1
$\begingroup$

I want to create a dependency graph of some sensors in the network ( based on their reported value). Please note that a change in the values of sensors is related to each other. For example, if the measured value by a sensor increases, it is possible to recognize the sensors which their measured values will be affected by this increase. This is because of the mathematical logic behind the reported values and sensor placement.

I also need to have some weights representing the weights of the dependency. In other words, this number shows how much two sensors in the created graph are dependent on each other (dependency rate).

Now, I am wondering how can I do that and with what tools and algorithms?

Thank you very much in advance for your help.

Improve this question
$\endgroup$
2
  • $\begingroup$ This is a very common problem that is widely studied in CS and statistics. The questions of which sensors change the values of other sensors, and the strength of that causal connection, are in some ways similar and some ways different. For the first one, I would read up on the PC Algorithm to start. For the second, Structural Equation Modeling. These are both very hard problems. If you present a more mathematically detailed description of the problem and assumptions you're willing to make, someone might be able to give a detailed answer. $\endgroup$
    – Sheridan Grant
    Sep 15, 2019 at 22:40
  • $\begingroup$ Thank you, Sheridan. Imagine someone just has data and don't know anything about the mathematical relations behind them and only want to use data (provided dataset which is a matrix) to achieve such a goal. Is it possible to use PC Algorithm and Structural Equation Modeling to get the first and second aim? Please also guide me with the best tools for such algorithms. Thanks. $\endgroup$
    – Arkan
    Sep 16, 2019 at 3:25

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.