Unit 3

Uncertainty
Bayesian Theory and Fuzzy Sets
 Introduction
With knowledge representation, we might write A→B, which means if A is true then B is true, but
consider a situation where we are not sure about whether A is true or not then we cannot
express this statement, this situation is called uncertainty

Uncertainty is the reported value that lies within the range of values within which the true
value is asserted to lie in.

In AI, there are numerous sources of uncertainty, including variation in specific data values and
the sample of data collected from the domain.

Missing information, unreliable information, conflicting information, noisy information and

confusing information are the main sources of uncertainty

There are different methods to manage uncertainty in AI and expert system: non-monotonic
logic, probability reasoning and fuzzy logic, Bayesian theory
Contd…..
 Agents may need to handle uncertainty, whether due to partial observability, no determinism or a
combination of both
 Agent may not know for certain what state it is in or where it will end up after a sequence of actions
 4 types of uncertainty in decision making process as Data, Action, Prediction and Judgment
 A purely logical approach has two main problems as RISK or Wastage of resources
 eg. if you want to reach at airport 2:00 pm and distance of airport from resident is approximate 25 km.
How much buffer time will you keep to reach at airport without delay or earlier?
 Tool of Degree of Belief = Probability Theory
 Ontological Commitments of logical and probability theory are same that world is composed of facts that
do or do not hold in any particular case
 Epistemological Commitments are different that logical agent believes each sentence to be true, false or
not, whereas probabilistic agent may have a numerical degree of belief between 0 and 1.
Causes of Uncertainty

 Laziness
 Theoretical Ignorance
 Practical Ignorance
 Information occurred from unreliable sources
 Experimental Errors
 Climate Change
 Equipment fault
How to handle Uncertainty

1. Implicit Methods
 Ignore uncertainty as much as possible
 Build procedures that are robust to uncertainty
 This is a approach used in the planning methods
2. Explicit Methods
 Build a model of the world that describes the uncertainty ( sensors, model, states, dynamics)
 Reason about the effect of actions given the model
 Probabilistic Reasoning – something is true or false
 Fuzzy Logic – handles degree of TRUTH, not uncertainty
 Default or non monotonic logic – make assumptions unless contradicted by evidence.
 Rule based approaches
 Fuzzy Logic

 fuzzy logic was first used with 1965 by Lotfi Zadeh a professor of UC Berkeley in California
 It was designed to allow the computer to determine the distinctions among data which is neither true nor
false
 Represent uncertainty with degree
 Represent the belongingness of member of crisp set (0,1) to fuzzy set
 It is a method of reasoning that resembles the human reasoning
 The approach of FL initiates the way of decision making in human that involves all intermediate possibilities
between digital values {0,1}
 It is an alternative more institutive approach to reasoning with imprecise knowledge.
 It does not claim to have the mathematical precision of probability theory, but rather to capture common
sense notions.
Contd….

Fig Real time examples of Fuzzy Logic

Classify Students with height

Who can drive good among your friends?
Patient visits doctor
Applications

Product Company Fuzzy Logic

Use fuzzy logic to controls brakes in hazardous cases depend on car
Anti-lock brakes Nissan
speed, acceleration, wheel speed etc.
Fuzzy logic is used to control the fuel injection and ignition based on
Auto transmission NOK/Nissan
throttle setting, cooling water temperature, RPM, etc.
Use to select gear based on engine load, driving style, and road
Auto engine Honda, Nissan
conditions.
Using for adjusting drum voltage based on picture density, humidity,
Copy machine Canon
and temperature.
Use for adjusting the cleaning cycle, rinse and wash strategies based
Dishwasher Matsushita depend upon the number of dishes and the amount of food served
on the dishes.
Fitness management Omron Fuzzy rules implied by them to check the fitness of their employees.
Kiln control Nippon Steel Mixes cement
Contd….

• Fuzzy set is a set of ordered pair

• The membership function is a function which represents the graph of fuzzy sets, and
allows users to quantify the linguistic term. It is a graph which is used for mapping
each element of x to the value between 0 and 1.
• A crisp set is fuzzy set, but a fuzzy set is not necessarily crisp set
Fuzzy Set Representation
Types of Membership Function

• Singleton membership function assigns membership value 1 to

particular value of x, and assigns value 0 to rest of all. It is
represented by impulse function as shown.
• The triangle which fuzzifies the input can be defined by three
parameters a, b and c, where a and c defines the base and b
defines the height of the triangle.

Singleton Membership Function

Triangular Membership Function

Contd….

• Trapezoidal membership function is defined by four

parameters: a, b, c and d. Span b to c represents the highest
membership value that element can take. And if x is
between (a, b) or (c, d), then it will have membership value
between 0 and 1.
• Find membership function value for x=3.5
Trapezoidal Membership Function
Contd….

• A Gaussian MF is specified by two parameters {m, σ} where

m = mean / center of the Gaussian curve
σ = spread of the curve
 Fuzzy Terminologies

• Support( A ) = { x | μA(x) > 0, x ∈ X }

• Core( A ) = { x | μA(x) = 1, x ∈ X }
• Boundary( A ) = { x | 0 < μA(x) < 1 , x ∈ X }
• Crossover( A ) = { x | μA(x) = 0.5 }
• Bandwidth( A ) = |x1 – x2|
Where, μA(x1) = μA(x2) = 0.5
• Alpha cut Aα = { x | μA(x) ≥ α }
• Strong Alpha cut Aα = { x | μA(x) > α }
Contd….

• Support: { (x2, 0.2), (x3, 0.5), (x4, 1), (x5, 1), (x6, 1),
(x7, 0.5), (x8, 0.2) }
• Core: { (x4, 1), (x5, 1), (x6, 1) }
• Crossover Points: { (x3, 0.5), (x7, 0.5) }
• Alpha Cut0.2: { (x2, 0.2), (x3, 0.5), (x4, 1), (x5, 1), (x6,
1), (x7, 0.5), (x8, 0.2) }
• Strong Alpha Cut0.2+: { (x3, 0.5), (x4, 1), (x5, 1), (x6, 1),
(x7, 0.5) }
• Boundary: { (x2, 0.2), (x3, 0.5), (x7, 0.5), (x8, 0.2) }
• Bandwidth : x7 – x3
• Normality = True
Fuzzy Set Operations

1. Union Operation : μA∪B(x) = max (μA(x), μB(x))

2. Intersection Operation: μA∩B(x) = min (μA(x), μB(x))
3. Complement Operation: μĀ(x) = 1-μA(x)
4. Difference Operation: μA-B(x) = min (μA(x), 1-μB(x))
Example:
A = {( X1, 0.6 ), (X2, 0.2), (X3, 1), (X4, 0.4)}
B = {( X1, 0.1), (X2, 0.8), (X3, 0), (X4, 0.9)}  B= {(X1, 0.9), (X2, 0.2), (X3, 1), (X4, 0.1)}

AUB = {(X1, 0.6), (X2, 0.8), (X3, 1), (X4, 0.9)}

A∩B = {(X1, 0.1), (X2, 0.2), (X3, 0), (X4, 0.4)}
Ā= {(X1, 0.4), (X2, 0.8), (X3, 0), (X4, 0.6)}
A-B= {(X1, 0.6), (X2, 0.2), (X3, 1), (X4, 0.3)}
Fuzzy Set Properties

1. Commutative Property : A ∪ B = B ∪ A and A ∩ B = B ∩ A

2. Associative Property: A ∪ (B ∪ C) = (A ∪ B) ∪ C and A ∩ (B ∩ C) = (A ∩ B) ∩ C
3. Idempotency Property: A ∪ A = A and A ∩ A = A
4. Absorption Property: A ∪ (A ∩ B) = A and A ∩ (A ∪ B) = A
5. Distributive Property : A∪ (B ∩ C) = (A ∪ B)∩ (A ∪ C) and A∩ (B ∪ C) = (A∩B) ∪ (A∩C)
6. Identity Property: A ∪ φ =A and A ∩ X = A and A ∩ φ = φ and A ∪ X = X
7. Transitive Property: If A ⊆ B ⊆ C, then A ⊆ C
8. Ivolution property:

9. De Morgan's Law:
Defuzzification Methods

1. Lambda Cut Method

2. Maxima Methods
• Height method
• First of maxima (FoM)
• Last of maxima (LoM)
• Mean of maxima (MoM)
3. Weighted average method
4. Centroid methods
• Center of gravity method (CoG)
• Center of sum method (CoS)
Lambda Cut Method

• This Lambda-cut set Aλ is also called alpha-cut set.

• Lambda-cut method is applicable to derive crisp value of a fuzzy set or fuzzy relation.
• In this method a fuzzy set A is transformed into a crisp set Aλ for a given value of λ (0 ≤ λ ≤ 1)
as, Aλ = { x | μA(x) ≥ λ }
Example – 1: Lambda-cut for Fuzzy Set
A = { (x1, 1.0), (x2, 0.5) , (x3, 0.3) , (x4, 0.4) }
For λ = 1: A1= { x1 }
For λ = 0.5: A0.5= { x1, x2 }
For λ = 0.4: A1= { x1, x2, x4 }
Maxima Methods

• The set of methods under maxima methods are:

• Height method
• First of maxima (FoM)
• Last of maxima (LoM)
• Mean of maxima (MoM)
1. Height method:
• This method is based on Max-membership principle, as μC(x*) ≥ μC(x), ∀x ∈ X
Contd….

2. First of Maxima (FoM) method

• Determine the smallest value of the domain with maximized membership degree
FoM = First of Maxima: x∗ = min{ x | μC(x) = h(C) }
3. Last of Maxima (LoM) method:
• Determine the largest value of the domain with maximized membership degree
LoM = Last of Maxima: x∗ = max{ x | μC(x) = h(C) }
Contd….

4. Middle of Maxima (MoM) method:

• In order to find middle of maxima, we have to find the “middle” of elements with maximum membership
value

Where, M ={ xi | μC(xi) = h(C) }, Or M is the set of points having highest membership value
Contd….

5. Weighted average method

• This method is also alternatively called ”Sugeno defuzzification” method.
• Formed by weighting each functions in the output by its respective maximum membership
value
• This method is applicable to fuzzy sets with symmetrical output membership functions
Contd….

Find defuzzified value for given aggregated fuzzy output set using
weighted average method from given figure

The center of each symmetric fuzzy output function is multiplied by

the height of the function.

x* = ((0.7 × 3) + (1.0 × 7)) / (0.7 + 1.0)

x∗ = 5.941
Example
Contd….

6. Center of Gravity (CoG) method

• The basic principle in CoG method is to find the point x∗ where a vertical line would slice the
aggregate into two equal masses.
• This method returns a precise value depending on the fuzzy set‘s center of gravity.
• The overall area of the membership function distribution used to describe the combined
control action is divided into a number of sub-areas
• Area and center of gravity, or centroid, of each sub regions are calculated. Then the sum of all
these sub-areas is used to determine the defuzzified value for a discrete fuzzy set
• Let Ai and xi denotes the area and center of gravity of ith sub-region.

• Ai=∫ μC(x) dx and n is the number of geometrical components

Contd….

• To compute the crisp value corresponding to above output fuzzy sets

we shall create aggregate output by placing them on same axis
Equation of line ab: (y – y1) / (x – x1) = (y2 – y1) / (x2 – x1)
For line ab, (x1, y1) = (0, 0) and (x2, y2) = (1, 0.5)
(y – 0) / (x – 0) = (0.5 – 0) / (1 – 0)
y / x = 0.5 / 1
y = 0.5x
Line ranges from [0, 1] on X-axis
Contd….

7. Center of Sum (CoS) Method

• In this method, area of overlapping region is considered multiple times, where as Center of Gravity
(CoG) method count it once.
where
Example

• Find crisp value corresponding to following fuzzy output sets using various defuzzification methods.

• Center of Gravity Method = 2.5

• Center of Sums Method = 2.3
• Weighted Area Method = 2.25
• First of Maxima = 1.5
• Last of Maxima = 3
• Middle of Maxima = NA
• Height Method = NA
Fuzzy Inference System (FIS)

• The fundamental task of any FIS is to apply the if-then rules on fuzzy input and produce the
corresponding fuzzy output.
• The whole process is based on the computer paradigm including fuzzy set theory, if-then rules and the
fuzzy reasoning process.
• Fuzzy inference (reasoning) is the actual process of mapping from a given input to an output using fuzzy
logic
• FIS have been successfully applied in fields such as automatic control, data classification, decision
analysis, expert systems , controller designing and many more
Fuzzy Inference Method (FIM)

• Linguistic Fuzzy: Mamdani fuzzy inference (Mamdani and Assilian (1975))

• If I1 is A AND I2 is B then O is C
• Mamdani approach follows linguistic fuzzy modeling and characterized by its high
interpretability and low accuracy.
• Precise Fuzzy Modeling: Sugeno or Takagi–Sugeno–Kang or TS fuzzy inference (Sugeno (1985))
• If I1 is A AND I2 is B then O is f(I1, I2) = a1I1 + b1I2 + c1
• Takagi and Sugeno’s approach follows precise fuzzy modeling and obtains high accuracy but at the
cost of low interpretability.
• The main difference between the two methods lies in the consequent of fuzzy rules.
Fuzzy Rule Based System
• IF premise (antecedent), THEN conclusion (consequent)
Aggregation of Fuzzy Rules

Conjunctive System of Rules:

• In this rule system, we must satisfy all the rule
• The rules are connected by ‘and’ connectives
• In this case, the aggregated output, y, is found by the fuzzy intersection of all the individual rule
consequents, yi where i=1, 2, 3, …, r
• y = y1 and y2 and y3 … yr
• y = y1 ∩ y2 ∩ y3 ∩ … ∩ yr
• μy(y) = min[μy1(y), μy2(y), …, μyL(y)]
Disjunctive System of Rules:
• In this rule system, we should satisfy at least one rule
• The rules are connected by the ‘or’ connectives
• In this case, the aggregated output, y, is found by the fuzzy union of all the individual rule consequents,
yi where i=1, 2, 3, …, r
• y = y1 or y2 or y3 … yr
• y = y1 ∪ y2 ∪ y3 ∪ … ∪ yr
• μy(y) = max[μy1(y), μy2(y), …, μyL(y)]
Fuzzy Expert System

• Fuzzy expert systems are different than the conventional expert systems which relies on the symbolic
logic. Where as, fuzzy expert system is inclined towards numeric computing.
• Fuzzy expert system perform reasoning from data using membership functions and fuzzy rules

• Knowledge Base (Long-Term Memory)

• Fuzzy Production Rules (If-Then)
• Data Base (Short-Term Memory)
• Fact from user or Parameters
• Inference Engine – Chatboat Application
• Data Driven (Forward Chaining, Modus Ponens)
• Goal Driven (Backward Chaining, Modus Tollens)
• Meta-Knowledge Base – Quick Search
• Explanatory Interface – Help and Guide
• Knowledge Acquisition Module – Verification
• Q&A, Interviews, R&D, Literature
Example

• Consider the design of a fuzzy controller for a steam turbine. Assume the input of the fuzzy controller as
temperature and pressure. The output will be the throttle setting of a steam turbine. Use 3 descriptors
for input and 5 descriptors for output variables. Derive the set of rules for controller action and get the
defuzzified values.
• Assume that the current temperature is 30% and pressure is 40% and we have to determine the throttle
position of the turbine for this particular condition
Solution
Step 1: Identification of variables
• Inputs: Temperature and pressure
• Output: Throttle setting of steam turbine
Contd….

Step 2: Fuzzy subset configuration

• Assign a linguistic descriptor for each fuzzy subset
• Temperature: Cool, Nominal, Warm
• Pressure: Low, Ok, Strong
• Throttle Setting:
• N2: Large Negative
• N1: Small Negative
• Z: Zero
• P1: Small Positive
• P2: Large Positive
Contd….

Step 3: Obtain Membership Function

• Define membership functions for descriptors (Temperature)
• Define membership functions for descriptors (Pressure)
• Triangle rule as (y2 – y1) / (x2 – x1) = (y – y1) / (x – x1)
• For fuzzy set COOL: (x1, y1) = (0,1) (x2,y2) = (20,0)
[0, 20] ⇒ (0 – 1) / (20 – 0) = (y – 1) / (x – 0)
μCool = (20 – xT) / 20
• For fuzzy set NOMINAL: (x1, y1) = (0,0) (x2,y2) = (20,1)
[0, 20] ⇒ (1 – 0) / (20 – 0) = (y – 0) / (x – 0)
⇒ μ =xT / 20
[20, 40] ⇒ (0 – 1) / (40 – 20) = (y – 1) / (x – 20)
⇒ μ = (40 – xT) / 20
• For fuzzy set WARM: (x1, y1) = (20,0) (x2,y2) = (40,1)
[20, 40] ⇒ (1 – 0) / (40 – 20) = (y – 0) / (x – 20)
μwarm = (xT – 20) / 20
Contd….

• For fuzzy set LOW: (x1,y1) =(0,1) (x2,y2)= (50,0)

[0, 50] ⇒ (0 – 1) / (50 – 0) = (y – 1) / (x – 0)
μlow = (50 – xP) / 50
• For fuzzy set OK: (x1,y1) = (0,0) (x2,y2) = (50,1)
[0, 50] ⇒ (1 – 0) / (50 – 0) = (y – 0) / (x – 0)
⇒ μ = xP / 50
[50, 100] ⇒ (0 – 1) / (100 – 50) = (y – 1) / (x – 500)
⇒ μ = (100 – xP) / 50
• For fuzzy set STRONG: (x1,y1) = (50,0) (x2,y2)= (100,1)
[50, 100] ⇒ (1 – 0) / (100 – 50) = (y – 0) / (x – 50)
μStrong = (xP – 50) / 50
Contd….

• Define membership functions for descriptors (Rotation)

Contd….

Step 4: Fuzzy rule base configuration

• As we assumed, this controller has 3 fuzzy sub sets for temperature and 3 fuzzy subsets for pressure. So
rule base will contain 3 x 3 i.e. 9 rules.
Contd….

Step 5: Fuzzification
Contd….

Step 7: Identification of output

• Rule 1: If temperature is cool and pressure is low, then throttle setting is P2
Contd….

Rule 2: If temperature is cool and pressure is ok, then throttle setting is Z

Contd….

Rule 3: If temperature is nominal and pressure is low, then throttle setting is P2

Contd….

Rule 4: If temperature is nominal and pressure is ok, then throttle setting is Z

Contd….

Step 8: Defuzzification (Average Weighted Method)

• Firing strength of each rule is highlighted in different colors in above figures. To compute the
corresponding crisp value, we shall aggregate all output functions by placing them on same axis.
Probability Theory

• It is a another approach to handle uncertainty at the time of knowledge representation

• It will rain today
• Behavior of someone for some situations
• A match between two teams or two players are some examples where we can assume that it will
happen but not sure about it, so here we use probabilistic reasoning.
• In probabilistic reasoning, there are two ways to solve problems with uncertain knowledge:
• Bayes' rule
• Bayesian Statistics
• Probability can be defined as a chance that an uncertain event will occur.
• It is the numerical measure of the likelihood that an event will occur. The value of probability always
remains between 0 and 1 that represent ideal uncertainties.
0 ≤ P(A) ≤ 1, where P(A) is the probability of an event A.
P(A) = 0, indicates total uncertainty in an event A.
P(A) =1, indicates total certainty in an event A.
Contd….

• Event: Each possible outcome of a variable is called an

event.
• Sample space: The collection of all possible events is
called sample space.
• Random variables: Random variables are used to
represent the events and objects in the real world.
• Prior probability: The prior probability of an event is
probability computed before observing new information.
• Posterior Probability: The probability that is calculated
after all evidence or information has taken into account. It
is a combination of prior probability and new information.
Conditional Probability

• Conditional probability is a probability of occurring an event when another event has already
happened.
• The probability of A under the conditions of B

Where P(A⋀B)= Joint probability of a and B

P(B)= Marginal probability of B
• If the probability of A is given and we need to find the probability of B

Example :
In a class, there are 70% of the students who like English and 40% of the students who likes English and
Mathematics. What is the percent of students who like English also like mathematics?
• A is an event that a student likes Mathematics
• B is an event that a student likes English.
Hence, 57% are the students who like English also like Mathematics.
Bayes Theorem

• In probability theory, it relates the conditional probability and marginal probabilities of two random
events.
• Bayes theorem can be derived using product rule and conditional probability of event A with known
event B
• As from product rule we can write

• Probability of event B with known event A

• Equating right hand side of both the equations, we will get

• The above equation is called as Bayes rule or Bayes theorem.

• P(A|B) is known as posterior
• P(B|A) is called the likelihood
• P(A) is called the prior probability and P(B) is called marginal probability
Example 1

• Suppose 15 men out of 300 men and 25 women out of 1000 are good orators. An orator is chosen at
random. Find the probability that a male person is selected. Assume that there are equal numbers of
men and women?
Let there be 1000 men and 1000 women.
Let E1 and E2 be the events of choosing a man and a woman respectively.
P(E1) = 1000/2000 = 1/2 , and P(E2) = 1000/2000 = ½

Let E be the event of choosing an orator.

P(E|E1) = 50/1000 = 1/20, and P(E|E2) = 25/1000 = 1/40

Probability of selecting a male person ,given that the person selected is a good orator
P(E1|E) = P(E|E1) * P(E1)/ P(E|E1) * P(E1) + P(E|E2) * P(E2)
= (1/2 * 1/20) /{(1/2 * 1/20) + (1/2 * 1/40)}
= 2/3
Hence the required probability is 2/3.
Example 2

• A man is known to speak to throw die 1 out of 4 times. He throws a die and reports that it is a six. Find
the probability that is actually a six?
E1 = event of getting a six,
E2 = event of not getting a six and
E = event that the man reports that it is a six.
P(E1) = 1/6, and P(E2) = (1 – 1/6) = 5/6
P(E|E1) = probability that the man speaks the truth
= 3/4
P(E|E2) = probability that the man does not speak the truth
= (1 – 3/4) = 1/4
Probability of getting a six ,given that the man reports it to be six
P(E1|E) = P(E|E1) * P(E1)/P(E|E1) * P(E1) + P(E|E2) * P(E2)
= (3/4* 1/6)/ (3/4*1/6)+ (1/4 * 5/6)
= 3/8
Bayesian Belief Network

• A Bayesian network is a probabilistic graphical model which represents a set of variables and
their conditional dependencies using a directed acyclic graph.
• It is also called a Bayes network, belief network, decision network, or Bayesian model.
• It can also be used in various tasks including optimized search engine, diagnosis of different
diseases, filtering spam emails, prediction and decision making under uncertainty.
• Bayesian Network can be used for building models from data and experts opinions and it
consists of two parts:
1. Directed Acyclic Graph
2. Table of conditional probabilities
Contd….

• A Bayesian network graph is made up of nodes and Arcs (directed links),

• Each node corresponds to the random variables and variable can be continuous or discrete.
• Arc or directed arrows represent the causal relationship or conditional probabilities between random
variables.
• These arcs represent that one node directly influence the other node and if there is no directed link
means that nodes are independent with each other.
• The Bayesian network has mainly two components:
1. Causal Component
2. Actual numbers
• Bayesian network is based on Joint probability distribution and conditional probability
• We can define the conditional dependencies as: A is conditionally dependent upon B, like P(A|B)
• We can also define the conditional independencies as: A is conditionally independent of C: P(A|B, C)
• We can also write the joint probability of B and C were given A as: P(A|B,C) = P(A|B,C) * P(B,C)
Example

• Harry installed a new burglar alarm at his home to detect burglary. The alarm reliably
responds at detecting a burglary but also responds for minor earthquakes. Harry has two
neighbors David and Sophia, who have taken a responsibility to inform Harry at work when
they hear the alarm. David always calls Harry when he hears the alarm, but sometimes he got
confused with the phone ringing and calls at that time too. On the other hand, Sophia likes to
listen to high music, so sometimes she misses to hear the alarm. Here we would like to
compute the probability of Burglary Alarm.
Problem:
• Calculate the probability that alarm has sounded, but there is neither a burglary nor an
earthquake occurred and David and Sophia both called the Harry.
Contd….

• List of all events occurring in this network

• Burglary (B)
• Earthquake(E)
• Alarm(A)
• David Calls(D)
• Sophia calls(S)
• We can write the events of problem statement in the form of probability: P[D, S, A, B, E]
• We can rewrite the above probability statement using joint probability distribution:
P[D, S, A, B, E]= P[D | S, A, B, E]. P[S, A, B, E]
= P[D | S, A, B, E]. P[S | A, B, E]. P[A, B, E]
= P[D | A]. P [ S| A, B, E]. P[ A, B, E]
= P[D | A]. P[ S | A]. P[A| B, E]. P[B, E]
= P[D | A ]. P[S | A]. P[A| B, E]. P[B |E]. P[E]
 Contd….

Calculate the probability that alarm has sounded,

but there is neither a burglary nor an earthquake
occurred and David and Sophia both called the
Harry.

P(S, D, A, ¬B, ¬E)

= P (S|A) *P (D|A)*P (A|¬B ^ ¬E) *P (¬B) *P (¬E)
= 0.75* 0.91* 0.001* 0.998*0.999
= 0.00068045

Example
Contd….

What is probability when David calls?

P(D)
= P(D|A) P(A) + P(D| ¬A) P(¬A)
= P(D|A) {P(A|B,E)*P(B,E) + P(A|B, ¬E)*P(B, ¬E) + P(A| ¬ B,
E)*P(¬ B, E) + P(A| ¬ B, ¬E)*P(¬ B, ¬E)} + P(D| ¬A)
{P(¬ A|B,E)*P(B,E) + P(¬ A|B, ¬E)*P(B, ¬E) + P(¬ A| ¬ B, E)*P(¬
B, E) + P(¬ A| ¬ B, ¬E)*P(¬ B, ¬E)}
= 0.91 + { 0.94*0.002*0.001+0.95*0.002*0.999+
0.69*0.998*0.001+0.999*0.998*0.999} + 0.09 +
{0.06*0.002*0.001*0.04*0.002*0.999+0.69*0.998*0.001
+0.999*0.998*0.999}
= 0.91+ 0.9986 + 0.09 + 1.065
= 3.0636
Contd….