The attached lab guide walks through step-by-step how to use the new Application Software Pack for the ML-based System State Monitor found on Github.
This is related to AN13562 - Building and Benchmarking Deep Learning Models for Smart Sensing Appliances on MCUs
This lab guide was written for RT1170 but the application software pack now also supports the LPC55S69 and Kinetis K66F devices. It can also be ported to other i.MX RT, LPC, and Kinetis devices.
There's also a document on Dataset creation that goes into more detail on the considerations to make when gathering data. For more details visit the ML-based System State Monitor website on NXP.com
There are two lab options:
- Using the FXOS8700CQ accelerometer found on some EVKs and also the FRDM-STBC-AGM01 sensor board.
- Using the FXLS8974CF accelerometer found on the ACCEL 4 Click board or the FRDM-STBI-A8974 board.
The FXLS8974CF is the latest accelerometer from NXP and is what is recommended to use.
The video below walks through the steps for the FRDM-STBC-AGM01 but there may be updated details in the lab guide so follow the lab guide if there is any differences.
