Skip to content

FCM algorithm based on Tabu Search algorithm for fuzzy clustering

License

Notifications You must be signed in to change notification settings

yhsunshining/fuzzy-c-means

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

90 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

fuzzy C-Means with Tabu Search

current Problem

  1. How to generate the neighbourhood with the local solution?

F: Use random to generate a mat, plus the mat and the solution. This dot is in a hyperrectangle neighbouthood of the mat.

  1. How to define the tabu object, code or the mat? if use the mat, what should we define the object, the mat itself or the area ?

F: use mat and tabu the area of a rect around the mat(see mat as a dot in N-d space)

  1. Calc the J first or judge the tabu-list first?

  2. When get the minimum J, the FMI isn't the maximum. When the FMI is maximum, the J isn't the minimum. What should we choose?

  3. How to comprehend the saddle point in iteration seq?

  4. How to comprehend that the local minimun is related in the init value in iteration seq?

F: In 3-d space ,z in the value of J, consider that there is a local minimun in the 2nd quadrant and a global minimun in the 4th quadrant. When y0>0, it's easy to find the local mininum and never find the global mininum.

About

FCM algorithm based on Tabu Search algorithm for fuzzy clustering

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages