Many researches on VLSI circuits have assumed that spatial process parameters are known before further analysis or optimization. However, it is a non-trivial task to extract those parameters from silicon measurements due to the inherently high complex...
Many researches on VLSI circuits have assumed that spatial process parameters are known before further analysis or optimization. However, it is a non-trivial task to extract those parameters from silicon measurements due to the inherently high complexity. In this paper, we propose an efficient and effective extraction method of spatial process parameters that utilizes support vector machine regression and particle swarm optimization.