Conference Paper

Prior knowledge-based fuzzy Support Vector Regression

Dept. of Autom., Univ. of Sci. & Technol. Beijing, Beijing
DOI: 10.1109/FUZZY.2008.4630397 In proceeding of: Fuzzy Systems, 2008. FUZZ-IEEE 2008. (IEEE World Congress on Computational Intelligence). IEEE International Conference on
Source: IEEE Xplore

ABSTRACT A new method was proposed for incorporating prior knowledge in the form of fuzzy knowledge sets into Support Vector Machine for regression problem. The prior knowledge of Fuzzy IF-THEN rules can be transformed into fuzzy information to generate fuzzy kernel, based on which FSVR (Fuzzy Support Vector Regression) is introduced. The merit of FSVR is that it can incorporate with prior knowledge represented by fuzzy IF-THEN rules to improve the performance of the conventional SVR in incomplete numeral dataset for training. The simulation results are feasible.

0 Bookmarks
 · 
55 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: In advanced semiconductor manufacturing, the in-process wafers need to be monitored periodically in order to obtain high stability and high yield rate. However, the actual measurement is usually obtained after all the work-pieces of the same lot have been processed. The parameter drift or shift of the production equipment could not be detected in real-time thereby increasing the production cost. We proposed a quality prediction system (QPS) based on support vector regression (SVR) and fuzzy learning mechanism (FLM) to overcome this problem. The SVR provided good generalization performance for prediction, and the embedded FLM implied a continuous improvement or at least non-degradation of the system performance in an ever changing environment. The effectiveness of the proposed QPS was validated by test on chemical vapor deposition (CVD) process in practical 12-inch wafer fabrication. The results show that the proposed QPS not only fulfills real-time quality measurement of each wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing process.
    FUZZ-IEEE 2009, IEEE International Conference on Fuzzy Systems, Jeju Island, Korea, 20-24 August 2009, Proceedings; 01/2009