SDM Techniques Based on TGSOM and its Application in R&D Performance Evaluation

Research and development activities (R&D) as the core competitiveness in the high-tech enterprises play an extremely important role and far-reaching significance. In order to measure the R&D performance of the high-tech enterprises scientifically and accurately, this paper introduces the tree-structured growing self-organizing maps (TGSOM) network into the spatial data mining (SDM) to be used in spatial clustering. This method not only can make up the limitation of the more data limit and biggish computation in the common spatial data mining, but also overcome the restriction of traditional maps (SOFM) that must appoint in advance. The performance measurement of 110 high-tech enterprises in Hebei Province shows that the results given by this method are reliable.