LSM6DSOX manual configuration for MLC

[Tam Tran]

Hi,

I am evaluating the MCL on LSM6DSOX. I am using a custom board, not the official motherboard, so Unico cannot communicate with my hardward to upload the configuration to the chip. I think I need to do the configuration manually

(basing on Weka decision tree .txt file from manually generated .ARFF files) but I stucked...

Anyone succeeded the configuration manually because I found no documentation on this? Could you please kindly give me some instructions on this? About how to change registers properly, which registers should be changed etc... I am reading the datasheet and application notes from ST but I am still much confused ...

Thank you very much.

[Eleon BORLINI]

​Hi @Tam Tran​ , we usually suggest users not to create an .arff file with tools different from Unico. What our experts suggest you is to try to follow these steps:

• Download Unico
• Launch Unico in offline mode, deselecting the checkbox: “Communication with the motherboard" on the init panel
• Convert your datalogs in a Unico-like format and upload in Unico
• Configure the MLC following Unico instructions, generating both the .arff file and the .ucf file in this way
• You can then generate the .c code for your library

Btw, you can check if these online-available already trained MLCs are ok for your immediate purpose.

Regards

[Tam Tran]

Thank you very much for your answer,

I ordered STEVAL-MKI197V1 and STEVAL-MKI109V3 and are waiting for their arrival to learn about Unico-like format datalogs.

Moreover, for many reasons, for a medical application, we are going to need a process which is transparent, well documented and can be validated.  We would like to talk about a collaboration with ST, focusing on machine learning core.  Could we contact you directly with a more detailed questions, rather than through the forum? We would then like to explain better what we are working on.

Regards.

[Eleon BORLINI]

Hi @Tam Tran​ , the application you are targeting seems interesting. We have some libraries related to HAR (human activity recognition), and if you are interested i can suggest some online documentation (UM2524, UM2193). Which is your target market, in more detail? You can answer me with a private message. Please note also that you can receive support from our distributors, if needed. Regards

[Tam Tran]

Thank you very much. Message sent.