SensiML & Silicon Labs Partner on Cutting-Edge AI for IoT: AutoML Smart Sensing Tools for the EFR32 / EFM32 Family of Low Energy MCUs

Silicon Labs Logo
Silicon Labs Thunderboard Sense 2 and Box

SensiML has collaborated with Silicon Labs to enable the rapid development of machine learning sensor insight for Silicon Labs‘ energy-friendly EFR32 and EFM32 microcontrollers (MCUs). To this end, we have enabled support within SensiML Analytics Studio for the Thunderboard Sense 2 IoT Development Starter Kit (SLTB004A). Thunderboard Sense 2 is a sensor-rich, small form-factor prototyping board that enables developers to quickly develop proof-of-concept devices for IoT products such as battery-powered wireless sensor nodes.

Using the Thunderboard Sense 2 and SensiML Analytics Toolkit, developers seeking to utilize Silicon Labs ultra-low-power EFR32 multi-protocol wireless SoCs and EFM32 MCUs to build intelligent IoT sensing products have the ability to quickly collect and label accurate training datasets from a variety of sensors, build corresponding AI inference models, and generate optimized firmware in a fraction of the time typically required. Furthermore, the low-cost of the Thunderboard hardware combined with the free Community Edition tier of SensiML’s AI toolkit allows developers to explore the possibilities of this combined solution and build working prototypes of their concepts without delay and with no upfront obligation.

Silicon Labs’ Thunderboard Sense 2 is a compact, low-power, and sensor-rich development platform based on the EFR32 wireless system-on-chip (SoC), making it an ideal tool for developing battery-operated wirelessly connected edge IoT devices. The SensiML Analytics Toolkit accelerates the development of compact, optimized AI sensor models for intelligent endpoints allowing meaningful insight to be generated locally in real-time at the embedded device.

Just a few of the possible applications enabled by the joint development platform include:

  • Industrial predictive maintenance
  • Remote process and equipment monitoring
  • Wearable device activity detection and form analysis
  • Gesture recognition
  • Audio recognition and acoustic event detection for smart homes and buildings

Leveraging SensiML tools with the Silicon Labs Thunderboard Sense 2 enables:

  • Reduced development time and rapid prototyping of innovative smart IoT product concepts using data-driven supervised and unsupervised ML model development
  • Ability to add AI/ML functionality to products without in-depth data science experience or expertise utilizing SensiML’s AutoML modeling engine
  • Faster time-to-market with differentiated intelligent IoT devices that remove dependence on cloud and smartphone AI processing to deliver sensor insights
  • High AI modeling confidence from an end-to-end workflow that includes powerful dataset annotation, automated data labeling, full model transparency, and flexibility to tune or modify all aspects of the code

The integration utilizes SensiML’s raw sensor data collection interface we call the Simple Streaming Interface in an available firmware from Silicon Labs allowing direct connectivity between the Thunderboard and SensiML Data Capture Lab. The default firmware build supports streaming of the integrated 6-axis motion sensor providing both accelerometer and gyro sensor data as well as audio sensor streaming from the onboard digital microphone.

The simple streaming interface and default firmware can also be readily modified and extended by the user to suit custom hardware and sensor configurations and the additional available sensors kitted on the Thunderboard PCB.

Silicon Labs Thunderboard Sense 2

Thunderboard Sense 2 is packed with sensors and supports SensiML Simple Streaming mode output for easy-to-configure sensor setup.

Get Data Capture Firmware
Get SensiML Community Edition
Read Firmware Documentation

“Leveraging our industry-leading platforms with SensiML tools provides developers with an open, transparent and complete end-to-end development solution for IoT devices at the edge. Together, we remove the barriers to implementing AI/ML, simplify the development process and enable a focus on innovation for our customers.”

Matt Saunders, Vice President of IoT at Silicon Labs

To learn more about how to use SensiML Analytics Toolkit with Thunderboard Sense 2, click here.

To learn more about Silicon Labs Thunderboard Sense 2 IoT Kit, visit their product page.

We’d welcome the opportunity to hear what projects you are building or plan to build with the Thunderboard Sense 2 and SensiML Analytics Toolkit. Drop us an email at Happy prototyping!

* All product names, logos, and brands are property of their respective owners.