Silicon Labs

Building Ultra-Small Footprint, Ultra-Low Power and Ultra-Efficient ML Models for Extreme Edge IoT Applications

A Trusted IoT Development Platform

Silicon Labs and SensiML have partnered to deliver rapid development of TinyML smart IoT sensing applications on Silicon Labs' end-to-end machine learning (ML) development solutions for existing Silicon Labs Series 1 and Series 2 wireless SoCs and its new EFR32BG24 and EFR32MG24 products, which features integrated AI/ML hardware acceleration providing up to 4x faster interferencing with up to 6x lower power consumption for ML processing.
Using Silicon Labs’ ML development solution, designers can enhance embedded applications with AI/ML capabilities, even in ultra-low-power wireless IoT devices. ML computing at the edge enables a variety of smart industrial and home applications including sensor-data processing for anomaly detection, predictive maintenance, audio pattern recognition like glass-break sensing and simple-command word recognition. The SensiML Analytics Toolkit accelerates the development of optimized AI sensor models for intelligent endpoints allowing meaningful insight to be generated locally in real-time at the embedded device.

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
Security application examples include door knocking, glass break detector, scream, and shot detection, cough detection, machine malfunction detector and breath monitoring.
Low-rate data, time-series data examples: Predictive/Preventative Maintenance Electricity Measurement P vs. Q forecasting, bio-signal analysis, healthcare and medical pulse detection, EKG, cold chain monitoring, accelerometer use cases like fall detection, pedometer, step counting, digital nose, battery monitoring and agricultural use-cases.

Add Predictive Maintenance to Smart Building Devices with TinyML: A Tutorial

By the end of this "Works With 2021" tutorial session, you will have surveyed several noteworthy tinyML smart building use cases, seen a working HVAC predictive maintenance application, and followed a step-by-step process for building this example application.
Thunderboard Sense 2 (SLTB004A)  Thunderboard Sense 2 is a compact, feature-packed development platform. It provides the fastest path to develop and prototype IoT products such as battery-powered wireless sensor nodes. The development platform combines a broad range of sensors with the powerful multi-protocol EFR32 radio and a mobile app offering Bluetooth communication and cloud connectivity. Thunderboard Sense 2 also has an on-board J-Link debugger and is fully supported in Simplicity Studio.

EFR32xG24 Dev Kit (xG24-DK2601B)  The EFR32xG24 Dev Kit is a compact, feature-packed development platform. It provides the fastest path to develop and prototype wireless IoT products. The development platform supports up to +10dBm output power and includes support for the 20-bit ADC as well as other key features such as the xG24’s AI/ML hardware accelerator.