Know and understand characteristics, uses and purpose of expert systems including mineral prospecting, car engine fault diagnosis, medical diagnosis, chess games, financial planning, route scheduling for delivery vehicles, plant and animal identifica

ICT Applications – Expert Systems

Learning Objective

Know and understand the characteristics, uses and purpose of expert systems, with examples from mineral prospecting, car engine fault diagnosis, medical diagnosis, chess games, financial planning, route scheduling for delivery vehicles, and plant and animal identification.

What is an Expert System?

• A computer program that mimics the decision‑making ability of a human expert.
• Combines a knowledge base (facts and rules) with an inference engine (reasoning mechanism).
• Provides advice, diagnosis or solutions in a specific domain.

Key Characteristics

Common Uses and Purposes

1. Assist decision‑making where expert knowledge is scarce or expensive.
2. Provide consistent, repeatable analysis.
3. Speed up problem solving and reduce human error.
4. Offer training and support for less‑experienced staff.
5. Enable remote or automated operation in hazardous environments.

Examples of Expert Systems

1. Mineral Prospecting

Purpose: Identify locations with a high probability of valuable mineral deposits.

• Uses geological data, satellite imagery, and historical mining records.
• Applies rules such as “If rock type = basalt and magnetic anomaly > threshold, then prospectivity = high.”

2. Car Engine Fault Diagnosis

Purpose: Detect and suggest repairs for engine problems.

• Inputs: Sensor readings, error codes, driver symptoms.
• Inference: Matches patterns to known fault models (e.g., “misfire + low fuel pressure → fuel injector issue”).

3. Medical Diagnosis

Purpose: Assist clinicians in identifying diseases.

• Knowledge base includes symptoms, test results, epidemiology.
• Example rule: “If fever > 38°C and rash present and travel to tropical region, then consider dengue fever.”

4. Chess Game Analysis

Purpose: Provide move recommendations and evaluate positions.

• Encodes strategic principles and end‑game tablebases.
• Uses minimax search with heuristics to simulate expert play.

5. Financial Planning

Purpose: Generate personalized investment or retirement plans.

• Considers income, expenses, risk tolerance, tax rules.
• Applies rules such as “If age > 60 and risk tolerance = low, then allocate 70% to bonds.”

6. Route Scheduling for Delivery \cdot ehicles

Purpose: Optimise routes to minimise travel time and fuel cost.

• Inputs: Delivery locations, traffic data, vehicle capacity.
• Uses algorithms (e.g., Clarke‑Wright savings) guided by expert routing rules.

7. Plant and Animal Identification

Purpose: Identify species from observable characteristics.

• Knowledge base contains taxonomic keys, habitat data, visual traits.
• Rule example: “If leaf shape = lanceolate and flower colour = red, then species = *Eucalyptus camaldulensis*.”

Advantages of Expert Systems

• Availability 24/7 – no need for human expert on‑site.
• Consistency – same conclusions for identical data.
• Scalability – can serve many users simultaneously.
• Cost‑effective – reduces need for expensive consultancy.

Limitations

• Limited to the knowledge encoded; cannot handle situations outside its domain.
• Knowledge acquisition can be time‑consuming.
• May lack the intuition and creativity of human experts.
• Maintenance required to keep the knowledge base up‑to‑date.

Summary Table