Issue No. 11 - November (1990 vol. 12)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.61708
<p>Parallel algorithms on SIMD (single-instruction stream multiple-data stream) machines for hierarchical clustering and cluster validity computation are proposed. The machine model uses a parallel memory system and an alignment network to facilitate parallel access to both pattern matrix and proximity matrix. For a problem with N patterns, the number of memory accesses is reduced from O(N/sup 3/) on a sequential machine to O(N/sup 2/) on an SIMD machine with N PEs.</p>
SIMD machines; parallel algorithms; computational complexity; hierarchical clustering; cluster validity; parallel memory system; alignment network; pattern matrix; proximity matrix; computational complexity; computerised pattern recognition; parallel processing
X. Li, "Parallel Algorithms for Hierarchical Clustering and Cluster Validity," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 12, no. , pp. 1088-1092, 1990.