SL-SNMTS011601V1

Solution Description

A solution detecting human motions in real-time using artificial intelligence (AI) and machine learning (ML) algorithms for pattern recognition and then display activity information on a smartphone or battery-operated handheld device via a wireless connection.

The application uses an ultra-low-power, high-accuracy LSM6DSL 6DoF inertial measurement unit (IMU) to collect motion data that is sent to an ultra-low-power STM32L475VG microcontroller with a single-precision floating point unit (FPU) and ST's adaptive real-time accelerator (ART Accelerator™) running one of three different pattern recognition algorithms (FP-AI-SENSING1) based on artificial neural networks for real-time human activity recognition (HAR).

HAR Model	Benefit	Design focus	Recognized activities
GMP (5 classes)	Better performance	More frequent inference thanks to overlapping windows	Stationary, walking, jogging, biking, and driving
IGN (5 classes)	Smaller RAM footprint	Lower power consumption thanks to extended deep sleep periods	Stationary, walking, jogging, biking, and driving
IGN WSDM (4 classes)	Smaller Flash footprint Trained with public dataset	Lightweight deep learning models Easy to reproduce with public models and datasets	Stationary, walking, jogging, and climbing stairs

An ultra-low-power, dual-core, multi-protocol STM32WB5MMG wireless module with a royalty-free Bluetooth® Low Energy 5.2 protocol stack sends the results of the pattern recognition algorithms to a smartphone or any other battery-operated device where it can be integrated with a dedicated mobile app. This app can be developed based on our ready-to-use BLE sensor mobile application for Android and iOS (STBLESensor).

This type of application is useful across a wide variety of domains including wearables, safety, environmental monitoring, healthcare & fitness, and transportation.

Key Product Benefits

STM32L475VG - powerful DSP capable microcontroller

This microcontroller with Arm^® Cortex^®-M4 core has the necessary peripherals to manage incoming digital audio signals and the processing power and memory to ensure rapid and accurate audio scene recognition with minimal power consumption.

LSM6DSL - 3D accelerometer and gyroscope.

System-in-package featuring a 3D digital accelerometer and a 3D digital gyroscope performing at 0.65 mA in high-performance mode and enabling always-on low-power features

STM32WB5MMG - ultra-low-power BLE 5.2 module

Ultra-low-power, compact Bluetooth module with a completely royalty-free Bluetooth LE 5.2 protocol stack

Read more Read less

All Features
Complete ready-to-use firmware featuring an implementation of neural networks for real-time human activity recognition (HAR)

All motion data is processed on the STM32 microcontroller, leveraging modern computing capabilities at the edge

3 different artificial neural network (ANN) models with various properties to fit with solution requirement and able to recognize up to 5 different classes (walking, jogging, climbing stairs, biking and driving)

Ultra-low-power implementation based on the use of a real-time operating system (RTOS)

Compatible with our ST BLE Sensor mobile app (Android/iOS) to display HAR algorithm results

Easy portability and scalability across different STM32 MCU series thanks to STM32Cube

Compliant with Bluetooth® Low Energy (BLE) SIG specification v5.2
Read more Read less

Kit Description

Distributor availability of B-L475E-IOT01A2

Distributor Name	Region	Stock	Min. Order	Third party link

Distributor reported inventory date:

Distributor Name

Distributor reported inventory date:

Distributor availability of B-L475E-IOT01A1

Distributor Name	Region	Stock	Min. Order	Third party link

Distributor reported inventory date:

Distributor Name

Distributor reported inventory date:

Running ready-to-use firmware, this motion sensing application for real-time human activity recognition (HAR) is designed around the STM32L4 Discovery kit for IoT nodes (B-L475E-IOT01A) with built-in low-power wireless connectivity associated with an STM32Cube function pack (FP-AI-SENSING1) for ultra-low-power motion sensing with artificial intelligence (AI). It features an implementation of neural networks running in an ultra-low-power STM32L475VG microcontroller for real-time human activity recognition (HAR) using 3D accelerometer and 3D gyroscope data provided by the onboard ultra-low-power, high-accuracy LSM6DSL motion sensor.

Please choose the correct board for your development needs.

Board	Frequency Band
B-L475E-IOT01A	Sub-GHz (915 MHz) RF module
B-L475E-IOT01A2	Sub-GHz (868 MHz) RF module

Featuring complete ready-to-use firmware including pre- and post-processing functions such as filtering gravity, reference rotation, and temporal filtering, the STM32Cube function pack (FP-AI-SENSING1) is designed for human activity recognition based on the outputs generated by neural networks (NN) implemented by libraries generated by the X-CUBE-AI extension pack using the STM32Cube initialization code generator (STM32CubeMX).

Offering many extended capabilities, the X-CUBE-AI extension pack can also be used to convert and optimize user AI models to customize applications for various use cases. For example, it is possible to add different activity classes (dancing, horse riding, etc.) or create other types of applications including asset tracking solutions where it is possible to determine if a package fell, was exposed to shocks and vibrations, or if it was placed upside down.
Once the activity data is processed, the results can be sent by the board’s Bluetooth module to a smartphone or any other battery-operated device where they can be displayed using a dedicated mobile app. Motion data can also be used to adapt a smart object's behavior based on user activity; for example, switching peripherals to low-power modes when the device has been immobile for a certain period of time.

More importantly, the mobile app can also be used to control data collection if users want to train their own AI algorithms using their own data. This app can be developed based on our ready-to-use BLE sensor mobile application for Android and iOS (STBLESensor).

Note that while the STM32L4 Discovery kit for IoT nodes (B-L475E-IOT01A) embeds a Bluetooth® V4.1 module (SPBTLE-RF) for evaluation purposes, we recommend using an ultra-low-power, dual-core, multi-protocol STM32WB5MMG wireless module with a royalty-free Bluetooth® Low Energy 5.2 protocol stack.

Get the Software

All Evaluation Features

Complete ready-to-use firmware featuring an implementation of neural networks for real-time human activity recognition (HAR).

FP-AI-SENSING1 is an STM32Cube function pack featuring a complete ready-to-use firmware for human activity recognition on the basis of outputs generated by neural networks (NN). The NN are implemented by libraries generated by the X-CUBE-AI extension for STM32CubeMX tool.

The B-L475E-IOT01A Discovery kit connects to a smartphone via a Bluetooth connection.

The BLE sensor mobile application for Android and iOS (STBLESensor) displays HAR results on an associated smartphone
Read more Read less

MEMS and sensors

Part number	Description
LSM6DSL	iNEMO 6DoF inertial measurement unit (IMU), for smart phones and battery operated IoT, Gaming, Wearable and Consumer Electronics. Ultra-low power and high accuracy

Part number

LSM6DSL

iNEMO 6DoF inertial measurement unit (IMU), for smart phones and battery operated IoT, Gaming, Wearable and Consumer Electronics. Ultra-low power and high accuracy

Microcontrollers & microprocessors

Part number	Description
STM32L475VG	Ultra-low-power with FPU Arm Cortex-M4 MCU 80 MHz with 1 Mbyte of Flash memory, USB OTG, DFSDM
STM32WB5MMG	Ultra-low-power Module - Dual core Arm Cortex-M4 MCU 64 MHz, Cortex-M0+ 32 MHz with 1 Mbyte of Flash memory, Bluetooth LE 5.4, 802.15.4, Zigbee, Thread, Matter, USB, LCD, AES-256

Part number

STM32L475VG

Ultra-low-power with FPU Arm Cortex-M4 MCU 80 MHz with 1 Mbyte of Flash memory, USB OTG, DFSDM

STM32WB5MMG

Ultra-low-power Module - Dual core Arm Cortex-M4 MCU 64 MHz, Cortex-M0+ 32 MHz with 1 Mbyte of Flash memory, Bluetooth LE 5.4, 802.15.4, Zigbee, Thread, Matter, USB, LCD, AES-256

Motion sensing application using AI to recognize human activities

Solution Description

Key Product Benefits

STM32L475VG - powerful DSP capable microcontroller

LSM6DSL - 3D accelerometer and gyroscope.

STM32WB5MMG - ultra-low-power BLE 5.2 module

All Features

Kit Description

Estimated cost

Something went wrong with the server request. Please try again in a few moments.

Project Title:

Project Description:

Application:

End Application:

Nature of Business:

Military Related:

Country/Region where the Software will be used:

Comment:

Request for software successfully submitted. The approval process may take up to 48 hours. After you have been approved, you should receive a link to the requested software via email.

Get the Software

All Evaluation Features

MEMS and sensors

Microcontrollers & microprocessors

Did you know?