- STMicroelectronics
- NEXT Mobility
- ICT and Industrial
- Smart Factories and Robotics
iNEMO™ Inertial Module
Features such as built-in state machines and machine learning cores allow for some data processing within the sensor.
In addition to conventional sensor functions, it is easy to implement functions such as detecting abnormal operation of various devices.
In addition, by performing data processing within the sensor, the load on the controller is reduced, contributing to reduced power consumption in applications.
It is also ideal for battery-powered applications.
STMicroelectronics' MEMS sensor special page can be found here
NEW
See here for development examples using the device's built-in Intelligent Sensor Processing Unit (ISPU) and the company's NanoEdge AI Studio machine learning library generation tool.
Notable Features
Machine Learning Core (MLC)
The acquired data can be classified using a pre-prepared decision tree.
ST also provides a free GUI tool that can generate decision trees.
low power consumption
The device consumes low power, enabling local algorithm processing of machine learning algorithms, for example, to run on the order of μA.
Qvar
The Qvar function, which detects potential fluctuations, can be used for applications such as presence detection, and when combined with functions such as the machine learning core, more advanced sensing can be achieved.
Use Cases
Smartwatch
Leveraging the machine learning core, the user's exercise state (running, walking, etc.) can be determined within the sensor.
The Qvar function also allows you to detect whether the device is attached or detached.
Monitoring the operating status of industrial equipment
Leveraging the machine learning core, you can detect abnormal equipment behavior by monitoring the vibrations emitted by the equipment.
VR headset
In addition to highly accurate acceleration and gyro sensing, it also enables more advanced gesture detection.
Inquiry
Related Product Information
Link to Related Technical Columns
Posture detection achieved with a microcontroller-based AI system: STMicroelectronics NanoEdge AI Studio/VL53L8CX
The model built with NanoEdge AI Studio is implemented on VL53L8CX and STM32, enabling low-cost, privacy-conscious posture detection.
The technological strengths of the STM32W series: wireless, security, and low power consumption all on one chip
The STM32W is a wireless SoC (microcontroller with built-in radio) that provides hardware security, low power consumption, and large memory capacity, enabling long-term operation of IoT devices and multi-protocol support.
SoC for IoT with Sub-GHz Wireless on a Single Chip - Low-power, High-reliability Wireless Design Realized by the STM32WL Series -
The STM32WL is a low-power SoC that integrates a Sub-GHz radio and an MCU, and supports long-distance IoT development with LoRa-compatible and certified modules.
Features and selection points for each STM32 microcontroller series
We will compare and explain the features and uses of the six major STM32 series (C0/G4/H5/H7/N6/U5) in terms of performance, power consumption, security, and AI functions.
Select ST's power semiconductor package compatibility with BCP
To address semiconductor supply risks, we will provide a detailed explanation from a BCP perspective on JEDEC-compliant package compatibility, the characteristics of representative TO-series packages, and considerations for heat, mounting, and reliability during design.
Types and Structure of SILICONE MOS FETS- ST's MOS FETS Lineup
This book explains the structure and characteristics of ST's planar/trench/superjunction MOS FETS, their application-specific selection, product lineup, and long-term supply, using diagrams and a practical perspective.