge Impulse Mobile app
The nRF Edge Impulse app was developed in collaboration with Edge Impulse to train and deploy embedded machine learning models on the Nordic Thingy:53 using Edge Impulse Studio. Every Nordic Thingy:53 comes pre-installed with firmware compatible with the nRF Edge Impulse mobile app. The app allows you to upload raw sensor data via your mobile device to the cloud-based Edge Impulse Studio and deploy fully trained ML models to the Nordic Thingy:53 over Bluetooth® Low Energy (LE).

The app allows you to choose between existing projects in Edge Impulse studio data or creating a new project and can collect sensor data from the following set of sensors on the Nordic Thingy:53:

• Accelerometer
• Microphone
• Magnetometer
• Light
• Temperature, Pressure, Humidity and Air quality
• Inertial (Accelerometer and Magnetometer)
• Light and Environment
• Light and Inertial
• Environment and Inertial

The collected sensor data can be labeled as training or testing data and may be inferenced directly in the app with machine learning model deployed to the Nordic Thingy:53.

Note: A free Edge Impulse account, which can be created from the nRF Edge Impulse app or at www.edgeimpulse.com, is required to connect the app with Edge Impulse Studio.

Contents
• Thingy:53
• Protective Enclosure
• Current measurement and debug board (Does not include cables)
• Getting-started card (nordic.semi.com/start-thingy53)

Additional Information
Datasheet
nRF Connect SDK
nRF Programmer
nRF Edge Impulse
Edge Impulse
Downloads
Developing with Thingy:53
nRF Connect SDK Fundamentals Course
WEBINAR Say hello to Thingy:53 - The prototyping platform for embedded ML

Important Dates 

Terms and Conditions
Click Here to read the Terms and Conditions.