Chapter 4-3 - Matlab FLC Toolbox FLC Applications
Chapter 4-3 - Matlab FLC Toolbox FLC Applications
Chapter 4:
Fuzzy Logic
Part 3 – Matlab FLC Toolbox & FLC Applications
www.utm.my
• Washing machine, rice cooker, refrigerator etc.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE
3
Introduction
● A Fuzzy Inference System (FIS) is a way of mapping an
input space to an output space using fuzzy logic
● FIS uses a collection of fuzzy membership functions and
rules, instead of Boolean logic, to reason about data.
● The rules in FIS (sometimes may be called as fuzzy expert
system) are fuzzy production rules of the form:
− if p then q, where p and q are fuzzy statements.
● For example, in a fuzzy rule
− if x is low and y is high then z is medium.
www.utm.my
− Here x is low; y is high; z is medium are fuzzy statements; x and
y are input variables; z is an output variable, low, high, and
medium are fuzzy sets.
www.utm.my
− Fuzzy Inferencing (apply implication method)
− Aggregation of all outputs
− Defuzzification
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 6
Fuzzification
● In the process of fuzzification, membership functions
defined on input variables are applied to their actual
values so that the degree of truth for each rule premise
can be determined.
● Fuzzy statements in the antecedent are resolved to a
degree of membership between 0 and 1.
− If there is only one part to the antecedent, then this is the
degree of support for the rule.
− If there are multiple parts to the antecedent, apply fuzzy logic
operators and resolve the antecedent to a single number
www.utm.my
between 0 and 1.
● Antecedent may be joined by OR; AND operators.
− For OR -- max
− For AND -- min
MEEM 1713 – ARTIFICIAL INTELLIGENCE 7
Fuzzy Inferencing
● In the process of inference
− Truth value for the premise of each rule is computed and
applied to the conclusion part of each rule.
− This results in one fuzzy set to be assigned to each output
variable for each rule.
● The use of degree of support for the entire rule is to
shape the output fuzzy set.
● The consequent of a fuzzy rule assigns an entire fuzzy set
to the output.
● If the antecedent is only partially true, (i.e., is assigned a
www.utm.my
value less than 1), then the output fuzzy set is truncated
according to the implication method.
www.utm.my
− min: truncates the consequent's membership function
− prod: scales it.
www.utm.my
− the maximum : point-wise maximum over all of the fuzzy sets
− the sum : (point-wise sum over all of the fuzzy
− the probabilistic sum.
www.utm.my
● Some other methods for defuzzification are:
− bisector, middle of maximum mom (the average of the
maximum value of the output set), largest of maximum
(lom), and smallest of maximum (som), etc.
MEEM 1713 – ARTIFICIAL INTELLIGENCE 11
4.2
Matlab Simulation Using
Fuzzy Logic Control
www.utm.my
Toolbox
MEEM 1713 – ARTIFICIAL INTELLIGENCE
12
Introduction
● MATLAB fuzzy logic toolbox provides facility for the development
of fuzzy-logic systems using
− graphical user interface (GUI) tools
− command line functionality
● There are five primary GUI tools
− Fuzzy Inference System (FIS) Editor
− Membership Function Editor
− Rule Editor
www.utm.my
− Rule Viewer
− Surface Viewer
Dynamically
Linked!
• changes in one
www.utm.my
GUI will
automatically
affect the other
GUIs.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 15
Fuzzy Inference System (FIS) Editor
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 16
Membership Function Editor
www.utm.my
function
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 18
Rule Editor
Rules –
automatically
updated
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 19
Rule Editor
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 20
Rule Viewer
www.utm.my
variable is used in
rules; shows output
of fuzzy system
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 22
Surface Viewer
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 23
Surface Viewer
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 24
3.2.1
An Example of Matlab
Simulation
www.utm.my
Tipping problem
www.utm.my
bill paid.
● Input variables
− Service : represented by poor, good,
excellent
− Food : represented by bad, delicious
● Output Variable:
− Tip : represented by cheap, average,
generous
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 28
Bad taste
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 29
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 30
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 31
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 32
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 33
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 34
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 35
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 36
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 37
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 38
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 39
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 40
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 41
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 42
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 43
Aggregate Conclusions
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 44
Defuzzification
16.7
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 45
All Steps Together looks like
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 46
4.3
Example of FLC Projects
www.utm.my
Fuzzy Logic Real-time Control Approaches
Project #1: Fuzzy control of a water bath
Project #2: Fuzzy control of traffic lights
Interface Card
(Adclone, NS, etc.)
Sensor
Personal
Computer
Process
www.utm.my
Actuator High-level
Languages
(C++, Pascal,
Visual Basic, Matlab etc.)
Fuzzy control
Personal development
Computer system or LLL
(Download)
www.utm.my
Sensor Micro-
A/D
Process Controller
(DSP, Fuzzy Chip,
D/A
MC68HC11, Arduino, Raspberry Pi, etc.)
Actuator
Raspberry Pi
BeagleBone Black
MSP 430
www.utm.my
Arduino Nano
Arduino Mega Arduino Uno
MEEM 1713 – ARTIFICIAL INTELLIGENCE 50
Arduino IDE
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 51
Arduino FIST
www.utm.my
+ Arduino Fuzzy Library
MEEM 1713 – ARTIFICIAL INTELLIGENCE 52
Project #1:
Water-Bath Temperature Control System
Objectives and Applications
www.utm.my
Nestle, F&N, Drinho, etc.
Control Signal
Sensor
Stirrer
www.utm.my
AC ~
Coil
(Heater)
Disturbance
Reference + Output
Fuzzy Logic Water Bath
(Desired Temp.) Temp.
Controller
-
www.utm.my
Sensor
Math-model of system:
www.utm.my
be measured from the error between
the output and the reference signals • (However, these characteristics are
not present in the above math-model
except for controller limits)
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 57
Configuration of the fuzzy controller
Error
e
Change in
FLC Control Signal
∆u
Derivative
of Error
∆e
www.utm.my
– Rate of change of error, ∆e(k) = e(k) - e(k-1)
• One output variable:
– Change in the control signal, ∆u(k)
For simplicity the 3 fuzzy variables can be broken into 3 fuzzy subsets
and the membership functions can be overlapped as follows:
e, ∆e, and ∆u µe N Z P
Linguistic Term Label
Negative N e
Zero Z µ∆e N Z P
Positive P
∆e
www.utm.my
µ∆u
N Z P
The universe for the 3 variables can be
set accordingly through observation.
∆u
Ge
Error
e Change in
www.utm.my
G∆u Control Signal
FLC
Derivative ∆u
of Error
∆e G∆e
www.utm.my
N
e Derivative
∆e ∆u of Error, ∆e Z z
• A matrix of the rule base can be set up as shown.
P
• The 1st row and the 1st column are the antecedents
and the boxes in the matrix are the consequents.
Error, e
N Z P
www.utm.my
Derivative
of Error, ∆e
Z
www.utm.my
same consequent resulted. This
occurs when several rules are fired. ∆u
• A defuzzification technique will be
Determined output ∆u(k)
used to give a crisp output value.
µc
• Defuzzification is required to produce the actual
signal that the plant can use. Z
• Thus, the fuzzy output value need to be
defuzzified.
• The output of the fuzzy controller is usually the
change in the control signal.
• The actual control signal to the plant is thus:
Max defuzzification
www.utm.my
technique is used, the output crisp value is:
µc(z*) ≥ µc(z) for all z ∈Z
• For centroid defuzzification, the value is given as
follows:
z* =
∑ µ C ( z ).z Centroid defuzzification
∑ µ C ( z)
MEEM 1713 – ARTIFICIAL INTELLIGENCE 64
Example 3.2
www.utm.my
output value.
µe N Z P N Z P
µe
0.75
0.8
e e
µ∆e N Z P
µ∆e N Z P
0.3 0.4
∆e ∆e
µ∆u N Z P
µ∆u Z P
N
0.3
0.4
∆u
∆u at µP =0.3 ∆u at µP =0.4 ∆u
www.utm.my
Rule1=(P,Z;P) and Rule 4=(Z,P;P), this means that (e, ∆e; ∆u).
• Suppose Rule 1: µP=0.75, µZ =0.3, thus, min (µP, µZ) --> µP at 0.3
• Since the consequent P is fired twice having 2 membership values, 0.3 and 0.4
thus, we need to use the max compositional operator to obtain only 1 P value of
the consequent.
• Similarly for Rules 2 and 3, the same computation will be done to obtain only 1 N
consequent (see next slide).
www.utm.my
Rule2=(P,N;Z) and Rule 3=(N,P;Z)
• Suppose Rule 2: µP=0.5, µN =0.6, thus, min (µP, µN) --> µZ at 0.5
• Suppose Rule 3: µN =1.0, µP=0.4, thus, min (µN, µP) --> µZ at 0.4
N Z P µe
µe N Z P
1.0
0.5
e e
µ∆e N Z P
µ∆e N Z P
0.6
0.4
∆e ∆e
µ∆u N Z P
µ∆u Z P
N
0.5
0.4
∆u ∆u
∆u at µZ =0.5 ∆u at µZ =0.4
www.utm.my
and 0.4 thus, we need to use the max compositional operator to obtain
only 1 N value of the consequent.
• Thus, max (µZ=0.5, µZ=0.4) will give µZ=0.5.
• Suppose we use the centroid defuzzification strategy. The next slide
will show how this is done to get the crisp output.
∆u
• Graphically this can be shown as follows. ∆u at µP =0.4
• The first consequent P was obtained at µP
µ∆u N Z P
=0.4 and the second consequent Z at µZ
0.5
=0.5.
∆u
• The centroid defuzzification algorithm will
∆u at µZ =0.5
calculate the crisp value of ∆u from the
following equation:
µ∆u Z P
www.utm.my
N
• Study the output of the water bath fuzzy control system at the
particular sampling interval.
• Note down the sampling interval, the setpoint (r), the output
(y), error (e), and del_error (∆e).
• By studying the rule-base matrix, write down the rules that are
fired at this interval in triple form, eg. (P, Z; N), etc..
www.utm.my
the appropriate alpha cut-set (firing angle) based on the input
values of e and ∆e.
www.utm.my
how ∆u is calculated.
µe N Z P
1.0
0.5
0.5
www.utm.my
1.0
N Z P
0.5
-5 -2.5 0 +2.5 +5 ∆u
www.utm.my
– a fuzzy logic controller
– conventional preset timer
Simulation Objectives
• Understanding fuzzy logic application for traffic lights control
• Understanding the components of a fuzzy logic controller
• Able to set up rules for controlling traffic conditions
• Able to compare and understand the advantages of fuzzy logic
controller over fixed-time controller of traffic lights
Control Objectives
• To control traffic flow optimally at an isolated junction
www.utm.my
• To minimise waiting time
• To reduce fuel costs
• To reduce waste of man-hours
www.utm.my
IF traffic from the north of the city is HEAVY
AND the traffic from the west is LESS
THEN allow movement of traffic from the north LONGER.
Control signal
Sensor Readings
Fuzzy Logic Relays/ Traffic
Controller Switches Lights
Traffic Flow
Traffic Condition
(Arrival) Lights
www.utm.my
R
FLC Switches Y
G
(Queue)
Traffic Condition
Sensors
State
Machine
Traffic
Counter
Light
- Queue -
Arrival
FLC Interface
www.utm.my
Block diagram of the fuzzy
traffic lights controller
www.utm.my
N
• Flow density of cars can be controlled for each
direction. W E
www.utm.my
LinguisticTerm Label
Longer L
Medium M
Short S
Zero Z
µArrival ARRIVAL
• For simplicity, triangular AN F MY TMY
membership functions are used
for each variable.
• In this case, the cardinals for
No. of Cars
µQueue QUEUE
the universes of discourse are S M L
VS
integers.
• The membership functions are
overlapped by about 25% to No. of Cars
www.utm.my
fuzzy subset to another. Z S M L
www.utm.my
• Fill up the rule base matrix as shown: Queue
• In this application the centroid defuzzification is used. M
www.utm.my
is completed
www.utm.my
• If not, you need to reconfigure your fuzzy controller
• Try simulating other conditions
www.utm.my
Applications of FLCS
www.utm.my
• Fuzzy Vacuum Cleaner
• Fuzzy Air Conditioner
• Fuzzy Blood Pressure Meter
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 86
Fuzzy logic washing machine
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 87
Example of a fuzzy
logic washing machine
Samsung SW-5AI(S)
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 88
Example of the Samsung’s
SW-5AI(S) Fuzzy logic
washing machine
www.utm.my
fabric, etc.
www.utm.my
• The wash sensor measures the
dirtiness (turbidity) of the water
through an optical sensor which is
installed near the drain valve.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE
• The wash sensor consists of an infrared light-emitting diode
(LED) and a photo-transistor.
www.utm.my
Wash sensor output
change over time.
www.utm.my
of wash water to decrease as shown in (a).
• The rate of decrease of the transmittance depends on the quality
of the dirt:
– Fast
MEEM 1713 – ARTIFICIAL for muddy dirt
INTELLIGENCE 93
• This is because muddy dirt is removed easily by the mechanical
force of the water flow produced by the rotation of the pulsator,
while oily dirt is not adequately removed until the detergent effect
takes place.
• When most of the dirt in the clothes has been removed, the
transmittance of the wash water approaches a state of saturation.
• The transmittance at saturation becomes lower when the clothes
are dirtier, and the transmittance becomes higher when the
www.utm.my
clothes are less dirty.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 95
• Using fuzzy inference, linguistic rules can be used to solve the washing problem
and the nonlinear property of the relation is approximated by an interpolation
function of the fuzzy inference
• In order to provide the inference 2 inputs are suitable:
– saturation time, Ts
– light transmittance, Vs
• and 1 output
– Washing time, Wt
• Saturation time is chosen because it is related to the quality of the dirt and light
transmittance is chosen because it is related to the amount of dirt and example of
the membership functions are given as follows:
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 96
• The washing machine can sense the following types of dirt:
– Muddy dirt (faster to be washed away)
– Oily dirt (need detergent and more time to be washed away)
• When most of dirt has been washed away the washing machine
approaches a state of saturation:
– Lower transmittance (heavy dirt)
– Higher transmittance (light dirt)
Fuzzy Vs
www.utm.my
rule base Low Middle High
Short T1 T2 T3
Ts
Long T4 T5 T6
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 98
Advantages of the fuzzy logic
washing machine:
• It would be very difficult to design a
rule base system without using fuzzy
logic concepts.
• Thus, with fuzzy logic it reduces
amount of required memory.
• Rules are acquired from skilled
launderers (experts).
• Nonlinear relationship between
degree of dirtiness and wash time can
be overcome by the nonlinear fuzzy
logic controller.
• Excessive or inadequate washing can
www.utm.my
be avoided.
• Many fuzzy logic washing machine
consists of one-touch button system
for the fuzzy wash.
MEEM 1713 – ARTIFICIAL INTELLIGENCE 99
Example #2: The
Fuzzy Rice
Cooker
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 100
General Overview
www.utm.my
and most importantly minus the hassle of stove
rice cooker.
www.utm.my
(deduced from the temperature rise and the power
consumption).
www.utm.my
next generation will use sensors as well as even
more general kinds of nonlinear information
processing.
MEEM 1713 – ARTIFICIAL INTELLIGENCE 103
Fuzzy Rice Cookers in the Market
www.utm.my
• Panasonic National Neuro-Fuzzy
Rice Cooker (Model SRMK10 …)
www.utm.my
Rice Cooker (Model NS-MYC- 18,
NS-JCC-18 …)
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 106
The diagram shows the basic components of a
rice cooker.
The main component is the rice container and is
heated directly by a heating coil.
The heat sensor, which reads the temperature
of the rice container, sends the reading as an
input to the fuzzy controller.
The fuzzy controller then control the heating coil
to obtain the desired heating of rice.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 107
Input/Output Variables
www.utm.my
Rate of Heating
(Change in the control signal)
www.utm.my
• The rate of heating is controlled by sending the
correct control signal to the heating coil.
0.8
0.6 LOW
MEDIUM
0.4 HIGH
www.utm.my
0.2
Amount of Rice
in Container
0.8
0.6 LOW
MEDIUM
0.4 HIGH
0.2
0
Temperature in
Container
Rate of Heating (Change in the control signal) (Output)
LOW MEDIUM HIGH
1
www.utm.my
0.8
0.6 LOW
MEDIUM
0.4 HIGH
0.2
Rate of
0
MEEM 1713 – ARTIFICIAL INTELLIGENCE Heating 111
Design of Fuzzy Control Rules
www.utm.my
THEN rate of heating is MEDIUM.
Amount of Rice
L M H
Temperature
of L M H H
Rice
www.utm.my
Container
M M M M
H L L M
MEEM 1713 – ARTIFICIAL INTELLIGENCE 113
When is the Rice Cooked?
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 114
Fuzzy vs. Traditional Rice Cooker
A fuzzy rice cooker is so much faster than a traditional
rice cooker. It can reduce cooking time to
approximately 20 minutes.
www.utm.my
possibilities which can not be achieved by traditional
rice cookers, such as the cooking of porridge and sushi
rice.
www.utm.my
fluffy rice.
Fuzzy controller also makes continuous keep
warm feature possible.
MEEM 1713 – ARTIFICIAL INTELLIGENCE 116
Disadvantages of Fuzzy Rice Cooker
www.utm.my
• The price of a fuzzy rice cooker is higher then the
conventional rice cookers.
• This new trend of fuzzy rice cooker design which will eventually take
place in the market and replace the conventional models.
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 118
Example #3:
A FUZZY AIR-CONDITIONER
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 119
Introduction to the Fuzzy Air-
Conditioner System
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 120
Introduction to the Fuzzy Air-
Conditioner System
www.utm.my
Air
Fuzzy Air-cond ROOM
2 Inputs 3 Outputs
www.utm.my
Heating Valve Humidifying Valve
www.utm.my
temperature and humidity.
Error
Fuzzy Controller
Output Air from
Cooling Valve
the Fuzzy Air-
Defuzzification
Fuzzification
Air Supply +
Rule Heating Valve Conditioner
- Base Humidifying Valve
Fan
temperature
Sensors
www.utm.my
humidity
HUMIDITY
low
medium
high
The fuzzy system outputs the optimal air circulation level by adjusting the
cooling valve, heating valve and humidifying valve in the air conditioner. The
www.utm.my
combined results are sent to the fan to be propagated to the environment.The
amount of the valves openings depends on these output variables:
zero
low
medium
high
MEEM 1713 – ARTIFICIAL INTELLIGENCE 125
Membership Functions
TEMPERATURE
ùt
cold cool warm hot
Area weather
condition
ùh HUMIDITY
low med high
www.utm.my
Area weather
condition
MEEM 1713 – ARTIFICIAL INTELLIGENCE 126
Rule Base System
www.utm.my
following is appropriate: (Note: Cooling valve is abbreviated with
CV, heating valve with HV and humidifying valve with UV )
IF temperature is cold AND humidity is med THEN CV is zero AND HV is high AND UV is med
IF temperature is cool AND humidity is med THEN CV is low AND HV is med AND UV is med
IF temperature is warm AND humidity is med THEN CV is med AND HV is low AND UV is med
IF temperature is hot AND humidity is med THEN CV is high AND HV is zero AND UV is med
IF temperature is cold AND humidity is low THEN CV is zero AND HV is high AND UV is high
www.utm.my
IF temperature is cool AND humidity is low THEN CV is low AND HV is med AND UV is high
IF temperature is warm AND humidity is low THEN CV is med AND HV is low AND UV is high
IF temperature is hot AND humidity is low THEN CV is high AND HV is zero AND UV is high
temperature temperature
cold cool warm hot cold cool warm hot
low high med low zero low low low low low
humidity
www.utm.my
medium high med low zero medium med med med med
high high med low zero high high high high high
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 130
RULES
www.utm.my
If temperature is LOW then open humidifying valve
SLIGHTLY
Act as predictor of humidity & also designed to prevent
overshoot in the output humidity curve
MEEM 1713 – ARTIFICIAL INTELLIGENCE 131
INTERFERENCE
www.utm.my
simplest method is called the MAX-MIN
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 133
DEFUZZIFICATION
www.utm.my
be set to HIGH
www.utm.my
Improves control performances
Simplifies implementation
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE 136
Importance of Maintaining Normal Blood Pressure
• Blood pressure can vary according to a variety of factors including age, sex, and
physical condition.
www.utm.my
• It is lower during sleep and higher when working.
www.utm.my
– Immediately after eating
– Smoking tobacco, drinking coffee
• Blood pressure will be lower than usual when
– After drinking alcohol
– After taking a bath
MEEM 1713 – ARTIFICIAL INTELLIGENCE 138
Fuzzy Logic measurement in the Blood Pressure meter
www.utm.my
• Thus making using conventional methods difficult.
• National employs fuzzy logic technology which double checks the
strength and shape of the pulse wave and then determine the blood
pressure.
MEEM 1713 – ARTIFICIAL INTELLIGENCE 139
Fuzzy logic inference engine
Pulse wave
Pressure
Pressure Time
www.utm.my
Fuzzy Inference
www.utm.my
• Error in measurement is detected
www.utm.my
MEEM 1713 – ARTIFICIAL INTELLIGENCE
142