EXPERT SYSTEMS

CONTENTS PAGE
• Introduction
• Characteristics of ES
• Components of ES
• Knowledge Acqusition
• Limitations
• Capabilities of ES
• Expert System Technology
• Application of Expert Systems
• Examples
• Project Proposal
 INTRODUCTION
Expert Systems are computer systems developed to mimic human reasoning and work at the level of
an expert in a particular field, e.g. in medical diagnosis.

They are computer programs that employ artificial intelligence techniques to address issues in a
particular field that often calls for human expertise. They utilized a knowledge-based architecture as
the first commercial systems to do so.
 CHARACTERISTICS OF ES
• Human experts are perishable, but an expert system is permanent.
• It helps to distribute the expertise of a human.
• One expert system may contain knowledge from more than one human experts thus making the
solutions more efficient.
• It decreases the cost of consulting an expert for various domains such as medical diagnosis.
 CHARACTERISTICS OF ES

• They use a knowledge base and inference engine.

• Expert systems can solve complex problems by deducing new facts through existing facts of
knowledge, represented mostly as if-then rules rather than through conventional procedural code.
• Expert systems were among the first truly successful forms of artificial intelligence (AI) software
 COMPONENTS OF ES
1. Knowledge Base – it represents facts and
rules. It consists of knowledge in a
particular domain as well as rules to solve a
problem, procedures and intrinsic data
relevant to the domain.

2. Inference Engine – The function of the inference engine is to 4. User Interface – This module makes it
fetch the relevant knowledge from the knowledge base, possible for a non-expert user to interact
interpret it and to find a solution relevant to the user’s problem. with the expert system and find a solution
The inference engine acquires the rules from its knowledge to the problem.
base and applies them to the known facts to infer new facts.
Inference engines can also include an explanation and
debugging abilities.

3. Knowledge Acquisition and Learning Module – The 5. Explanation Module – This module
function of this component is to allow the expert system helps the expert system to give the user an
to acquire more and more knowledge from various explanation about how the expert system
sources and store it in the knowledge base. reached a particular conclusion.
The Inference Engine generally uses two strategies for
acquiring knowledge from the Knowledge Base, namely :

Forward Chaining.
Backward Chaining.
 FORWARD CHAINING

Forward Chaining is a strategic process used by the Expert System to answer the questions – What
will happen next. This strategy is mostly used for managing tasks like creating a conclusion, result or
effect. Example is a prediction or share market movement status.
 BACKWARD CHAINING

Backward Chaining is a strategy used by the Expert System to answer the questions – Why this has
happened. This strategy is mostly used to find out the root cause or reason behind it, considering what
has already happened. Example – diagnosis of stomach pain, blood cancer or dengue, etc.
 KNOWLEDGE ACQUSITION

• Gather information from experts in the field(e.g doctors, geologists, etc).

• Design the knowledge base.
• Input data into knowledge base.
• Design the rule base.
• Design inference engine
• Design display of results
• Test system with known problems and solutions
• Design appropriate user interface
 LIMITATIONS
• They lack creativity/does not reason.
• They are unable to learn outside the system.
• They lack sensory experience.
• They take time and are difficult to develop.
• They need to be constantly updated to keep pace with recent developments in the field they are
applied.
• Do not have human-like decision-making power.
• Cannot possess human capabilities.
• Cannot produce correct result from less amount of knowledge.
• Requires excessive training.
 CAPABILITIES OF ES
• Provides consistent answers
• Fast identification of solutions to problems by quickly analysing data.
• They produce reliable and accurate results if well programed.
• There is no need for an expert to be present since they can act as a prompt to an
expert.
• They can deal with complex situations much faster than humans.
• They could be used in hazardous areas (e.g. Oil prospecting).
• They do not forget as humans do.
• Many copies can be made at a low cost.
• Knowledge of several experts is combined.
• Save costs on wages and salaries for staff.
• Conclusions are based on logic, no emotions involved.
• Can explain its reasoning method
EXPERT SYSTEM TECHNOLOGY
 APPLICATION OF EXPERT SYSTEMS

• Medical Diagnosis.
• Loan assessment
• Financial planning
• Diagnostics (e.g. finding faults in a car engine, etc.), tax and financial calculations
• Quality Control
• Automated support
• Robotic surgery
• Diagnosis of a software development project.
• Planning experiment in biology, chemistry and molecular genetics.
• Forecasting crop damage.
 EXAMPLES OF EXPERT SYSTEMS

• DENDRAL: It was an artificial intelligence-based expert system used for chemical analysis. It
used a substance’s spectrographic data to predict its molecular structure.

• MYCIN: An early backward chaining expert system that uses artificial intelligence to identify
bacteria causing severe infections, such as bacteremia and meningitis, and to recommend
antibiotics, with the dosage adjusted for patient's body weight — the name derived from the
antibiotics themselves, as many antibiotics have the suffix "-mycin". The Mycin system was also
used for the diagnosis of blood clotting diseases.
 EXAMPLES OF EXPERT SYSTEMS

• CaDet: It is a clinical support system that could identify cancer in its early stages in patients.

• PUFF: Expert System able to diagnose lung diseases.

• DXplain: It is a clinical support system that could identify cancer in its early stages in patients.
 OTHER EXAMPLES CONT...

• The problem being addressed was diagnosing, assessing, and correcting student behaviour. The
examples of expert systems in this field are SMH.PAL, Intelligent Clinical Training and STEAMER.

• An expert system for providing incremental solutions for complex problems. The examples are SAINT,
MATHLAB and MACSYMA.

• An expert system for interpreting, predicting, repairing, and monitoring system behaviors. Examples
include Real Time Process Control, Space Shuttle Mission Control.
 EXPERT SYSTEMS PROJECT

• We are going to create an expert system that can identify a cyber crime based on the information
provided by the user and be able to give out recommendations/ solutions to the crime.
• Our human expert is going to be the AU System Administrator.
GROUP MEMBERS

Delight Shumba - 200449

Denver Mazhindu - 210503
Adrian Dingiswayo - 210389
Kimberly Lunga - 210386
Tadiwa Mwenje - 210384
Rumbidzai Chakumarani - 210781
Dylan Basikoro - 200447