The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

new clustering algorithm - K-NC and 1-NC

sgenzersgenzer Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
edited November 2018 in Help

Stumbled across this article about "cliques" and "clique density" as an improvement to k-NN.  Anyone see this before and/or implemented it?

 

http://www.datasciencecentral.com/profiles/blogs/nice-generalization-of-the-k-nn-clustering-algorithm

 

Scott

Tagged:

Answers

  • Telcontar120Telcontar120 RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn

    This seems quite similar conceptually to the Cluster-Based Local Outlier Factor approach, which is used in outlier detection (and is included in the free anomaly detection extension in RapidMiner).  I'd have to dig in further to see how they are different, or have an implementation of the k-NC to compare the outcomes.  But if you are interested in this then you may want to check out CB-LOF.

     

    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
Sign In or Register to comment.