Accurate lithography hotspot detection based on PCA-SVM classifier with hierarchical data clustering

Jhih-Rong Gao; Bei Yu; David Z. Pan

doi:10.1117/12.2045888

28 March 2014 Accurate lithography hotspot detection based on PCA-SVM classifier with hierarchical data clustering

Jhih-Rong Gao, Bei Yu, David Z. Pan

Author Affiliations +

Proceedings Volume 9053, Design-Process-Technology Co-optimization for Manufacturability VIII; 90530E (2014) https://doi.org/10.1117/12.2045888
Event: SPIE Advanced Lithography, 2014, San Jose, California, United States

Abstract

As technology nodes continues shrinking, layout patterns become more sensitive to lithography processes, resulting in lithography hotspots that need to be identified and eliminated during physical verification. In this paper, we propose an accurate hotspot detection approach based on PCA (principle component analysis)-SVM (sup- port vector machine) classifier. Several techniques, including hierarchical data clustering, data balancing, and multi-level training, are provided to enhance performance of the proposed approach. Our approach is accurate and more efficient than conventional time-consuming lithography simulation; in the meanwhile, provides high flexibility to adapt to new lithography processes and rules.

Citation Download Citation

Jhih-Rong Gao, Bei Yu, and David Z. Pan "Accurate lithography hotspot detection based on PCA-SVM classifier with hierarchical data clustering", Proc. SPIE 9053, Design-Process-Technology Co-optimization for Manufacturability VIII, 90530E (28 March 2014); https://doi.org/10.1117/12.2045888

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE