Title :
Statistical Analysis of Multi-Censored Electromigration Data using the EM Algorithm
Author :
Raghavan, N. ; Cher Ming Tan
Author_Institution :
Nanyang Technol. Univ., Singapore
Abstract :
The novelty of this work lies in using the E&M algorithm for analyzing multi-censored mixture distribution EM data. Furthermore, the Akaike Information Criterion (AIC) will be used to determine the number of failure mechanisms in a given set of failure data and the Bayes´ posterior probability theory is applied to determine the probability of each failure data belonging to the different failure mechanisms. All these useful information are further validated by performing failure analysis on selected test units.
Keywords :
ULSI; electromigration; failure analysis; integrated circuit interconnections; statistical analysis; Akaike information criterion; Bayes posterior probability theory; EM algorithm; failure analysis; multicensored electromigration data; statistical analysis; Algorithm design and analysis; Aluminum; Circuit testing; Data analysis; Electromigration; Failure analysis; Integrated circuit interconnections; Statistical analysis; Statistical distributions; Ultra large scale integration;
Conference_Titel :
Physical and Failure Analysis of Integrated Circuits, 2007. IPFA 2007. 14th International Symposium on the
Conference_Location :
Bangalore
Print_ISBN :
978-1-4244-1014-9
DOI :
10.1109/IPFA.2007.4378096
