Fundamental dan Metode

Pengembangan Sistem Pakar

Aries Maesya
Information Systems Applications
Applications of Expert Systems

PUFF:
Medical system
for diagnosis of respiratory
conditions

PROSPECTOR:
Used by geologists to
identify sites for drilling or
mining
Applications of Expert Systems
MYCIN:
Medical system for diagnosing blood
disorders. First used in 1979

DESIGN ADVISOR:
Gives advice to designers of
processor chips
Applications of Expert Systems

DENDRAL: Used to identify the

structure of chemical compounds.
First used in 1965

LITHIAN: Gives advice to

archaeologists examining
stone tools
 Contoh Aplikasi ES
HelloYellow(310-YELO) : voice-driven Yellow Pages searching
application
DENDRAL (1960): Sistem pakar yang digunakan untuk
mendeteksi bahan kimia
Mycin (1970) : Medical ES, diagnosed infection blood disease
Microsoft Troubleshooter : solves problem by working with
user to diagnose symptons
PROSPECTOR. Sistem pakar geologi yang digunakan untuk
mendeteksi mineral
XCON/R1. Sistem pakar yang digunakan untuk
mengkonfigurasi sistem komputer DEC VAX.

6
 Applications of Expert Systems and Artificial Intelligence

Credit granting
Information management and retrieval
AI and expert systems embedded in products
Plant layout
Hospitals and medical facilities
Help desks and assistance
Employee performance evaluation
Loan analysis
Virus detection
Repair and maintenance
Shipping
Marketing
Warehouse optimization
 Application Decision Support Systems in e-Cities

Banking. Stakeholders (suppliers, contrctors,

Intelligent Transport Systems. managers, etc.).
E-government. Organisation management.
Public sector. Negotiation.
Hospitals. Airlines applications.
Crime analysis. Business.
Tourism. Wood industry.
Transport. Risk management.
Electricity technology. E-Learning.
Stocks Housing, etc
Loans.
Application of Expert Systems in e-Cities

intelligent transport systems, legal advice,

knowledge management, financial consultancy,
e-learning, insurance,
banking, trade,
financial services, travel/tourism,
management services, employment,
auctioning, housing,
medical advice, construction,
health care, real estate market, etc.
 Decision Support Systems
A decision support system (DSS) is an information system
application that provides its users with decision-oriented
information whenever a decision-making situation arises.
When applied to executive managers, these systems are
sometimes called executive information systems (EIS).
A data warehouse is a read-only, informational database that is
populated with detailed, summary, and exception data and
information generated by other transaction and management
information systems. The data warehouse can then be accessed by
end-users and managers with DSS tools that generate a virtually
limitless variety of information in support of unstructured decisions.
 Expert Systems
An expert system is a programmed decision-making
information system that captures and reproduces
the knowledge and expertise of an expert problem
solver or decision maker and then simulates the
thinking or actions of that expert.

Expert systems are implemented with artificial

intelligence technology that captures, stores, and
provides access to the reasoning of the experts.
 Topik
Sistem Pakar (Expert System) dan Artificial
Intelligence
Struktur Sistem Pakar
Proses Pengembangan Sistem Pakar
Karakteristis Sistem Pakar
Kelebihan dan Kekurangan Sistem Pakar
Aplikasi dan Perangkat Lunak Sistem Pakar

12
AI vs Expert System

Vision
robotics
Natural
language
Artificial
Speech Intelligence

Artificial understanding
neural expert
network systems

Giarratano Ch 1 figure 1-1

13
 Artificial Intelligence
The exciting new effort to make computers think
machines with minds, in the full and literal sense.
(Haugeland 1985)
The study of mental faculties through the use of
computational models. (Charniak & McDermott 1985)
AI is the part of computer science concerned with
designing intelligent computer systems, that is,
systems that exhibit the characteristics we associate
with intelligence in human behaviour
understanding language, learning, reasoning, solving
problems and so on. (Barr & Feigenbaum, Jackson chapter 2)

14
 Sistem Pakar
Sistem pakar adalah suatu sistem komputer yang
berbasis pengetahuan (knowledge-based) terpadu
sehingga memiliki kemampuan untuk memecahkan
berbagai masalah dalam bidang tertentu secara
cerdas dan efektif, sebagaimana layaknya seorang
pakar.
Istilah sistem pakar seringkali juga disebut dengan
Knowledge-Based System (KBS) atau Knowledge-
Based Expert System.

15
What Human Do When Solving Problem?

16
 Sistem Pakar

Facts
Knowledge Base

Expertise
Inference Engine

17
18
 The Knowledge Hierarchy
knowledge on knowledge
(e.g how/when to apply)

knowledge-
based understanding of a domain,
systems meta- can be applied to solve
knowledge problems

knowledge lower volume, higher value,

with context and
management
information databases,
information associated meanings

transaction large volume, low

systems
systems data value, usually no
meaning/ context
noise may contain
irrelevant items
which obscure data
19
 Data vs Information vs Knowledge

Data is just bits (represents raw numbers or

assertions)
Information = Data + context and relevance (data
with semantics)
Knowledge is Information with decision-making and
action directed utility and purpose (relationship
among concept relevant to particular area)

20
21
22
Struktur Sistem Pakar

23
 Struktur Sistem Pakar #1
Knowledge Base
Inference Engine
Working Memory
Agenda
Explanation Facility
Knowledge Acquisition Facility
User Interface

24
 Struktur Sistem Pakar #2
Knowledge-based: bagian ini mengandung kaidah kepakaran
berupa aturan (rules) dan prosedur.
Inference Engine : adalah suatu mekanisme kontrol untuk
pengambilan kesimpulan berdasarkan fakta dan knowledge-
based.
Working memory: bagian ini mengandung kumpulan fakta
yang akan digunakan oleh knowledge-based (rule)
Agenda : adalah kumpulan rule yang dihasilkan oleh inference
engine dan sesuai (matching) dengan fakta yang tersedia

25
 Struktur Sistem Pakar #3
Explanation Facility: adalah fasilitas yang digunakan
untuk menjelaskan cara sistem menarik kesimpulan
(reasoning) kepada user.
Knowledge Acquisition Facility: adalah fasilitas yang
digunakan untuk memasukkan fakta/data kedalam
sistem.
User Interface: adalah suatu mekanisme dimana
antara user dengan sistem saling berkomunikasi.

26
Knowledge Engineering Process
Knowledge Sources of knowledge
validation (experts, others)
(test cases)
Knowledge
Acquisition
Encoding
Knowledge Knowledge
base Representation

Explanation
justification

Inferencing

27
Expert Systems Development

Determining requirements

Identifying experts

Domain
Construct expert system components The area of knowledge
addressed by the
expert system.
Implementing results

Maintaining and reviewing system

 Participants in Expert Systems Development and
Use

Domain expert
The individual or group whose expertise and knowledge is
captured for use in an expert system
Knowledge user
The individual or group who uses and benefits from the
expert system
Knowledge engineer
Someone trained or experienced in the design,
development, implementation, and maintenance of an
expert system
Schematic
 Expert
system

Knowledge engineer
Domain expert Knowledge user
 Evolution of Expert Systems Software
Expert system shell
Collection of software packages & tools to design, develop,
implement, and maintain expert systems

high
Expert system
Ease of use

shells
Special and 4th
generation
Traditional
languages
programming
languages
low
Before 1980 1980s 1990s
 Expert Systems Development Alternatives

high
Develop
from
scratch
Develop
Development from
costs shell
Use
existing
package
low

low high
Time to develop expert system
 Kelebihan Sistem Pakar #1
Sistem pakar dikembangkan karena adanya keterbatasan manusia (pakar)
dalam membuat keputusan. Berikut keterbatasan manusia:
Kepakaran manusia (human expertise) sangat jarang
Manusia akan mengalami kelelahan secara fisik dan mental bila
melakukan pekerjaan berat
Manusia memiliki keterbatas dalam mengingat
Manusia kadangkala menjadi tidak konsisten dalam pengambilan
keputusan
Manusia memiliki keterbatas dalam berfikir (working memory)
Manusia tidak dapat melakukan mengolah data yang besar dengan cepat
Pemikiran manusia kadang bias
Manusia bisa berbohong, bersembunyi atau meninggal

33
 Kelebihan Sistem Pakar
Economical. Dengan pengembangan sistem pakar, maka biaya yang harus
dikeluarkan bisa lebih ekonomis dibandingkan dengan biaya seorang
pakar.
Availability. Dengan sistem pakar, maka permasalah dapat diselesaikan
kapan saja, tanpa tergantung kepada keberadaan seorang pakar.
Respon time. Sistem pakar sering kali memiliki waktu respon yang lebih
cepat dibanding dengan manusia.
Reliability. Kepakaran sistem pakar dapat dikembang lebih luas lagi. Selain
itu juga sistem pakar tidak memiliki perasasaan/emosi sehingga bisa lebih
objektif dalam memecahkan masalah
Explanation. Sistem pakar memiliki fasilitas untuk menjelaskan bagaimana
pengambilan keputusan (reasoning) dilakukan.
Intellectual property. Sistem pakar dilengkapi kemampuan intelektual.

34
 Kekurangan Sistem Pakar
Limited knowledge. Sistem pakar memiliki keterbatasan pengetahuan.
Pengetahuan sistem pakar hanya dibatasi oleh pengetahuan yang
dimasukkan kedalam sistem. Sistem pakar tidak memahami keterkaitan
antara konsep dan keterhubungannya. Sistem pakar tidak memiliki
common-sense knowledge.
Mechanical Reasoning. Sistem pakar dibangun dengan ketentuan yang
sudah ditetapkan, sehingga pada sistem pakar tidak dapat menentukan
metode yang paling tepat untuk menyelesaikan masalah. Sistem pakar
mungkin saja menyelesaikan masalah yang mudah dengan waktu
komputasi yang sangat tinggi.
Lack of trust. Kesimpulan yang diberikan oleh sistem pakar tidak dapat
dikritik

35
 Expert System Application Area #1
Control: control systems adaptively govern the behaviour of a given system
to meet specifications(e.g., manufacturing process, treatment of a patient)
Prediction: inferring likely consequences of a given situation (e.g.,
predicting the expected damage to a crop from an invading insect).
Diagnosis: infer system malfunctions or faults from observable information
( finding the disease of a patient from her symptoms.)
Design: configures objects under a set of problem constraints(e.g., design
of electronic circuits)
Planning: form actions to achieve a given (a robot's accomplishment of a
given work function).

36
 Expert System Application Area #2

Monitoring: compare observable information on the behavior

of a system with system states that are considered important
to its operation (e.g., interpretation of signals from sensors).
Debugging and repair: proposing and implementing remedies
for malfunctions.
Instruction: guides the education of students in a given topic.
Interpretation: produce an understanding of a situation from
available information (e.g., interpretation of speech analysis
results).

37
 Perangkat Lunak Sistem Pakar
Perangkat Lunak Berbasis Bahasa
Pemrograman
Perangkat lunak jenis ini merupakan bahasa pemrograman tingkat
tinggi (higher-level languanges). Dengan perangkat lunak ini pengguna
dituntut untuk merancang bagaimana merepresentasikan
pengetahuan (knowledge representation) dan membuat penalaran
pengetahuan (reasoning).

Perangkat Lunak Berbasis Shell

Contoh: WINEXSYS, PROLOG, LISP, CLIPS, JESS, KAPPA-PC, Babylon dan
lain-lain

38
 Referensi
Rich, E and K. Knight, 1991, Artificial Intelligence, McGraw-
Hil, New Delhi
E. Turban, 1990, Decision Support and Expert Systems:
Management support system, Macmillan, New York.
Giarratano, J. Expert Systems - Principles and Programming.
Third Edition. 1998. PWS Publishing Company

39