STMicroelectronics Web Tools and Smart Sensors Accelerate the Implementation of AIoT Projects

Deploy machine learning models for sensor node-to-cloud solutions on MEMS machine learning cores

China, November 19, 2024 - STMicroelectronics has launched a new web-based tool, ST AIoT Craft, which simplifies the development of node-to-cloud AIoT (Artificial Intelligence of the Internet of Things) projects and related network configuration on the machine learning core (MLC) of STMicroelectronics smart MEMS sensors.

The MLC machine learning core is a unique feature of the ST MEMS product portfolio that enables sensors to run decision tree learning models directly. MLC can run autonomously without the involvement of the host system, with low latency and low power consumption, and efficiently handle tasks that require AI functions, such as classification and pattern detection.

ST AIoT Craft also integrates all the steps required to develop and configure IoT projects using MLC to implement AI in sensors, and provides developers with a safe and easy-to-use development method that provides strong security protection for cloud data. This is an online tool that runs on a web browser and does not require software downloads, making it very convenient to use. Because there is no need to download and install, it saves users a lot of time and facilitates collaboration between teams (for example, AI experts and embedded software engineers).

In this software, the AutoML function is a tool for creating decision tree models that automatically select the best attributes, filters, and window sizes for sensor data sets. The framework can also train decision trees to run on MLC and generate configuration files to deploy trained models. For beginners, this software is a quick start guide to get started with STMicroelectronics smart sensors, which simplifies the development of AI applications. In addition, when you need to configure the network connection of the IoT project, you can use the DSM tool (Data Sufficiency Module) to set up the gateway. The DSM module can intelligently filter the data points to be transmitted to the cloud, optimize the amount of communication data, minimize power consumption, and facilitate future secondary training.

Users can find code examples on how to use decision trees to build IoT sensor-to-cloud solutions, including fan coil monitoring, asset tracking, human activity recognition, and head gestures. These examples can be downloaded and installed on STMicroelectronics IoT reference boards, such as SensorTile.box Pro, STWIN, and STWIN.box, and developers can run sample benchmarks, customize these examples, import their own data, or improve existing datasets to speed up project development.

ST AIoT Craft is included in the ST Edge AI Suite software package. This package provides developers with all the software tools, examples, and models needed to develop and deploy machine learning algorithms on ST's edge AI products. ST's edge-AI edge intelligence products include STM32 microcontrollers (MCUs), Stellar MCUs, and MEMS sensors with built-in MLC or intelligent sensor processing units (ISPUs).

STM32 is a registered and/or unregistered trademark of STMicroelectronics International NV or its affiliates in the EU and/or elsewhere. In particular, STM32 is registered in the United States Patent and Trademark Office.