Can I use the deep learing toolbox to find relationship between input and response?

4 views (last 30 days)
Hello!
I am trying to find a way of compensating a thermal error.
I have experimental data with the output error position (thin line plots) plotted against the input temperature measured with a thermocouple (thick line plot).
I have tried to come up with a precition algoritm but haven't been able to get it spot on.
I would like to come up with a way of predicting the output given the current temperature (and all temperatures up until that point).
Is the deep learnign toolbox apropriate for this or would something else be better? Are there any guides on how to achieve something like this.
Thanks,
Steve
thermal error.png

Answers (1)

Sai Bhargav Avula
Sai Bhargav Avula on 5 Aug 2019
Edited: Sai Bhargav Avula on 5 Aug 2019
I understand that you are using a sequential temperature input, in which case you can use LSTM network of the deep learning toolbox. But if the data samples are less then you can use any Machine learning techniques like Boosting algorithms in Statistics and Machine Learning toolbox.  

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!