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

[Hpott.2]

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?

[fauvarque.daniel · Accepted solution]

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)

[Hpott.2]

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]

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?