• State Verified Answer
  • Locked Locked
  • Replies 1 reply
  • Subscribers 73 subscribers
  • Views 332 views
  • Users 0 members are here
Attachments (0)
Nordic Case Info
  • Case ID: 277674
Options
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Why machine_learning firmware on Thingy:52 use LIS2DH sensor instead of MPU-9250?

Haroldo

The Thingy:52 application uses LIS2DH in low power standby mode and the MPU-9250 for advanced motion tracking.


Why machine_learning firmware used LIS2DH sensor instead of MPU-9250?

Parents
  • +1

    Hello,

    The machine learning application for the Thingy:52 is a pretrained model to showcase the power of Tiny ML (µC Machine Learning), built with Edge Impulse Studio. I do not know if there is any particular reason for using the LIS2DH instead of the MPU-9250 in the example, but since they both provide acceleration data I suppose the LIS2DH is good enough for the purpose of the demonstration.

    Best regards,
    Karl

Reply
  • +1

    Hello,

    The machine learning application for the Thingy:52 is a pretrained model to showcase the power of Tiny ML (µC Machine Learning), built with Edge Impulse Studio. I do not know if there is any particular reason for using the LIS2DH instead of the MPU-9250 in the example, but since they both provide acceleration data I suppose the LIS2DH is good enough for the purpose of the demonstration.

    Best regards,
    Karl

Children
No Data
Related
Terms of service