Multiple-classification ripple-down rules

Multiple-classification ripple-down rules (MCRDR) is an incremental knowledge acquisition technique which preserves the benefits and essential strategy of ripple-down rules (RDR) in handling the multiple classifications. MCRDR, the extension of RDR, is based on the assumption that the knowledge an expert provides is essentially a justification for a conclusion in a particular context.[1]

Implementations

Below is a list of implementations of MCRDR

  • The alpha version of RDR(MCRDR) Framework was developed by UNSW and UTAS Research Team and funded by ARC (System available at BESTRDR)
  • RDR(MCRDR) document classifier was developed by Dr.Yang Sok Kim and AProf.Byeong Ho Kang (System available at BESTRDR)
  • RDR(MCRDR) smart expert system was developed by UTAS Research Team and funded by Hyundai Steel.
  • Pacific Knowledge Systems (PKS) uses a commercial product called RippleDown Expert that is based on Multiple Classification Ripple Down Rules
  • Medscope Medication Review Mentor uses Multiple Classification Ripple Down Rules to identify adverse drug interactions with a patient's medicines regimen

BEST RDR Warehouse

BEST-RDR (Best Expert System Technique – Ripple Down Rule) website is freely accessible RDR publication and system warehouse that helps you to find programs and publications about RDR. A great amount of publications and programs based on RDR (MCRDR) are available to public.

What functions are available in the BEST RDR?

  1. BEST-RDR website provides detailed explanation of what the RDR and MCRDR are
  2. BEST-RDR provides every RDR(MCRDR) publication details from 1987–2013.
  3. BEST-RDR provides sources of various RDR(MCRDR) based system for download
gollark: Longer-term predictions of scientific developments always tend to miss some weird thing which came out of seemingly nowhere.
gollark: I think they would argue that seed AI isn't that far-future and very important to get right. But it's very hard to tell if it *actually* is.
gollark: You could probably make an excuse along the lines of "if it's not accurate enough, it is liable to go horribly wrong and explode *your* ship".
gollark: I think you can *technically* emulate those on classical computers, but very slowly.
gollark: Also pain toggles and metadata and not just "something hurts now, good luck working out why and also you can't stop it".

See also

References

  1. B.Kang, P. Compton and P.Preston (1995). "Multiple classification ripple down rules: evaluation and possibilities". In The 9th Knowledge Acquisition for Knowledge Based Systems Workshop.
  • "BEST RDR (Best Expert System Technique Ripple Down Rules)". RDR systems and publications available. Retrieved February 15, 2013.
  • B.Kang, P. Compton and P.Preston (1995). "Multiple classification ripple down rules: evaluation and possibilities". In The 9th Knowledge Acquisition for Knowledge Based Systems Workshop.
  • H.Yoon, SC.Han, BH.Kang and SB.Park (2012). "V&V to Use Agile Approach in ES Development: Why RDR Works for Expert System Developments!. Computer Applications for Software Engineering". Disaster Recovery, and Business Continuity.CS1 maint: multiple names: authors list (link)


This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.