Week 5 - Introduction to Artificial Intelligence Applications


Find a journal article (or conference proceedings paper) that describes an expert system/artificial intelligence application related to your field of research or interest. You may find such papers in the following journals: Applied Engineering in Agriculture, Transactions of ASAE, or Applied AI in Natural Resources. There are many other possible places to find an article too. Read the article and prepare a brief review that is emailed to me (engelb) by the end of week 6. If possible, indicate what software was used and describe the benefits of expert system/artificial intelligence approach in solving the problem.

Review this document.

Read Chapters 2 (The Representation of Knowledge) and 6 (The Design of Expert Systems) in the text "Expert Systems: Principles and Programming."

WWW sites of possible interest (these are optional):

WWW Virtual Library: AI

Electronic AI Journals

Important Terms and Concepts:

In this section of the course, we will explore expert systems (ES) which have grown from the artificial intelligence (AI) field. ES have many possible applications within agriculture and engineering. They may be used to complement the other systems analysis and engineering techniques that we examine.

It is important to understand the human decision making process to best understand how one should develop ES and decision support software. Follow this link to learn more about decision making and decision support.

The following sections highlight materials from your reading and other sources.

ES definition/properties

  1. "reasons" by symbol manipulation
  2. solves problems with a high degree of complexity and difficulty
  3. expertise is exemplified by high-level rules, the avoidance of a blind search, and high performance
  4. uses heuristics or "rules of thumb" to arrive at an answer
  5. reformulates the problem from lay terminology into a form suitable for expert rule application
  6. utilizes a well structured knowledge base sufficient for the solution of problems within a relatively narrow domain
  7. provides explanations of its line of reasoning and answers questions about its knowledge
  8. integrates new knowledge on an incremental basis without detrimentally affecting previous knowledge or control strategies


An expert is a person who, because of training and experience, is able to do things the rest of us cannot; experts are not only proficient but also smooth and efficient in the actions they take. Experts know a great many things and have tricks and caveats for applying what they know to problems and tasks; they are also good at plowing through irrelevant information in order to get at basic issues, and they are good at recognizing problems they face as instances of types with which they are familiar. Underlying the behavior of experts is the body of operative knowledge we have termed expertise. It is reasonable to suppose, therefore, that experts are the ones to ask when we wish to represent the expertise that makes their behavior possible.

Comparing Humans and ES

Good News
human expertise                   ES

perishable permanent difficult to transfer easy to transfer difficult to document easy to document unpredictable consistent expensive affordable

Bad News
human expertise                    ES

creative uninspired adaptive needs to be told sensory experience symbolic input broad focus narrow focus common sense knowledge technical knowledge

Categories of ES Applications

  1. Interpretation - inferring situation description from sensor data
  2. Prediction - inferring likely consequences of given situations
  3. Diagnosis - inferring system malfunctions from observables
  4. Design - configuring objects under constraints
  5. Planning - designing actions
  6. Monitoring - comparing observations to expected outcomes
  7. Debugging - prescribing remedies for malfunctions
  8. Repair - executing plans to administer prescribed remedies
  9. Instruction - diagnosing, debugging, and repairing student behavior
  10. Control - governing overall system behavior

Agricultural ES Applications

  1. marketing
  2. diagnostics
  3. planning
  4. operations management
  5. expert control
  6. university/government

Requirements for ES development

  1. task does not require common sense
  2. task requires only cognitive skills
  3. experts can articulate their methods
  4. genuine experts exist
  5. experts agree on solution
  6. task is not too difficult
  7. task is not poorly understood

When is ES Development Justified

  1. task solution has a high payoff
  2. human expertise being lost
  3. human expertise scarce
  4. expertise needed in many locations
  5. expertise needed in hostile environments

Characteristics that make use of ES appropriate

  1. task requires symbol manipulation
  2. task requires heuristic solutions
  3. task is not too easy
  4. task has practical value
  5. task is of manageable size

Potential Limitations in ES Development

  1. lack of resources
  2. ES not good at: