Background Study ABout Expert Systems

Its been over 5 weeks since we got to start our project and the work is still like..."p grat lair" lol. So we have decide to use a good software development technique here. We will most probably be using the spiral model for this project.

So as I said before that we will be using AIML..but we have recently looked into the facts and see that AIML will not really fit this program.. we need an AI that will also be able to learn new things. Does AIML cater for this? I don't know yet. Will have to make some research on this.

So to REALLY start this hyper project.. we are doing some background research about existing softwares. Brief info:

• MYCIN
• DENDRAL
• ZERO

MYCIN

MYCIN was an early expert system developed over five or six years in the early 1970s at Stanford University. It was written in Lisp.  It arose in the laboratory that had created the earlier Dendral expert system, but emphasized the use of judgmental rules that had elements of uncertainty (known as certainty factors) associated with them. This expert system was designed to identify bacteria causing severe infections, such as bacteremia and meningitis, and to recommend antibiotics, with the dosage adjusted for patient's body weight.


MYCIN operated using a fairly simple inference engine, and a knowledge base of ~600 rules. It would query the physician running the program via a long series of simple yes/no or textual questions. At the end, it provided a list of possible culprit bacteria ranked from high to low based on the probability of each diagnosis, its confidence in each diagnosis' probability, the reasoning behind each diagnosis (that is, MYCIN would also list the questions and rules which led it to rank a diagnosis a particular way), and its recommended course of drug treatment.


DENDRAL 


Dendral was an influential pioneer project in artificial intelligence (AI) of the 1960s, and the computer software expert system that it produced. Its primary aim was to help organic chemists in identifying unknown organic molecules, by analyzing their mass spectra and using knowledge of chemistry.

It consists of two sub-programs, Heuristic Dendral and Meta-Dendral,^[5]. It was written in Lisp (programming language), which was considered the language of AI. 




ZERO


Zero is an artificial intelligent chatbot being designed by Computer Hope as a way to help develop our natural language processing and fuzzy logic methods used in scripts throughout our web page. Our overall goal is to develop easier methods for users to locate the answers to their computer related questions through the use of artificial intelligence.

As Zero continues to talk and be taught by other users it's database of knowledge and potential responses grow and enable Zero to learn.

Written in Perl!!


There are many others but most codes are not open source. Possible languages we will be using are JESS, CLIPS, PERL, LISP or AIML.

AM still comparing the different ones. Will be updating soon of their advantages and disadvantages. Express your comments here and share what you know. I would be most grateful to your valued knowledge sharing.

Read more...

Enter your email address:

Delivered by FeedBurner