• State Resolved
  • Locked Locked
  • Replies 2 replies
  • Subscribers 30 subscribers
  • Views 281 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Classification Models

Mohamed Naceur Hassine
Intellectual 460 points
Other Parts Discussed in Thread: AWR1843

Hello,

I'm using AWR1843 radar and I want to implement a Classification model in the OOB demo. (Ps : After clustering the objects using the DBSCAN algorithm, I am now trying to classify them).

So here is the classification models that I will test it : 

 - DecisionTreeRegressor

 - GradientBoostingRegressor

 - KNeighborsRegressor

 - LinearRegression

 - RandomForestRegressor

 - SGDRegressor

I want to know which of these models can be implemented in AWR1843 Millimeter Wave Radar (In general: can be used in an embedded system).

Thank you,

Ben Hassine

  • +1
    TI__Mastermind 20605 points

    Hi Ben,

    The implementation feasibility of these algorithms can depend on many things. To narrow it down, is it possible for you to give approximate memory and timing constraints for these algorithms considering your use case? Also, have you performed analysis of memory and timing on the 1843 after your inclusion of the clustering algorithm into the demo? With these inputs, you should be able to determine whether it will be possible.

    Regards,

    Kaushik

  • 0 in reply to Kaushik Gowda
    Intellectual 460 points

    Hi Kaushik,

    Thank you for your reponse. I will see the approximate memory and time constraints for these algorithms and look for ones that can be adapted to AWR1843 (OOB demo) and get back to you. 

    Regards,

    Ben Hassine