A fuzzy C-means clustering placement algorithm
Mehdi Dastoori Razaz · 1993 IEEE International Symposium on Circuits and Systems · 2002
A placement algorithm based on fuzzy c-means clustering techniques is presented. The first stage of the algorithm is to construct the max-product transitive closure of the connection matrix, which is then used as a fuzzy similarity relation in a clustering process. This stage is then followed by a combination of fuzzy c-means clustering and linear ordering process to partition modules and construct the final placement configuration. Details of various building blocks of the algorithm and its complexity of computation are described. Experimental results using the algorithm are presented and discussed.>