Scribd
Upload
70 views2 pages

ECE431 - Signal Detection and Estimation Theory Assignment 1

This document contains instructions for Assignment 1 of the ECE431 course on signal detection and estimation theory. It lists 5 questions regarding minimum mean squared error (MMSE) estimation, maximum a posteriori (MAP) estimation, least squares estimation, and maximum likelihood estimation. The questions involve estimating unknown parameters from noisy observations following different probability distributions, with some additional constraints or prior information provided. Students are asked to show their work and clearly state any additional assumptions made for full marks.

Uploaded by

Mehthab Saheba Shaik
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
70 views2 pages

ECE431 - Signal Detection and Estimation Theory Assignment 1

This document contains instructions for Assignment 1 of the ECE431 course on signal detection and estimation theory. It lists 5 questions regarding minimum mean squared error (MMSE) estimation, maximum a posteriori (MAP) estimation, least squares estimation, and maximum likelihood estimation. The questions involve estimating unknown parameters from noisy observations following different probability distributions, with some additional constraints or prior information provided. Students are asked to show their work and clearly state any additional assumptions made for full marks.

Uploaded by

Mehthab Saheba Shaik
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

ECE431 - Signal Detection and Estimation Theory

Assignment 1
Date given: 9 April, 2020 Maximum marks: 50
Due date: 16 April, 2020

Instructions:

1. Write legibly and clearly explain your steps. Upload pictures/scan of your solutions on Moodle.

2. Clearly mention any additional assumptions you make that are not given in the question.

Q1. [10] Observations x[n] are given by

x[n] = An2 + w[n], n = 0, 1, . . . , N − 1,

where w[n] is white Gaussian noise (WGN) with mean zero and known variance σ 2 . It is given
2 ). Find the MMSE estimator of A.
that A is independent of w[n] and has distribution N (0, σA

Q2. [10] The data point x is known to have the conditional PDF
1
p(x|θ) = e−|x−θ| , −∞ < x < ∞
2
and θ is a random parameter with density given by
(
λe−λθ , θ ≥ 0
p(θ) =
0, θ < 0

where λ is a known constant. Find the MMSE and MAP estimates of the parameter θ.

Q3. [10] It is known that given A, x has a Gaussian mixture density given by

1 1  x2  1 1  (x − A)2 
p(x|A) = √ exp − 2 + √ exp −
2 2πσ 2 2σ 2 2πσ 2 2σ 2

Find the MAP estimate of A for the following prior densities on A:

(a) [5] A is a uniform random variable in [0 β].


(b) [5] A is an exponential random variable with parameter β.

Here σ 2 and β are known parameters.

1
Q4. [10] Observations x[n] are noisy measurements of the signal model

s[n] = 2θ1 + θ2 , n = 0, 1, . . . , N − 1
s[n] = θ1 − 2θ2 , n = N, N + 1, . . . , 2N − 1.

(a) [5] Find the Least Squares (LS) estimate of θ = [θ1 θ2 ]T .


(b) [5] If it is additionally given that θ1 + θ2 = 0, find the LS estimate of θ which satisfies this
constraint.

Q5. [10] Let 1, 2, . . . , N be an arbitrary indexing of all the countries in the world (assume there are
N countries). It is hypothesized that, during a global flu pandemic, the cumulative total of the
number of people infected by the virus so far, in the n-th country, is Poisson distributed at the
end of any given day. The mean of this Poisson distribution is λt where λ is the rate constant
and t is the number of days (integer) since the pandemic has been present in a country (t > 0).
An estimate of λ is to be found on the T -th day since the first ever case was recorded globally.
At the end of T -th day, let there be x[n] infected people in the n-th country and it is given that
the pandemic first appears in this country k[n] days after the first ever case is globally recorded,
0 ≤ k[n] < T . Assume that the number of people infected is independent across countries and
that all countries have been infected by T -th day. Find the maximum likelihood estimate (MLE)
of λ in terms of T , x[n], and k[n].

You might also like