cancel
Showing results for 
Search instead for 
Did you mean: 

STM32 Variant selection for time series machine learning application. For gas sensors data analysis

Hpott.2
Associate

I wanted to classify gas sensors data which is acquired through industrial sensors using Machine learning algorithm on STM board. Any idea which variant of STM32" will work best for this application?

1 ACCEPTED SOLUTION

Accepted Solutions
fauvarque.daniel
ST Employee

If you have a neural network you can easily use the X-CUBE-AI pack (extension of STM32CubeMX) in the mcu finder of STM32CubeMX to select the MCU that will meet your requirements.

The choice depends on the complexity of the network and the associated ram and flash needed to run the network and if you want to have a low power MCU (STM32L4) or a high performance MCU (STM32F4, STM32F7, STM32H7)


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

View solution in original post

3 REPLIES 3
fauvarque.daniel
ST Employee

If you have a neural network you can easily use the X-CUBE-AI pack (extension of STM32CubeMX) in the mcu finder of STM32CubeMX to select the MCU that will meet your requirements.

The choice depends on the complexity of the network and the associated ram and flash needed to run the network and if you want to have a low power MCU (STM32L4) or a high performance MCU (STM32F4, STM32F7, STM32H7)


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
Hpott.2
Associate

My experience with USB type sensor data(USB MOX stick) interfacing was bad with MCU kit. Does any of the above STM Module specially M4 series have good or better support for my USB type sensor data for which I would deploy my ML algorithm.

darla14
Senior

If you have a neural network you can easily use the X-CUBE-AI pack (extension of STM32CubeMX) in the mcu finder of STM32CubeMX to select the MCU that will meet your requirements.

> You mean to say , neural network from any other source(like running on Desktop) , Not necessary generated and workable on any other non STM32 MCU?