Expert System

Definition; An Expert System is a computer program that mimics the decision-making ability of a human expert.
It uses knowledge + reasoning to solve complex problems in a specific domain.

It is a major application   of Artificial Intelligence (AI).

Key Components

1. Knowledge Base → Stores facts & rules (like an expert’s brain). Example: “If crop leaves are yellow → possible nitrogen deficiency.”
2. Inference Engine → The reasoning part (applies rules to facts to reach a conclusion).
3. User Interface → Interaction between user and system (questions/answers).

Working (Simple Steps)

1. User gives input (problem/question).
2. System checks rules in the knowledge base.
3. Inference engine applies reasoning.
4. System gives advice, diagnosis, or solution (like an expert).

Examples of Expert Systems

Agriculture

• AGRO-EXPERT → Suggests crop management practices.
• Paddy-Doctor → Diagnoses rice diseases & suggests treatment.
• Krishi Gyan → Expert advisory for farmers.

Medical

• MYCIN → Early medical expert system (diagnosed infections, suggested antibiotics).
• DENDRAL → Analyzed chemical compounds.

Industry/Business

• XCON (Digital Equipment Corp.) → Configured computer systems.
• CLIPS (NASA) → Decision support for space projects.

Facts for Exams

• First Expert System: DENDRAL (1965, Stanford University) – chemistry analysis.
• Best-known Medical Expert System: MYCIN (1970s).
• In India, expert systems are widely used in agriculture extension, healthcare, and engineering.

Decision Support System (DSS)

A Decision Support System (DSS) is a computer-based information system that helps in decision-making processes by analyzing large volumes of data, providing useful information, and suggesting alternatives. DSS does not replace human decision-making but supports it by offering data, models, and analytical tools.

Features of DSS

1. Interactive system – allows users to query and analyze data.
2. Data-driven – uses databases, data warehouses, and real-time data.
3. Model-driven – uses statistical, mathematical, or simulation models.
4. Supports unstructured/semi-structured decisions – useful in complex situations.
5. User-friendly – often uses dashboards, charts, and visualization tools.

Types of DSS

1. Data-driven DSS – focuses on access and analysis of large datasets (e.g., business intelligence tools).
2. Model-driven DSS – uses mathematical or simulation models (e.g., crop simulation models in agriculture).
3. Knowledge-driven DSS – uses expert systems to suggest actions (e.g., medical diagnosis support).
4. Communication-driven DSS – supports collaboration and group decision-making (e.g., groupware, video conferencing).

Examples of DSS

• Agriculture:
  • CROPWAT (by FAO) – helps farmers calculate water requirements for irrigation.
  • DSSAT (Decision Support System for Agrotechnology Transfer) – predicts crop yield under different conditions.
• Business: SAP BusinessObjects – helps in financial and strategic decision-making. Microsoft Power BI – interactive dashboards for business analytics.
• Healthcare: Clinical DSS – assists doctors in diagnosis and treatment recommendations.

In short, DSS = Data + Models + User Interface → helps in better, faster, and evidence-based decisions.