From: oguzd77@yahoo.com   
      
   hi;   
   i have developed a data mining tool that uses   
   k-means clustering algorithm. The solution is nearly correct(after a   
   few   
   trials it is high probability that "every cluster is chosen right").   
   But i want to omit the trials so i think i have to start with the   
   optimization of choosing the "right initial cluster centers."!!   
   i want to know if there is a technique or a known method for   
   choosing the right initial cluster centers(rather than randomly   
   choosing)   
   in order to optimize the clustering solution.   
      
   i will be very pleased if i recieve an answer very soon.   
   thank you   
   Oguz Divilioglu   
      
   [ comp.ai is moderated.  To submit, just post and be patient, or if ]   
   [ that fails mail your article to , and ]   
   [ ask your news administrator to fix the problems with your system. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)