In this simulation, I just used the one algorithm named as least mean square (LMS) for the system identification task. It is designed for those who are new to adaptive signal processing. You can modify this example for CLMS, NLMS, LMF, qLMS or even to FLMS etc very easily.
Shujaat Khan (2020). System Identification using least mean square (LMS) algorithm (https://www.mathworks.com/matlabcentral/fileexchange/63935-system-identification-using-least-mean-square-lms-algorithm), MATLAB Central File Exchange. Retrieved .
Abdelwahab Afifi for complex signal or system, Please see https://www.mathworks.com/matlabcentral/fileexchange/60393-plant-identification-using-lms-and-clms
and also see this paper https://ieeexplore.ieee.org/document/1451737
When I use the Algorithm in a complex system where the input and the output are complex. I didn't get the expected results/curves. Does the command need to be modified adapted to the complex values?
What is the difference between system identification and blind system identification.
Here the purpose of adding noise in desired output signal is to simulate the measurement noise scenario. If you add noise in input signal then you will get the response of the system for that noisy signal, which is not equals to the measurement noise.
Why is input the original signal and desired signal is noise-corrupted signal? Is that correct? Please help soon.
thanks, useful script!
- Monte Carlos Simulations