Hello,(adsbygoogle = window.adsbygoogle || []).push({});

I am trying to estimate transfer function of unknown LTI system, given output and assumed input as point process.

I have measurement of output, while input, which is assumed to be point process, could be created synthetically using known times and amplitudes.

My questions:

1. What is the best approach to estimate spectrum of synthetic point process signal (a-parametric/parametric/AR...)?

2. Is there theoretical formulation for point process spectrum, which could be used to create numerical instance for my transfer estimation purpose.

3. Is there a way to estimate zero/poles of system given only output measurement and assumptions on input, without calculation of input and output signals spectrums?

4. Is there methodology to estimate number of zeros/poles based on given input and output?

Thanks,

Alexei Nomazov,

Algorithms Researcher.

**Physics Forums - The Fusion of Science and Community**

The friendliest, high quality science and math community on the planet! Everyone who loves science is here!

# A LTI Impulse Response Estimation with Point Process Input

Tags:

Have something to add?

Draft saved
Draft deleted

Loading...

Similar Threads - Impulse Response Estimation | Date |
---|---|

Which mathematicians were most responsible for formalizing mathematics | Jul 8, 2013 |

Convolution integral and fourier transform in linear response theory | Apr 15, 2013 |

Convolution of Impulses | Jan 23, 2012 |

Convolution in Discrete time of a function with Impulse with delay? | Feb 14, 2010 |

Heaviside function and Unit impulse (delta) help | Apr 8, 2009 |

**Physics Forums - The Fusion of Science and Community**