Scribd
Upload
43 views2 pages

E1 244: Homework - 6: 1 Topics

This homework assignment involves three topics: 1. Finding the Bayes rule and minimum Bayes risk for binary hypothesis testing with uniform costs and equal priors. 2. Deriving a Bayesian decision rule for a communication system performing binary signaling over an additive white Gaussian noise channel. 3. Performing hypothesis testing on a non-parametric (NP) problem to distinguish between two hypotheses based on a received signal plus noise, and analyzing the test's performance.

Uploaded by

Rakesh Kota
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
43 views2 pages

E1 244: Homework - 6: 1 Topics

This homework assignment involves three topics: 1. Finding the Bayes rule and minimum Bayes risk for binary hypothesis testing with uniform costs and equal priors. 2. Deriving a Bayesian decision rule for a communication system performing binary signaling over an additive white Gaussian noise channel. 3. Performing hypothesis testing on a non-parametric (NP) problem to distinguish between two hypotheses based on a received signal plus noise, and analyzing the test's performance.

Uploaded by

Rakesh Kota
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

E1 244: Homework - 6

Assigned: 30 Mar. 2011

1 Topics
• Bayesian detection

• NP Testing

2 Problems
1. Find the Bayes rule and minimum Bayes risk for a binary H.T. with uni-
form costs and equal priors, with

c0 y 2 |y| ≤ 1

p0 (y) =
0 else

c1 (3 − |y|) |y| ≤ 3
p1 (y) =
0 else

where c0 and c1 are constants.

2. A communication system uses binary signaling by sending one of the


following two signals: s1 (t) to send one, and s0 (t) to send zero, where
s1 (t) = −As(t), s0 (t) = As(t), A > 0, and

1 0<t<1
s(t) =
0 else

The transmitted signal is corrupted by zero mean white Gaussian noise


n(t) with autocorrelation function Rn (τ ) = σ 2 δ(τ ), so that the received
signal is given by

−As(t) + n(t) 1 sent
y(t) =
As(t) + n(t) 0 sent

The receiver computes the decision statistic


Z ∞
Z= y(t)s(t)dt
−∞
The receiver would like to decide whether 0 or 1 was sent, or (if it is not
confident about a 0/1 decision), erase the signal. We would like to obtain
a Bayesian decision rule for doing this as follows.
Let Θ = {0, 1} and A = {0, 1, e}. The observation is Z . Assume the cost
structure

 1 a 6= θ, a = 0, 1
C(a, θ) = 0 a=θ
c a=e

where θ = 0, 1 and where c ∈ (0, 1) is the cost of an erasure.


(a) Find the Bayes rule for equal priors. Simplify the form of the rule as
much as possible and specify its dependence on the problem param-
eters c, A, and σ 2 .
(b) For d = A/σ = 5, find c and a corresponding Bayesian decision
rule δA so that the probability of erasure p1 is twice the probability
of error p2 . Compare with the values of p1 and p2 for a Bayesian
decision rule δB corresponding to c = 1/2 .
3. NP Testing. Consider the hypothesis testing problem

H0 : ri = ni , i = 1, . . . , N, (N odd)
H1 : ri = m + ni ,

and let r , [r1 , . . . , rN ]T .


(a) Find the Log-Likelihood Ratio (LLR), defined as
 
p(R|H1 )
LLR = log
p(R|H0 )

(b) (LLR as a random variable.) Find p(LLR |H0 ) and p(LLR |H1 ).
Plot.
(c) Matlab. Define δ(ri ) as

1 ri ≥ η
δ(ri ) =
0 otherwise

And let δ (1) (r) be


 PN
(1) 1 i=1 δ(ri ) ≥ (N − 1)/2
δ (r) =
0 otherwise

That is, δ (1) (r) takes a majority vote among δ(ri ). Find PF , PD and
plot the ROC.
(d) Find the α-level NP test and plot its ROC. Compare with (d).

You might also like