AI - a Guide to Intelligent Systems.pdf - Member of EEPIS

310
KNOWLEDGE ENGINEERING AND DATA MINING
Mac system start-up, the first clause of all rules will identify this task. For
example,
Rule: 1
if task is ‘system start-up’
then ask problem
Rule: 2
if task is ‘system start-up’
and problem is ‘system does not start’
then ask ‘test power cords’
Rule: 3
if task is ‘system start-up’
and problem is ‘system does not start’
and ‘test power cords’ is ok
then ask ‘test Powerstrip’
All the other rules will follow this structure. A set of rules to direct
troubleshooting when the Mac system does not start (in Leonardo code) is
shown in Figure 9.3.
Now we are ready to build a prototype, or in other words to implement the
initial set of rules using an expert system development tool.
How do we choose an expert system development tool?
In general, we should match the features of the problem with the capabilities of the
tool. These tools range from high-level programming languages such as LISP,
PROLOG, OPS, C and Java, to expert system shells. High-level programming
languages offer a greater flexibility and can enable us to meet any project requirements,
but they do require high-level programming skills. On the other hand, shells,
although they do not have the flexibility of programming languages, provide us with
the built-in inference engine, explanation facilities and the user interface. We do not
need any programming skills to use a shell – we just enter rules in English in the shell’s
knowledge base. This makes shells particularly useful for rapid prototyping.
So how do we choose a shell?
The Appendix provides some details of a few commercial expert systems shells
currently available on the market. This can help you to choose an appropriate
tool; however the internet is rapidly becoming the most valuable source of
information. Many vendors have Web sites, and you can even try and evaluate
their products over the Web.
In general, when selecting an expert system shell, you should consider how
the shell represents knowledge (rules or frames), what inference mechanism it
uses (forward or backward chaining), whether the shell supports inexact reasoning
and if so what technique it uses (Bayesian reasoning, certainty factors or
fuzzy logic), whether the shell has an ‘open’ architecture allowing access to