Behavioral-level performance modeling of analog and mixed-signal systems using support vector machines

Author

Ren, X. ; Kazmierski, T.J.

Author_Institution

Sch. of Electron. & Comput. Sci., Southampton Univ.

fYear

2006

fDate

14-15 Sept. 2006

Firstpage

28

Lastpage

33

Abstract

This paper presents a novel behavioral-level analog and mixed-signal (AMS) system performance modeling methodology using support vector machines (SVM). The method relies on linearly graded sub-spaces to model complex multi-dimensional performance spaces. A detailed evaluation of the method has been carried out for the purpose of potential use for AMS synthesis. The method has been applied to a complex non-ideal 2^nd order sigma-delta modulator (SDM) and results show good accuracy of performance modeling and numerical efficiency

Keywords

circuit simulation; integrated circuit design; integrated circuit modelling; mixed analogue-digital integrated circuits; sigma-delta modulation; support vector machines; SVM; behavioral-level analog/mixed-signal system performance modeling; sigma-delta modulator; support vector machine; Circuits; Computer science; Delta-sigma modulation; Hardware; Kernel; Power system modeling; Process design; Risk management; Support vector machines; System performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Behavioral Modeling and Simulation Workshop, Proceedings of the 2006 IEEE International

Conference_Location

San Jose, CA

Print_ISBN

0-7803-9742-8

Type

conf

DOI

10.1109/BMAS.2006.283465

Filename

4062047