Expert system in computer

Expert Systems

Kiran Paul

EXPERT SYSTEM

Expert system are intelligent computer programs designed to stimulate the problem-solving behavior of human experts.

These programs perform a task that would otherwise be performed by a human expert.

It create a tool that can be used by a layman to solve difficult or ambiguous problems.

There are expert systems that can be diagnose human illnesses, make financial forecast, and schedule routes for delivery vehicles.

They also play chess, underwrite insurance policies, and perform many services which previously required human expertise.

Some expert systems are designed to take the place of human experts, While others are designed to aid them.

DEFINITION

“An expert system is an interactive computer-based decision tool that uses both facts and heuristics to solve difficult decision problems based on knowledge acquired from an expert.”

An expert system compared with traditional computer :

Inference engine + Knowledge = Expert system

CHARACTERISTICS

EXPERTISE

SYMBOL MANIPULATION

INTELLIGENCE

COMPLEXITY

REFORMULATION

REASONING ABOUT SELF

TYPE OF TASK

KINDS OF EXPERT SYSTEMS

Advice expert system

Decision-support expert system

Intelligent interfaces

Learning systems

COMPONENTS OF EXPERT SYSTEM

Knowledge base

Inference engine

User interface

In addition to above components,

Working memory

Domain expert

Explanation capacity

A knowledge maintenance module to update the knowledge base.

An interface to other systems, such as database management and spreadsheets etc.

Components of Expert System

User Interface

Knowledge

Base

Working

Storage

Inference

Engine

User

System Engineer

Domain Expert

Expertise

KnowledgeEngineer

Encoded Expertise

NEED OF EXPERT SYSTEM?

Human expertise is very scarce.

Humans get tired from physical or mental workload.

Humans forget crucial details of a problem.

Humans are inconsistent in their day-to-day decisions.

Humans have limited working memory.

Humans are unable to comprehend large amounts of data quickly.

Humans are unable to retain large amounts of data in memory.

Humans are slow in recalling information stored in memory.

Humans are subject to deliberate or inadvertent bias in their actions.

Humans can deliberately avoid decision responsibilities.

Humans lie, hide, and die.

WHERE EXPERT SYSTEM ARE MOST EFFECTIVE?

Decision Support

Problem-Solving Diagnostics

Data Analysis

Advisory System

Background Monitoring

Inconsistency Detection

Smart Questionnaires

Application in Agriculture

Diagnosis diseases of wheat symptoms - recommendations.

Problem in leaves- disease may be Stem rust(h1)

Problem in leaves- disease may be Flag smut (h0)

The developmental process then adds additional information to help determine whether the hypothesis “disease is flag smut on leaves” is true.

This is not as simple as it might look as other considerations include

symptoms appeared on the defected parts including size of patches

color of spots

condition of defected organ and other information.

The representation of flag smut disease is mentioned below.

• RULE [Is it going to find the problem area which is flag smut?]

• If [season] = "spring" and • [stage]="early" and • [problem_is_in]="leaves" and • [leave_part]="upper" and • [strip_color]="light_green_to_grey_black

Then [the problem] = "FALG SMUT IS DIAGNOSED"

• [recommendation 1]= "CAUSAL ORGANISM: Urocystic tritici" and

• [recommendation 2]= "PERPETUATION: The disease is perpetuated through seed borne and/or soil borne spores, which can survive in the soil up to a period of three years" and

• [

• recommendation 3]= "MANAGEMENT:

1. GROW RESISTANT CULTIVARS.

5. EARLY PLANTING

6. USING THE WET METHOD OF SOWING. IRRIGATING JUST AFTER SOWING.

7. ROGUE OUT AND BURN THE INFECTED PLANT. "

Starting consultation

Problem classification

season

AMRAPALIKA: An expert system for the diagnosis of pests, diseases and disorders in Indian mango.Dr. Wheat: A Web-based expert system for diagnosis of diseases and pests in Pakistani wheat.

EXPERT SYSTEM IN AGRICULTURE

BENEFITS OF EXPERT SYSTEMS

Increase the probability, frequency, and consistency of making good decisions.

Help distribute human expertise.

Facilitate real-time, low-cost expert level decisions by the non expert.

Enhance the utilization of most of the available data.

Permit objectivity by weighing evidence without bias and without regard for the user’s personal and emotional reactions.

Permit dynamism through modularity of structure.

Free up the mind and time of the human expert to enable him or her to concentrate on more creative activities.

Encourage investigations into the subtle areas of a problem.

LIMITATIONS OF EXPERT SYSTEMS

Not widely used or tested.

Limited to relatively narrow problems.

No “common sense”.

Cannot readily deal with “mixed” knowledge.

Possibility of error.

Cannot refine own knowledge base.

Difficult to maintain.

System are not always up to date.

May have high development costs

Conclusion

An expert system is a powerful tool with extensive potential in various field.

The development of an expert system requires the combined effort of specialists from many fields of different areas and can only be accomplished with the cooperation of the users and advisors who will use them.