Reasoning Under Uncertainty

 Most tasks requiring intelligent behavior have some

degree of uncertainty associated with them.

 The type of uncertainty that can occur in knowledge-

based systems may be caused by problems with the
data. For example:

1. Data might be missing or unavailable

2. Data might be present but unreliable or

ambiguous due to measurement errors.

3. The representation of the data may be imprecise

or inconsistent.

4. Data may just be user’s best guess.

5. Data may be based on defaults and the defaults

may have exceptions.

1
 The uncertainty may also be caused by the
represented knowledge since it might

1. Represent best guesses of the experts that are

based on plausible or statistical associations they
have observed.

2. Not be appropriate in all situations (e.g., may

have indeterminate applicability)

 Given these numerous sources of errors, most

knowledge-based systems require the incorporation of
some form of uncertainty management.

 When implementing some uncertainty scheme we

must be concerned with three issues:

1. How to represent uncertain data

2. How to combine two or more pieces of uncertain
data
3. How to draw inference using uncertain data

We will introduce three ways of handling uncertainty:

2
 Probabilistic reasoning.

 Certainty factors

 Dempster-Shafer Theory

3
 1. Classical Probability
The oldest and best defined technique for managing
uncertainty is based on classical probability theory. Let us
start to review it by introducing some terms.

 Sample space: Consider an experiment whose

outcome is not predictable with certainty in advance.
However, although the outcome of the experiment
will not be known in advance, let us suppose that the
set of all possible outcomes is known. This set of all
possible outcomes of an experiment is known as the
sample space of the experiment and denoted by S.

For example:
 If the outcome of an experiment consists in the
determination of the sex of a newborn child, then
S = {g, b}

where the outcome g means that the child is a girl

and b that it is a boy.

 If the experiment consists of flipping two coins,

then the sample space consists of the following
four points:
S = {(H, H), (H, T), (T, H), (T, T)}

4
 Event: any subset E of the sample space is known as
an event.

 That is, an event is a set consisting of possible

outcomes of the experiment. If the outcome of the
experiment is contained in E, then we say that E has
occurred.

For example, if E = {(H, H), {H, T)}, then E is the

event that a head appears on the first coin.

 For any event E we define the new event E’, referred

to as the complement of E, to consist of all points in
the sample space S that are not in E.

 Mutually exclusive events: A set of events E1, E2, ...,

En in a sample space S, are called mutually exclusive
events if Ei  Ej = , i  j, 1 i, j  n.

5
 A formal theory of probability can be made using
three axioms:

1. 0  P(E)  1.

2.  P(Ei) = 1 (or P(S) = 1)

i

This axiom states that the sum of all events which do

not affect each other, called mutually exclusive
events, is 1.

As a corollary of this axiom:

P(Ei) + P(Ei’) = 1,

where Ei’ is the complement of event Ei.

3. P(E1  E2) = P(E1) + P(E2),

where E1 and E2 are mutually exclusive events. In

general, this is also true.

6
 Compound probabilities

 Events that do not affect each other in any way are

called independent events. For two independent
events A and B,

P(A  B) = P(A) P(B)

Independent events: The events E1, E2, ..., En in a

sample space S, are independent if

P(Ei1  ...  Eik) = P(Ei1) ...P(Eik)

for each subset {i1, ...,ik) {1, ..., n},1 k  n, n  1.

 If events A and B are mutually exclusive, then

P(A  B) = P(A) + P(B)

 If events A and B are not mutually exclusive, then

P(A  B) = P(A) + P(B) - P(A  B)

This is also called Addition law.

7
 Conditional Probabilities

The probability of an event A, given B occurred, is called

a conditional probability and indicated by

P(A | B)

The conditional probability is defined as

P(A  B)
P(A | B) = ------------------, for P(B)  0.
P(B)

 Multiplicative Law of probability for two events is

then defined as

P(A  B) = P(A | B) P(B)

which is equivalent to the following

P(A  B) = P(B | A) P(A)

 Generalized Multiplicative Law

P(A1  A2  ...  An) =
P(A1 | A2  ...  An) P(A2 | A3  ...  An)
... P(An-1 | An) P(An)

8
 An example
As an example of probabilities, Table below shows
hypothetical probabilities of a disk crash using a Brand X
drive within one year.

Brand X Brand X’ Total of Rows

Crash C 0.6 0.1 0.7
No crash C’ 0.2 0.1 0.3
Total of columns 0.8 0.2 1.0

Hypothetical probabilities of a disk crash

X X’ Total of rows
C P(C  X) P(C  X’) P(C)
C’ P(C’ X) P(C’  X’) P(C’)
Total of columns P(X) P(X’) 1

Probability interpretation of two sets

Using above tables, the probabilities of all events can be
calculated. Some probabilities are
(1) P(C) = 0.7
(2) P(C’) = 0.3
(3) P(X) = 0.8
(4) P(X’) = 0.2
(5) P(C  X) = 0.6
(the probability of a crash and using Brand X)

9
(6) The probability of a crash, given that Brand X is
used, is
P(C  X) 0.6
P(C | X) = ------------- = ------- = 0.75
P(X) 0.8

(7) The probability of a crash, given that Brand X is not

used, is
P(C  X’) 0.1
P(C | X’) = ------------- = ------- = 0.50
P(X’) 0.2

 Probabilities (5) and (6) may appear to have similar

meanings when you read their descriptions. However
(5) is simply the intersection of two events, while (6)
is a conditional probability.

The meaning of (5) is the following:

IF a disk drive is picked randomly, then 0.6 of the

time it will be Brand x and have crashed.

In other words, we are just picking samples from the

population of disk drives. Some of those drives are
Brand X and have crashed (0.6), some are not Brand
X and have crashed (0.1), some are Brand X and

10
 have not crashed (0.2), and some are not Brand X
and have not crashed (0.1).

In contrast, the meaning of the conditional

probability (6) is very different

IF a Brand X disk drive is picked, then 0.75 of the

time it will have crashed.

 Note also that if any of the following equation is true,

then events A and B are independent.

P(A | B) = P(A) or

P(B | A) = P(B) or

P(A  B) = P(A) P(B).

11
 Bayes’ Theorem

Note that conditional probability is defined as

P(H  E)
P(H | E) = ------------------, for P(E)  0.
P(E)

i.e., the conditional probability of H given E.

 In real-life practice, the probability P(H | E) cannot

always be found in the literature or obtained from
statistical analysis. The conditional probabilities

P(E | H)

however often are easier to come by;

 In medical textbooks, for example, a disease is

described in terms of the signs likely to be found in a
typical patient suffering from the disease.

 The following theorem provides us with a method for

computing the conditional probability P(H | E) from
the probabilities P(E), P(H) and P(E | H);

12
From conditional probability:

P(H  E)
P(H | E) = ------------------,
P(E)

P(E  H)
Furthermore, we have, P(E | H) = ---------------
P(H)
So,
P(E | H)P(H) = P(H | E)P(E) = P(H  E)
Thus
P(E | H) P(H)
P(H | E) = ---------------------
P(E)

 This is the Bayes’ Theorem. Its general form can be

written in terms of events, E, and hypotheses
(assumptions), H, in the following alternative forms.

P(E  Hi)
P(Hi | E) = -------------------
 P(E  Hj)
j

P(E | Hi) P(Hi) P(E | Hi) P(Hi)

= ----------------------- = ---------------------
 P(E | Hj) P(Hj) P(E)
j

13
 Hypothetical reasoning and
backward induction
 Bayes’ Theorem is commonly used for decision tree
analysis of business and the social sciences.

 The method of Bayesian decision making is also used

in expert system PROSPECTOR.

We use oil exploration in PROSPECTOR as an example.

Suppose the prospector believes that there is a better than
50-50 chance of finding oil, and assumes the following.

P(O) = 0.6 and P(O’) = 0.4

Using the seismic survey technique, we obtain the

following conditional probabilities, where + means a
positive outcome and - is a negative outcome

P(+ | O) = 0.8 P(- | O) = 0.2 (false -)

P(+ | O’)= 0.1 (false +) P(- | O’) = 0.9

 Using the prior and conditional probabilities, we can

construct the initial probability tree as shown below.

14
 Probabilities
No oil oil Prior
Subjective Opinion
P(O’) = 0.4 P(O)=0.6 of site: P(Hi)

– test + test – test + test Conditional

P(-|O’) P(+|O’) P(-|O) P(+| Seismic test result
O) P(E|Hi)
=0.9 = 0.1 = 0.2 = 0.8
P(-O’) P(+O’) P(-O) P(+O) Joint: P(EH)
=0.36 =0.04 =0.12 =0.48 =P(E|Hi)P(Hi)

Initial probability tree for oil exploration

15
 Using Addition law to calculate the total probability
of a + and a - test

P(+) = P(+  O) + P(+  O’) = 0.48 + 0.04 = 0.52

P(-) = P(-  O) + P(-  O’) = 0.12 + 0.36 = 0.48

 P(+) and P(-) are unconditional probabilities that can

now be used to calculate the posterior probabilities at
the site, as shown below.

Probabilities
– test + test unconditional
P(-) = 0.48 P(+)=0.52 P(E)
Posterior
No oil oil No oil oil Of site:
P(O’|-) P(O|-) P(O’|+) P(O|+) P(Hi|E) = P(E|
=3/4 = 1/4 = 1/13 = 12/13 Hi)P(Hi)/P(E)

P(-O’) P(-O) P(+O’) P(+O) Joint: P(EH)

=0.36 =0.12 =0.04 =0.48 =P(Hi|E)P(E)

Revised probability tree for oil exploration

16
 The Figure below shows the Baysian decision tree
using the data from the above Figure. The payoffs are
at the bottom of the tree.
Thus if oil is found, the payoff is
$1,250,000 - $200,000 - $50,000 = $1,000,000
while a decision to quit after the seismic test result gives a
payoff of -$50,000.
A
Event
P(-) = 0.48 P(+)=0.52 Test result
+ or -

D E Act.
Quit or drill
Quit Drill Quit Drill

B C
Event
No oil oil No oil oil
Oil or no oil
P(O’|-) P(O|-) P(O’|+) P(O|+)
=3/4 = 1/4 = 1/13 = 12/13
-$50,000 -$50,000 payoff
-$1,000,000 $1,000,000 -$1,000,000 $1,000,000

Initial Bayesian Decision tree for oil exploration

The assumed amounts are:

Oil lease, if successful: $1,250,000
Drilling expense: -$200,000
Seismic survey: -$50,000

17
 In order for the prospector to make the best decision,
the expected payoff must be calculated at event node
A.

 To compute the expected payoff at A, we must work

backward from the leaves. This process is called
backward induction.

18
 The expected payoff from an event node is the sum of
the payoffs times the probabilities leading to the
payoffs.

Expected payoff at node C

$846,153 = ($1,000,000) (12/13) - ($1,000,000) (1/13)

Expected payoff at node B

-$500,000 = ($1,000,000) (1/4) - ($1,000,000) (3/4)

A $416,000
Event
P(-) = 0.48 P(+)=0.52 Test result
+ or -
-$50,000 $846,153
D E Act.
Quit or drill
Quit Drill Quit Drill

B C
Event
No oil oil No oil oil
Oil or no oil
P(O’|-) P(O|-) P(O’|+) P(O|+)
=3/4 = 1/4 = 1/13 = 12/13
-$50,000 -$50,000 payoff
-$1,000,000 $1,000,000 -$1,000,000 $1,000,000

Complete Bayesian Decision tree for oil exploration

Using backward induction

19
 The decision tree shows the optimal strategy for the
prospector. If the seismic test is positive, the site
should be drilled, otherwise, the site should be
abandoned.

 The decision tree is an example of hypothetical

reasoning or “what if” type of situations.

 By exploring alternate paths of action, we can prune

paths that do not lead to optimal payoffs.

20
 Bayes’ rule and knowledge-based
systems
As we know, rule-based systems express knowledge in an
IF-THEN format:

IF X is true
THEN Y can be concluded with probability p

 If we observe that X is true, then we can conclude

that Y exist with the specified probability. For
example

IF the patient has a cold

THEN the patient will sneeze (0.75)

 But what if we reason abductively and observe Y

(i.e., the patient sneezes) while knowing nothing
about X (i.e., the patient has a cold)? What can we
conclude about it? Bayes’ Theorem describes how we
can derive a probability for X.

21
 Within the rule given above, Y (denotes some piece
of evidence (typically referred to as E) and X denotes
some hypothesis (H) given

P(E | H) P(H)
(1) P(H | E) = -------------------
P(E)
or
P(E | H) P(H)
(2) P(H | E) = -----------------------------------------
P(E | H)P(H) + P(E | H’)P(H’)

To make this more concrete, consider whether Rob has a

cold (the hypothesis) given that he sneezes (the evidence).

 Equation (2) states that the probability that Rob has a

cold given that he sneezes is the ratio of the
probability that he both has a cold and sneezes, to the
probability that he sneezes.

 The probability of his sneezing is the sum of the

conditional probability that he sneezes when he has a
cold and the conditional probability that he sneezes
when he doesn’t have a cold. In other words, the
probability that he sneezes regardless of whether he
has a cold or not. Suppose that we know in general

22
 P(H) = P(Rob has a cold)
= 0.2
P(E | H) =P(Rob was observed sneezing | Rob has a cold)
= 0.75
P(E | H’) = P(Rob was observed sneezing |
Rob does not have a cold)
= 0.2
Then

P(E) = P(Rob was observed sneezing)

= (0.75)(0.2) + (0.2)(0.8)
= 0.31

and

P(H | E) =P(Rob has a cold | Rob was observed sneezing)

(0.75)(0.2)
= ---------------
(0.31)
= 0.48387

 Or Rob’s probability of having a cold given that he

sneezes is about 0.5.

23
 We can also determine what his probability of having
a cold would be if he was not sneezing:

P(E’ | H)P(H)
P(H | E’) = -------------------
P(E’)
(1-0.75) (0.2)
= -------------------
(1 - 0.31)
= 0.07246

 So knowledge that he sneezes increasing his

probability of having a cold by approximately 2.5,
while knowledge that does not sneeze decreases his
probability by a factor of almost 3.

24
 Propagation of Belief

Note that what we have just examined is very limited

since we have only considered when each piece of
evidence affects only one hypothesis.

 This must be generalized to deal with “m” hypotheses

H1, H2, ... Hm and “n” pieces of evidence E1, ..., En, the
situation normally encountered in real-world
problems. When these factors are included, Equation
(2) becomes

P(Ej1Ej2...Ejk | Hi) P(Hi)

(3) P(Hi | Ej1 Ej2 ...Ejk) = -----------------------------------
P(Ej1 Ej2 ... Ejk)

P(Ej1 | Hi)P(Ej2 | Hi) ... P(Ejk | Hi)P(Hi)

= -------------------------------------------------------
m

P(Ej1 | Hl)P(Ej2 | Hl) ... P(Ejk | Hl)P(Hl)

l=1

where {j1, ...,jk) {1, ..., n}

 This probability is called the posterior probability of

hypothesis Hi from observing evidence Ej1, Ej2, ..., Ejk.

25
 This equation is derived based on several
assumptions:

1. The hypotheses H1, ..., Hm, m  1, are mutually

exclusive.
2. Furthermore, the hypotheses H1, ..., Hm are
collectively exhaustive.
3. The pieces of evidence E1, ..., En, n  1, are
conditionally independent given any hypothesis
Hi, 1  i  m .

Conditional independent: The events E1, E2, ...,

En, are conditionally independent given an event
H if
P(Ej1  ...  Ejk | H) = P(Ej1 | H) ...P(Ejk | H)
for each subset {j1, ...,jk) {1, ..., n}.

 This last assumption often causes great difficulties for

probabilistic based methods.

For example, two symptoms, A and B, might each

independently indicate that some disease is 50 percent
likely. Together, however, it might be that these
symptoms reinforce (or contradict) each other. Care
must be taken to ensure that such a situation does not
exist before using the Bayesian approach.

26
 To illustrate how belief is propagated through a
system using Bayes’ rule, consider the values shown
in the Table below. These values represent
(hypothetically) three mutually exclusive and
exhaustive hypotheses

1. H1, the patient, Rob, has a cold;

2. H2, Rob has an allergy; and

3. H3, Rob has a sensitivity to light

with their prior probabilities, P(Hi)’s, and two

conditionally independent pieces of evidence

1. E1, Rob sneezes and

2. E2, Rob coughs,

which support these hypotheses to differing degrees.

i=1 i=2 i=3

(cold) (allergy) (light sensitive)

P(Hi) 0.6 0.3 0.1

P(E1 | Hi) 0.3 0.8 0.3
P(E2 | Hi) 0.6 0.9 0.0

27
 If we observe evidence E1 (e.g., the patient sneezes),
we can compute posterior probabilities for the
hypotheses using Equation (3) (where k = 1) to be:

(0.3)(0.6)
P(H1 | E1) = ------------------------------------------ = 0.4
(0.3)(0.6) + (0.8)(0.3) + (0.3)(0.1)

(0.8)(0.3)
P(H2 | E1) = ------------------------------------------ = 0.53
(0.3)(0.6) + (0.8)(0.3) + (0.3)(0.1)

(0.3)(0.1)
P(H3 | E1) = ------------------------------------------ = 0.06
(0.3)(0.6) + (0.8)(0.3) + (0.3)(0.1)

 Note that the belief in hypotheses H1 and H3 have

both decreased while the belief in hypothesis H2 has
increased after observing E1. If E2 (e.g., the patient
coughs) is now observed, new posterior probabilities
can be computed from Equation (3) (where k = 2):

P(H1 | E1  E2)
(0.3)(0.6)(0.6)
= ------------------------------------------------------------
(0.3)(0.6)(0.6) + (0.8)(0.9)(0.3) + (0.3)(0.0)(0.1)
= 0.33

28
P(H2 | E1  E2)
(0.8)(0.9)(0.3)
= ------------------------------------------------------------
(0.3)(0.6)(0.6) + (0.8)(0.9)(0.3) + (0.3)(0.0)(0.1)
= 0.67

P(H3 | E1  E2)
(0.3)(0.0)(0.1)
= ------------------------------------------------------------
(0.3)(0.6)(0.6) + (0.8)(0.9)(0.3) + (0.3)(0.0)(0.1)
= 0.0

 Hypothesis H3 (e.g., sensitivity to light) has now

ceased to be a viable hypothesis and H 2 (e.g., allergy)
is considered much more likely than H1 (e.g., cold)
even though H1 initially ranked higher.

29
 Advantages and disadvantages of
Bayesian methods

The Bayesian methods have a number of advantages that

indicates their suitability in uncertainty management.

 Most significant is their sound theoretical foundation

in probability theory. Thus, they are currently the
most mature of all of the uncertainty reasoning
methods.

While Bayesian methods are more developed than the

other uncertainty methods, they are not without faults.

1. They require a significant amount of probability data

to construct a knowledge base. Furthermore, human
experts are normally uncertain and uncomfortable
about the probabilities they are providing.

2. What are the relevant prior and conditional

probabilities based on? If they are statistically based,
the sample sizes must be sufficient so the
probabilities obtained are accurate. If human experts
have provided the values, are the values consistent
and comprehensive?

30
3. Often the type of relationship between the hypothesis
and evidence is important in determining how the
uncertainty will be managed. Reducing these
associations to simple numbers removes relevant
information that might be needed for successful
reasoning about the uncertainties. For example,
Bayesian-based medical diagnostic systems have
failed to gain acceptance because physicians distrust
systems that cannot provide explanations describing
how a conclusion was reached (a feature difficult to
provide in a Bayesian-based system).

4. The reduction of the associations to numbers also

eliminated using this knowledge within other tasks.
For example, the associations that would enable the
system to explain its reasoning to a user are lost, as is
the ability to browse through the hierarchy of
evidences to hypotheses.

31
 2: Certainty factors

 Certainty factor is another method of dealing with

uncertainty. This method was originally developed
for the MYCIN system.

 One of the difficulties with Bayesian method is that

there are too many probabilities required. Most of
them could be unknown.

 The problem gets very bad when there are many

pieces of evidence.

 Besides the problem of amassing all the conditional

probabilities for the Bayesian method, another major
problem that appeared with medical experts was the
relationship of belief and disbelief.

 At first sight, this may appear trivial since obviously

disbelief is simply the opposite of belief. In fact, the
theory of probability states that

P(H) + P(H’) = 1

and so

32
 P(H) = 1 - P(H’)
 For the case of a posterior hypothesis that relies on
evidence, E

(1) P(H | E) = 1 - P(H’ | E)

 However, when the MYCIN knowledge engineers

began interviewing medical experts, they found that
physicians were extremely reluctant to state their
knowledge in the form of equation (1).

 For example, consider a MYCIN rule such as the

following.

IF 1) The stain of the organism is gram positive, and

2) The morphology of the organism is coccus, and
3) The growth conformation of the organism is chains
THEN There is suggestive evidence (0.7) that the
identity of the organism is streptococcus

 This can be written in terms of posterior probability:

(2) P(H | E1 E2  E3) = 0.7

where the Ei correspond to the three patterns of the

antecedent.

33
 The MYCIN knowledge engineers found that while
an expert would agree to equation (2), they became
uneasy and refused to agree with the probability result

(3) P(H’ | E1 E2  E3) = 1 - 0.7 = 0.3

 This illustrates these numbers such as 0.7 and 0.3 are

likelihoods of belief, not probabilities.

 Let us have another example.

Suppose this is your last course required for a degree.

Assume your grade-point-average (GPA) has not
been too good and you need an ‘A’ in this course to
bring up your GPA. The following formula may
express your belief in the likelihood of graduation.

(4) P(graduating | ‘A’ in this course) = 0.70

Notice that this likelihood is not 100%. The reason

it’s not 100% is that a final audit of your course and
grades must be made by the school. There could be
problem due to a number of reasons that would still
prevent your graduation.

34
 Assuming that you agree with (4) (or perhaps your
own value for the likelihood) then by equation (1)

(5) P(not graduating | ‘A’ in this course) = 0.30

 From a probabilistic point of view, (5) is correct.

However, it seems intuitively wrong. It is just not
right that if you really work hard and get an ‘A’ in
this course, then there is a 30% chance that you won’t
graduate. (5) should make you uneasy.

 The fundamental problem is that while P(H | E)

implies a cause of effect relationship between E and
H, there may be no cause and effect relationship
between E and H’.

These problems with the theory of probability led the the

researchers in MYCIN to investigate other ways of
representing uncertainty.

 The method that they used with MYCIN was based

on certainty factors.

35
 Measures of belief and disbelief

In MYCIN, the certainty factor (CF) was originally

defined as the difference between belief and disbelief.

CF(H, E) = MB(H, E) - MD(H, E)

where

CF is the certainty factor in the hypothesis H

due to evidence E
MB is the measure of increased belief in H due to E
MD is the measure of increased disbelief in H due to E

 The certainty factor is a way of combining belief and

disbelief into a single number.

 Combining the measures of belief and disbelief into a

single number has some interesting uses.

 The certainty factor can be used to rank hypothesis in

order of importance.

For example, If a patient has certain symptoms

which suggest several possible diseases, then the

36
 disease with the highest CF would be the one that
is first investigated by ordering tests.

The measures of belief and disbelief were defined in

terms of probabilities by

= 1 if P(H) = 1
MB(H, E)
max[P(H | E), P(H)] - P(H)
= ---------------------------------- otherwise
1 - P(H)

= 1 if P(H) =1
MD(H,E)
min [P(H | E), P(H)] - P(H)
= ---------------------------------- otherwise
- P(H)

37
 According to these definitions, some characteristics
are shown in Table 5-1.

____________________________________
Characteristics Values
------------------------------------------------------
Ranges 0  MB  1
0  MD  1
-1  CF  1
-------------------------------------------------------
Certain True Hypothesis MB =1
P(H | E) = 1 MD =0
CF = 1
-------------------------------------------------------
Certain False Hypothesis MB =0
P(H’|E) =1 MD =1
CF = -1
-------------------------------------------------------
Lack of evidence MB = 0
P(H | E) = P(H) MD = 0
CF =0
-------------------------------------------------------

Some Characteristics of MB, MD and CF

38
 The certainty factor, CF, indicates the net belief in
hypothesis based on some evidence.

 A positive CF means the evidence supports the

hypothesis since MB > MD.

 A CF = 1 means that the evidence definitely proves

the hypothesis.

 A CF = 0 means one of two possibilities.

1. First, a CF = MB - MD = 0 could mean that both

MB and MD are 0.

2. The second possibility is that MB = MD and both

are nonzero. The result is that the belief is
canceled out by the disbelief.

 A negative CF means that the evidence favors the

negation of the hypothesis since MB < MD. Another
way of stating this is that there is more reason to
disbelief a hypothesis than to belief it.

For example, a CF = -70% means that the disbelief is

70% greater than the belief.

39
 A CF=70% means that the belief is 70% greater than
the disbelief.

 Certainty factors allow an expert to express a belief

without committing a value to the disbelief.

 The following equation is true.

CF(H, E) + CF(H’, E) =0

 The equation means that evidence supporting a

hypothesis reduces support to the negation of the
hypothesis by an equal amount so that the sum is
always 0.

 For the example of the student graduating if an ‘A’ is

given in the course

CF(H,E) = 0.70 CF(H’,E) = -0.70

which means
(6) I am 70 % certain that I will graduate if I get
an ‘A’ in this course.
(7) I am -70% certain that I will not graduate if I
get an ‘A’ in this course.

 0 means no evidence.

40
 So certainty values greater than 0 favor the hypothesis
 Certainty factors less than 0 favor the negation of the
hypothesis. Statements (6) and (7) are equivalent
using certainty factors
 The above CF values might be elicited by asking

How much do you believe that getting an ‘A”

will help you graduate?

if the evidence is to confirm the hypothesis, or

How much do you disbelief that getting ‘A’

will help you graduate?

An answer of 70% to each question will set CF(H, E)

= 0.7, and CF(H’,E) = -0.70.

41
 Calculation with Certainty Factors

Although the original definition of CF was

CF = MB - MD

there were difficulties with this definition

 because one piece of disconfirming evidence could

control the confirmation of many other pieces of
evidence.

For example, ten pieces of evidence might produce a

MB = 0.999 and one disconfirming piece with MD =
0.799 could then give

CF = 0.999 - 0.799 = 0.200

 The definition of CF was changed in MYCIN in 1977

to be

MB - MD
CF = ------------------------
1 - min(MB, MD)

42
 This softens the effects of a single piece of
disconfirming evidence on many confirming pieces of
evidence. Under this definition with MB=0.999,
MD=0.799

0.999-0.799 0.200
CF = --------------------------- = ------------- = 0.995
1- min(0.999, 0.799) 1 - 0.799

 The MYCIN method for combining evidence in the

antecedent of a rule are shown in Table 5-2.

-------------------------------------------------------------
Evidence, E Antecedent Certainty
-------------------------------------------------------------
E1 AND E2 min [CF(E1, e),CF(E2, e)]
E1 OR E2 max[CF(E1, e),CF(E2, e)]
NOT E -CF(E, e)
--------------------------------------------------------------
Table 5-2

 For example, given a logical expression for

combining evidence such as

E = (E1 AND E2 AND E3) or (E4 AND NOT E5)

the evidence E would be computed as

43
 E = max[min(E1, E2, E3), min(E4, -E5)]
for values
E1 = 0.9 E2 = 0.8 E3 = 0.3
E4 = -0.5 E5 = -0.4
the result is
E = max[min(0.9, 0.8, 0.3), min(-0.5, -(-0.4)]
= max[0.3, -0.5]
= 0.3

 The formula for the CF of a rule

If E THEN H
is given by

(8) CF(H,e) = CF(E,e) CF(H,E)

where
CF(E,e) is the certainty factor of the evidence E
making up the antecedent of the rule base on
uncertain evidence e.

CF(H,E) is the certainty factor of hypothesis

assuming that the evidence is with certainty, when
CF(E,e) = 1.
CF(H,e) is the certainty factor of the hypothesis
based on uncertain evidence e.

44
 Thus, if all the evidence in the antecedent is known
with certainty, the formula for the certainty factor of
the hypothesis is

CF(H,e) = CF(H,E)

since CF(E,e) = 1.

 See an example. Consider the CF for the

streptococcus rule discussed before,

IF 1) The stain of the organism is gram positive, and

2) The morphology of the organism is coccus, and
3) The growth confirmation of the organism is chains
THEN There is suggestive evidence (0.7) that the
identity of the organism is streptococcus

where the certainty factor of the hypothesis under

certain evidence is

CF(H, E) = CF (H, E1E2E3) = 0.7

and is also called the attenuation factor.

The attenuation factor is based on the assumption

that all the evidence--E1, E2 and E3--is known with
certainty. That is,

45
 CF(E1, e) = CF(E2, e) = CF(E3, e) = 1
 What happens when all the evidenced are not known
with certainty?

 In the case of MYCIN, the formula (8) must be used

to determine the resulting CF value since CF(H,
E1E2E3) = 0.7 is no longer valid for uncertain
evidence.

For example, assuming

CF(E1,e) = 0.5
CF(E2,e) = 0.6
CF(E3,e) = 0.3

then

CF(E,e) = CF(E1E2E3,e)
= min[CF(E1,e), CF(E2,e), CF(E3,e)]
= min[0.5, 0.6, 0.3]
= 0.3

The certainty factor of the conclusion is

CF(H, e) = CF(E,e) CF(H,E)
= 0.3 * 0.7
= 0.21

46
 What happen when another rule also concludes the
same hypothesis, but with a different certainty factor?

 The certainty factors of rules concluding the same

hypothesis is calculated from the combining function
for certainty factors defined as

(9) CFCOMBINE(CF1,CF2)

= CF1 + CF2 (1 - CF1) if both CF1 and CF2 > 0

CF1 + CF2
= ------------------------- if one of CF1 and CF2 < 0
1 - min(|CF1|,|CF2|)

= CF1 + CF2 (1 + CF1) if both CF1 and CF2 < 0

where CF1 is CF1(H, e) and CF2 is CF2(H, e).

 The formula for CFCOMBINE used depends on whether

the individual certainty factors are positive or
negative.

 The combining function for more than two certainty

factors is applied incrementally. That is, the CFCOMBINE
is calculated for two CF values, and then the
CFCOMBINE is combined using formula (9) with the
third CF values, and so forth.

47
 The following figure summarizes the calculations
with certainty factors for two rules based on uncertain
evidence and concluding the same hypothesis.

Hypothesis, H

Rule 1 Rule 2

CF1(H, e) = CF1(E, e)CF1(H,e) CF2(H, e) = CF2(E, e)CF2(H,e)

AND OR NOT AND OR NOT

(min) (max) (-) (min) (max) (-)

CF of two rules with the same hypothesis

based on uncertain evidence

48
 In our above example, if another rule concludes
strepococcus with certainty factor CF2 = 0.5, then the
combined certainty using the first formula of (9) is

CFCOMBINE(0.21, 0.5) = 0.21 + 0.5(1 - 0.21) = 0.605

 Suppose a third rule also has the same conclusion, but

with a CF3 = -0.4. Then the second formula of (9) is
used to give
0.605 - 0.4
CFCOMBINE(0.605, -0.4) = --------------------------
1 - min(|0.605|, |0.4|)

0.205
= --------- = 0.34
1 - 0.4
 The CFCOMBINE formula preserves the commutativity
of evidence. That is

CFCOMBINE(X,Y) = CFCOMBINE(Y,X)

and so the order in which evidence is received does

not affect the result.

49
 Advantages and disadvantages of
certainty factors
The CF formalism has been quite popular with expert
system developers since its creation because

1. It is a simple computational model that permits

experts to estimate their confidence in conclusion
being drawn.

2. It permits the expression of belief and disbelief in

each hypothesis, allowing the expression of the effect
of multiple sources of evidence.

3. It allows knowledge to be captured in a rule

representation while allowing the quantification of
uncertainty.

4. The gathering of the CF values is significantly easier

than the gathering of values for the other methods. No
statistical base is required - you merely have to ask
the expert for the values.

Many systems, including MYCIN, have utilized this

formalism and have displayed a high degree of
competence in their application areas. But is this

50
competence due to these systems’ ability to manipulate
and reason with uncertainty or is it due to other factors?
Some studies have shown that changing the certainty
factors or even turn off the CF reasoning portion of
MYCIN does not seems to affect the correct diagnoses
much.

 This revealed that the knowledge described within the

rule contributes much more to the final, derived
results than the CF values.

Other criticisms of this uncertainty reasoning method

include among others:

1. The CF lack theoretical foundation. Basically, the CF

were partly ad hoc. It is an approximation of
probability theory.

2. Non-independent evidence can be expressed and

combined only by “chunking” it together within the
same rule. When large quantities of non-independent
evidence must be expressed, this proves to be
unsatisfactory

3. the CF values could be the opposite of conditional

probabilities.

For example, if
51
 P(H1) = 0.8 P(H2) = 0.2
P(H1 | E) = 0.9 P(H2 | E) = 0.8
then CF(H1, E) = 0.5 and CF(H2, E) = 0.75

 Since one purpose of CF is to rank hypotheses in

terms of likely diagnosis, it is a contradiction for
a disease to have a higher conditional probability
P(H | E) and yet have a lower certainty factor,
CF(H, E).

52
 3: Dempster-Shafer Theory

Here we discuss another method for handling uncertainty.

It is called Dempster-Shafer theory. It is evolved during
the 1960s and 1970s through the efforts of Arthur
Dempster and one of his students, Glenn Shafer.

 This theory was designed as a mathematical theory of

evidence.

 The development of the theory has been motivated by

the observation that probability theory is not able to
distinguish between uncertainty and ignorance owing
to incomplete information.

53
 Frames of discernment
Given a set of possible elements, called environment,

 = {1, 2, ..., n}

that are mutually exclusive and exhaustive.

 The environment is the set of objects that are of

interest to us.

 For example,

 = {airline, bomber, fighter}

 = {red, green, blue, orange, yellow}

 One way of thinking about  is in terms of questions

and answers. Suppose

 = {airline, bomber, fighter}

and the questions is, “what are the military aircraft?”.

The answer is the subset of 

{2, 3} = {bomber, fighter}

54
 Each subset of  can be interpreted as a possible
answer to a question.
 Since the elements are mutually exclusive and the
environment is exhaustive, there can be only one
correct answer subset to a question.

 Of course, not all possible questions may be

meaningful.

 The subsets of the environment are all possible valid

answers in this universe of discourse.

 An environment is also called a frame of

discernment.

 The term discern means that it is possible to

distinguish the one correct answer from all the other
possible answers to a question.

 The power set of the environment (with 2 N subsets for

a set of size N) has as its elements all answers to the
possible questions of the frame of discernment.

55
 Mass Functions and Ignorance

In Bayesian theory, the posterior probability changes as

evidence is acquired. Likewise in Dempster-Shafer
theory, the belief in evidence may vary.

 It is customary in Dempster-Shafer theory to think

about the degree of belief in evidence as analogous to
the mass of a physical object.

That is, the mass of evidence supports a belief.

 The reason for the analogy with an object of mass is

to consider belief as a quantity that can move around,
be split up, and combined.

56
 A fundamental difference between Dempster-Shafer
theory and probability theory is the treatment of
ignorance.

 As discussed in Chapter 4, probability theory must

distribute an equal amount of probability even in
ignorance.

For example, if you have no prior knowledge, then

you must assume the probability P of each possibility
is

1
P = ----
N

where N is the number of possibilities.

E.g., The formula P(H) + P(H’) = 1 must be enforced

 The Dempster-Shafer theory does not force belief to

be assigned to ignorance or refutation of a hypothesis.

The mass is assigned only to those subsets of the

environment to which you wish to assign belief.

57
 Any belief that is not assigned to a specific subset is
considered no belief or nonbelief and just associated
with environment .

 Belief that refutes a hypothesis is disbelief, which is

not nonbelief.

For example, we are trying to identify whether an

aircraft is hostile. Suppose there is the evidence of 0.7
indicating a belief that the target aircraft is hostile,
where hostile aircraft are only considered to be
bombers and fighters. Thus, the mass assignment is to
the subset {bomber, fighter), and

m1({bomber, fighter}) = 0.7

The rest of the belief is left with the environment, ,

as nonbelief.

m1() = 1- 0.7 = 0.3.

58
 The Dempster-Shafer theory has a major difference
with probability theory which would assume that

P(hostile) = 0.7
P(non-hostile) = 1 - 0.7 = 0.3

 0.3 in Dempster-Shafer theory is held as nonbelief in

the environment by m(). This means neither belief
nor disbelief in the evidence to a degree of 0.3.

A mass has considerably more freedom than probabilities

as show in the table below.

Dempster-Shafer theory Probability theory

-------------------------------------------------------------------
m() does not have to be 1 Pi = 1
i
If X  Y, it is not necessary P(X)  P(Y)
that m(X)  m(Y)

No required relationship P(X) + P(X’) = 1

between m(X) and m(X’)

59
We now state things more formally.

 Let  be a frame of discernment (environment). A

mass assignment function assigns a number m(x) to
each x   such that:
(1) 1  m(x)  0
(2) m() = 0
(3)  m(x) = 1
x

 Let  be a frame of discernment (environment). and

let m be a mass assignment function on . A set x 
 is called a focal element in m if m(x) > 0. The core
of m, denoted by k(m), is the set of all focal elements
in m.

Let us consider a medical example. Suppose

 = {heart-attack, pericarditis, pulmonary-embolism,

aortic-dissection}.

 Note that each mass assignment on  assigns mass

numbers to 24 = 16 sets. If for a specific patient there
is no evidence pointing at a certain diagnosis in
particular, the mass of 1 is assigned to .

1 if x = 

60
 m0(x) =
0 otherwise
 Each proper subset of  gets assigned the number 0.
The core of m0 is equal to {}

 Now suppose that some evidence has become

available that points to the composite hypothesis
heart-attack or pericarditis with some certainty.

Then the subset {heart-attack, pericarditis} will be

assigned a mass, e.g., 0.4. Due to lack of further
information, the remaining certainty 0.6 is assigned to
.
0.6 if x = 
m1(x) = 0.4 if x = {heart-attack, pericarditis }
0 otherwise

 Now suppose we have obtained some evidence

against the hypothesis that our patient is suffering
from pericarditis. This information can be considered
as support for hypothesis that the patient is not
suffering from pericarditis. This is equivalent to the
composite hypothesis heart-attack or pulmonary-
embolism or aortic-dissection. We therefore assign a
mass, for example 0.7, to the set {heart-attack,
pulmonary-embolism, aortic-dissection}

0.3 if x = 

61
m2(x) = 0.7 if x = {heart-attack, pulmonary-embolism,
aortic-dissection }
0 otherwise

62
 Combining evidence
Dempster-Shafer theory provides a function for
computing from two pieces of evidence and their
associated masses describing the combined influence of
these pieces of evidence.

 This function is known as Dempster’s rule of

combination.

 Let m1 and m2 be mass assignments on , the frame

of discernment. The combined mass is computed
using the formula (special form of Dempster’s rule
of Combination)

m1  m2(Z) =  m (X) m (Y)

1 2
X Y= Z

For instance, using our hostile aircraft example, based

on two pieces of evidence, we obtain
m2({B}) = 0.9 m2() = 0.1
-------------------------------------------------------------
m1({B, F}) = 0.7 {B} 0.63 {B, F} 0.07
m1() = 0.3 {B} 0.27  0.03

E.g., the entry T11 is calculated as this

63
 T11({B}) = m1({B, F}) m2({B}) = (0.7)(0.9)=0.63
 Once the individual mass products have been
calculated as shown above, then according to
Dempster’s Rule the products over the common set of
intersections are added

m3({B}) = m1  m2({B})
= 0.63 + 0.27 = 0.90 Bomber

m3({B, F}) = m1  m2({B, F })

= 0.07 Bomber or fighter

m3() = m1  m2() = 0.03 nonbelief

 The m3({B}) represents the belief that the target is a

bomber and only a bomber.

 m3({B, F}) and m3() imply more information as

their sets include a bomber, it is plausible that their
sums may contribute to a belief in the bomber.

 So 0.07 + 0.03 = 0.1 may be added to the belief of 0.9

in the bomber set to yield the maximum belief (= 1)
that it could be a bomber. This is called the plausible
belief.

64
 We have two belief values for the bomber, 0.9 and 1.
This pair represents a range of belief. It is called an
evidential interval.

 The lower bound is called the support (Spt) or Bel,

and the upper bound is called plausibility (PIs).

For instance, 0.9 is the lower bound in the above

example, and 1 is the upper bound.

 The support is the minimum belief based on the

evidence, while the plausibility is the maximum belief
we are willing to give.

 Thus, 0  Bel  PIs  1. Table below shows some

common evidential interval.

Evidential Interval Meaning

------------------------------------------------------------------------
[1, 1] Completely true
[0, 0] Completely false
[0, 1] Completely ignorant
[Bel, 1] where 0 < Bel < 1 here Tends to support
[0, PIs] where 0 < PIs < 1 here Tends to refute
[Bel, PIs] where 0 < Bel PIs < 1 here Tends to both support and refute

65
 The Bel (belief function, or support) is defined to be
the total belief of a set and all its subsets.

Bel(X) =  m(Y)
Y X
For example,

Bel1({B, F}) = m1({B, F}) + m1({B}) + m1({F})

= 0.7 + 0 + 0 = 0.7

 Belief function is different from the mass, which is

the belief in the evidence assigned to a single set.
 Since belief functions are defined in terms of masses,
the combination of two belief functions also can be
expressed in terms of masses of a set and all its
subsets.
 For example:
Bel1  Bel2({B}) = m1m2({B}) + m1 m2()
= 0.90 + 0 = 0.9.

Bel1  Bel2({B, F})

= m1m2({B, F}) + m1m2({B}) + m1 m2({F})
= 0.07 + 0.9 + 0 = 0.97

Bel1  Bel2()
= m1 m2() + m1m2({B, F}) + m1m2({B})
= 0.03 + 0.07 + 0.9 = 1

66
 Bel() = 1 in all cases since the sum of masses must
always equal 1.

 The evidential interval of a set S, EI(S), may be

defined in terms of the belief.

EI(S) = [Bel(S), 1 - Bel(S’)]

 For instance, if S = {B}, then S’ = {A, F} and

Bel({A, F})
= m1m2({A, F}) + m1m2({A}) + m1 m2({F})
=0+0+0=0

since these are not focal elements and the mass is 0

for nonfocal elements.

 Thus, EI({B}) = [0.90, 1 - 0] = [0.9, 1]

Also, since Bel({A}) = 0, and

Bel({B, F}) = Bel1  Bel2({B, F}) = 0.97.

Then
EI({B, F}) = [0.97, 1 - 0] = [0.97, 1]
EI({A}) = [0, 0.03]

67
 The plausibility is defined as the degree to which the
evidence fails to refute X

PIs(X) = 1 - Bel(X’)

Thus, EI(X) = [Bel(X), PIs(X)]

 The evidential interval [total belief, plausibility] can

be expressed,

[evidence for support, evidence for support + ignorance]

 The dubiety (Dbt) or doubt represents the degree to

which X is disbelieved or refuted.

 The ignorance (Igr) is the degree to which the mass

supports X and X’.

These are defined as follows:

Dbt(X) = Bel(X’) = 1 - PIs(X)

Igr(X) = PIs(X) - Bel(X)

68
 The Normalization of Belief
 Let us see an example. Suppose a third evidence now
reports conflicting evidence of an airliner

m3({A}) = 0.95, m3() = 0.05

 The table shows how the cross products are

calculated.

m1m2({B}) m1m2({B, F}) m1m2()

0.90 0.07 0.03
----------------------------------------------------------------------------------
m3({A}) = 0.95  0.855  0.0665 {A} 0.0285
m3() = 0.05 {B} 0.045 {B, F} 0.0035  0.0015

 Thus

m1m2m3({A}) = 0.0285
m1m2m3({B}) = 0.045
m1m2m3({B, F}) = 0.0035
m1m2m3() = 0.0015
m1m2m3() = 0

 Note that for this example, the sum of all the masses
is less than 1

69
  m1m2m3(X)
= 0.0285 + 0.045 + 0.0035 + 0.0015 = 0.0785
 However a sum of 1 is required because the combined
evidence m1m2m3, is a valid mass and the sum
over all focal elements must be 1.

This is a problem.
 The solution to this problem is a normalization of the
focal elements by dividing each focal element by
1-
where  is defined for any sets X and Y as
=  m1(X)m2(Y)
X Y = 

For our problem,

 = 0.855 + 0.0665 = 0.9215

 Dividing each m1m2m3 focal element by 1 - 

m1m2m3({A}) = 0.363
m1m2m3({B}) = 0.573
m1m2m3({B, F}) = 0.045
m1m2m3() = 0.019

 The one evidence of {A} has considerably reduced

the belief in {B}.

70
 The total normalized belief in {B} is now

Bel({B}) = m1m2m3({B}) = 0.573

Bel({B}’) = Bel({A, F})

= m1m2m3({A, F}) +
m1m2m3({A}) +
m1m2m3({F})
= 0 + 0.363 + 0 = 0.363

and so the evidential interval is now

EI({B}) = [Bel({B}), 1 - Bel({B}’)]

= [0.573, 1 - 0.363]
= [0.573, 0.637]

 The general form of Dempster’s Rule of

Combination is,
 m1(X) m2(Y)
X Y = Z
m1m2(Z) = --------------------------
1-

 Note that  = 1 is undefined.

71
Difficulty with the Dempster-Shafer
theory

One difficulty with the Dempster-Shafer theory occurs

with normalization and may lead to results which are
contrary to our expectation.

 The problem is that it ignores the belief that the

object being considered does not exist.

For example, the beliefs by two doctors, A and B, in a

patient’s illness are as follows

mA(meningitis) = 0.99, mA(brain tumor) = 0.01

mB(concussion) = 0.99, mB(brain tumor) = 0.01

Both doctors think there is a very low chance, 0.01, of

a brain tumor but greatly disagree on the major
problem.

The Dempster rule of combination gives a combined

belief of 1 in the brain tumor. The result is very
unexpected.

72