The difference between KF (model fit) and KF (model mismatch)

[jiangyy630]

Dear author, hello. I have two questions that I would like to ask you. The first question: When I run the main_linear_canical.py file in the main code package, I get that the difference between KF (model fit) and KF (model mismatch) is more than 3 [dB], which should be greater than 20 [dB]. But when I set F as the identity matrix, I got the same 3 [dB] as in the paper. Why is this? The second question: When I ran the main_linear.py file in the architecture - # 1 code package, I found that the difference between KF (model fit) and KF (model mismatch) was more than 3 [dB], which should be around 24 [dB]. Why is this?

[jiangyy630]

Regarding the two questions I mentioned, perhaps we should use the one you mentioned in your paper: "In our numerical research, when introducing model uncertainty, we optimize the performance of the MB algorithm by carefully adjusting the covariance matrix, usually through grid search."? Where is this part reflected in the code? Or does this part of the work require me to manually adjust the code covariance matrix myself?

[jiangyy630]

Or, how do I modify the parameters in the main code package and the architecture - # 1 code package when I need to draw images under certain information in my paper? I suspect it was my improper operation process. Finally, I also encountered a problem that I have been unable to solve: