Jing Guo
ABSTRACT
A distance metric of patterns is crucial to hotspot cluster analysis and classification. In this paper, we propose an improved tangent space based metric for pattern matching based hotspot cluster analysis and classification. The proposed distance metric is an important extension of the well-developed tangent space method in computer vision. It can handle patterns containing multiple polygons, while the traditional tangent space method can only deal with patterns with a single polygon. It inherits most of the advantages of the traditional tangent space method, e.g., it is easy to compute and is tolerant with small variations or shifts of the shapes. Compared with the existing distance metric based on XOR of hotspot patterns, the improved tangent space based distance metric can achieve up to 37.5% accuracy improvement with at most 4.3x computational cost in the context of cluster analysis. The improved tangent space based distance metric is a more reliable and accurate metric for hotspot cluster analysis and classification. It is more suitable for industry applications.
- Chul-Hong Park, Yoo-Hyon Kim, Ji-Soong Park, Kwan-Do Kim, Moon-Hyun Yoo, and Jeong-Taek Kong. A systematic approach to correct critical patterns induced by the lithograhpy process at the full-chip level. In Proc. SPIE, 1999.Google Scholar
- Gerard T. Luk-Pat, Alexander Miloslavsky, Frank Tseng, and Linni Wen et. al. Correcting lithography hotspots during physical-design implementation. In Proc. SPIE, 2006.Google Scholar
- Li-Da Huang and Wong M. D. F. Optical proximity correction (OPC)-friendly maze routing. In DAC, 2004. Google ScholarDigital Library
- J. Mitra, P. Yu, and D. Z. Pan. RADAR: Ret-aware detailed routing using fast lithography simulations. In DAC, 2005. Google ScholarDigital Library
- Duo Ding and David Z. Pan. Machine learning based lithographic hotspot detection with critical feature extraction and classifications. In International conference on integrated circuit design technology, 2009.Google ScholarCross Ref
- Duo Ding, Andres J. Torres, Fedor G. Pikus, and David Z. Pan. High performance lithographic hotspot detection using hierarchically refined machine learning. In ASPDAC, 2011. Google ScholarDigital Library
- H. Yao, S. Sinha, J. Xu, C. Chiang, Y. Cai, and X. Hong. Efficient range pattern matching algorithm for process-hotspot detection. In ICCAD, 2006.Google Scholar
- Ning Ma. Automatic IC Hotspot Classification and Detection using Pattern-Based Clustering. PhD thesis, Engineering ĺC Mechanical Engineering, University of California, Berkeley, 2008.Google Scholar
- Daniel P. Huttenlocher Klara Kedem and Joseph S. B. Mitchell Esther M. Arkin, L. Paul Chew. An efficiently computable metric for comparing polygonal shapes. (3):209--216, 1991. Google ScholarDigital Library
- Longin Jan Latecki and Rolf Lakamper. Shape similarity measure based on correspondence of visual parts. (10):1--6, 2000.Google Scholar
- S. C. Johnson. Hierarchical clustering schemes. Psychometrika, pages 241--254, 1967.Google ScholarCross Ref
- L. Hubert and J. Schultz. Quadratic assignment as a general data-analysis strategy. Br. J. Math. Stat. Psychol, pages 190--241, 1976.Google Scholar
- G. W. Milligan. A monte carlo study of thirty internal criterion measures for cluster analysis. Psychometrika, (2):187--199, 1981.Google Scholar
- Venkatesh Ganti, Raghu Ramakrishnan, and Johannes Gehrke. Clustering large datasets in arbitrary metric spaces. Proceedings of the 15th International Conference on Data Engineering, pages 502--511, 1999. Google ScholarDigital Library
Index Terms
- Improved tangent space based distance metric for accurate lithographic hotspot classification
Recommendations
Improved Tangent Space-Based Distance Metric for Lithographic Hotspot Classification
A distance metric of patterns is crucial to hotspot cluster analysis and classification. In this paper, we propose an improved tangent space (ITS)-based distance metric for hotspot cluster analysis and classification. The proposed distance metric is an ...
On the similarity metric and the distance metric
Similarity and dissimilarity measures are widely used in many research areas and applications. When a dissimilarity measure is used, it is normally required to be a distance metric. However, when a similarity measure is used, there is no formal ...
Isochronous Temporal Metric for Neighbourhood Analysis in Classification Tasks
AbstractMachine learning, classification, and clustering techniques use the distance functions to evaluate the proximity between data entries and deduce the best neighbouring element and the closest matching entry. The best neighbour is not only the ...
Comments