Summary of ETA COMPUTE’S ECM3532 AI SENSOR BOARD WITH TENSAI SOC FOR TINYML
Eta Compute’s ECM3532 AI Sensor board is a tiny, low-power TinyML development platform combining an Arm Cortex-M3 MCU and an NXP CoolFlux DSP for on-device ML. It integrates microphones, environmental and motion sensors, BLE connectivity, battery support, data logging, and expansion options, targeting sound classification, keyword spotting, activity/context awareness, and defect detection for IoT prototypes.
Parts used in the ECM3532 AI Sensor board:
- Arm Cortex-M3 microcontroller (up to 100 MHz)
- 512KB FLASH
- 256KB SRAM
- 8KB BootROM
- NXP CoolFlux 16-bit DSP (with 32KB program memory, 64KB data memory)
- 2 x PDM MEMS Microphones: TDK-Invensense ICS-41350
- Pressure/Temperature sensor: BOSCH BMP388
- 6-axis MEMS Accelerometer/Gyro: TDK-Invensense ICM-20602
- Battery cradle for a CR2032 battery
- Bluetooth Low Energy module: ABOV A31R118 with antenna (BLE v4.2)
- Micro SD card slot for RF extension
- 6-pin UART and power port
- 64Mbit serial Flash for data logging
- 5 LEDs and push-button
Eta Compute’s ECM3532 AI Sensor board is a low-power AI development platform with advanced sensors, compatible with sound classification, keyword spotting, activity classification, context awareness, and defect detection. It has an embedded Cortex-M3 microcontroller that functions up to a frequency of 100 Mhz, and NXP CoolFlux 16-bit DSP dedicated for machine learning using TinyML technology.
The AI sensor board integrates two microphones, one pressure and temperature sensor, and one 6-axis MEMS accelerometer and gyroscope. The ECM3532 AI sensor board also comes with small form factor with 1.4” x 1.4” dimensions, a built-in battery socket, and flexible Bluetooth connectivity with the A31R118 chip, this makes it suitable for IoT deployment and experimentation of application prototypes. The AI sensor board also has an expansion connector that simplifies the addition of other RF interfaces.
Key Features
- Arm Cortex-M3 core works up to 100 MHz with less than 5μA/MHz run mode
- Integrated 512KB FLASH, 256KB SRAM, and 8KB BootROM
- NXP CoolFlux 16-bit DSP with 32KB program memory, 64KB data memory
- 2 x PDM MEMS Microphones: TDK-Invensense ICS-41350
- 1 x Pressure/Temperature sensor: BOSCH BMP388
- 1 x 6-axis MEMS Accel/Gyro: TDK-Invensense ICM-20602
- Battery cradle for a CR2032 battery
- Bluetooth Low Energy on board: BLE v4.2: ABOV A31R118 and antenna
- Extension for other types of RF through Micro SD card slot
- 6 pin UART and power port
- 64Mbit serial Flash for data logging
- 5 LEDs and push-button
Read more: ETA COMPUTE’S ECM3532 AI SENSOR BOARD WITH TENSAI SOC FOR TINYML
- What processors are on the ECM3532 AI Sensor board?
It includes an Arm Cortex-M3 microcontroller and an NXP CoolFlux 16-bit DSP. - Can the board run TinyML applications?
Yes, the board is designed for TinyML machine learning workloads using the CoolFlux DSP and Cortex-M3. - What microphones are integrated on the board?
It has 2 PDM MEMS microphones: TDK-Invensense ICS-41350. - Does the board include motion sensing?
Yes, it includes a 6-axis MEMS accelerometer and gyroscope TDK-Invensense ICM-20602. - How is wireless connectivity provided?
Bluetooth Low Energy v4.2 is provided by the ABOV A31R118 and an antenna. - Is there on-board data logging storage?
Yes, it includes a 64Mbit serial Flash for data logging. - What environmental sensor is included?
It includes a BOSCH BMP388 pressure and temperature sensor. - Can the board operate on battery power?
Yes, it has a battery cradle for a CR2032 battery. - Does the board support expansion for other RF interfaces?
Yes, it has an extension via a Micro SD card slot for other RF interfaces. - What interfaces are available for serial communication and power?
It provides a 6-pin UART and power port.
