Summary of LOW-POWER AI SENSOR BOARD FOR MACHINE LEARNING AT THE EDGE
The ECM3532 AI Sensor Board by Eta Compute is an ultra-low-power integrated solution for machine learning at the edge. Powered by the TENSAI SoC, it enables months of operation on a single battery cell. The board features dual PDM microphones, pressure and temperature sensors, a 6-axis MEMS accelerometer/gyroscope, Bluetooth connectivity via ABOV Semiconductor's chip, and an expansion connector for additional RF interfaces. Designed with Edge Impulse support, it accelerates IoT prototype development while minimizing risk and cost.
Parts used in the ECM3532 AI Sensor Board:
- TENSAI SoC
- Two PDM microphones
- Pressure and temperature sensor
- 6-axis MEMS accelerometer and gyroscope
- Embedded battery socket
- Bluetooth chip (ABOV Semiconductor A31R118)
- Expansion connector
Eta Compute has launched an integrated, ultra-low-power AI Sensor Board, the ECM3532 AI Sensor Board, which has been designed for machine learning at the edge. [via]
The board was developed to cut the initial phase of smart sensor development through its TENSAI SoC. The low power ECM3532 AI Sensor Board contains almost every function needed for a working prototype. Because of the low power design, the board is able to for months on a single battery cell while performing machine learning algorithms. It integrates two PDM microphones, one pressure and temperature sensor, and one 6-axis MEMS accelerometer and gyroscope. It has a form factor of only 1.4 inch x 1.4 inch. The embedded battery socket and Bluetooth connectivity through ABOV Semiconductor’s A31R118 chip, makes it an ideal asset for IoT deployment and field testing application prototypes. The board’s expansion connector makes it simple to add other RF interfaces.
“Our fully integrated ECM3532 AI Sensor Board reduces risk, complexity, and costs for developers creating low power smart sensors and accelerates their time to proof of concept,” said Ted Tewksbury, CEO of Eta Compute. “For the first time, they can rely on a single, fully integrated board complemented by Edge Impulse’s comprehensive SaaS development platform to drive innovative IoT solutions to market.”
“Designing low-power devices with embedded machine learning has been a huge challenge,” said Zach Shelby, CEO of Edge Impulse. “The new Eta Compute AI Sensor Board opens up endless application possibilities for developers without compromising on power consumption, and with full support on Edge Impulse we reduce development time to days instead of months.”
Read more: LOW-POWER AI SENSOR BOARD FOR MACHINE LEARNING AT THE EDGE
- What is the primary purpose of the ECM3532 AI Sensor Board?
It is designed for machine learning at the edge to cut the initial phase of smart sensor development. - How long can the board operate on a single battery cell?
The low power design allows the board to function for months on a single battery cell. - Which components are integrated into the board?
It integrates two PDM microphones, one pressure and temperature sensor, and one 6-axis MEMS accelerometer and gyroscope. - Can I add other RF interfaces to this board?
Yes, the board has an expansion connector that makes it simple to add other RF interfaces. - What platform supports the board for development?
The board is complemented by Edge Impulse’s comprehensive SaaS development platform. - Does using this board reduce development time?
Yes, full support on Edge Impulse reduces development time to days instead of months. - What is the form factor of the board?
The board has a compact form factor of only 1.4 inch x 1.4 inch.
