Linearly graded behavioural analogue performance models using support vector machines and VHDL-AMS
Linearly graded behavioural analogue performance models using support vector machines and VHDL-AMS
A concept of linearly graded statistical models for analogue performance evaluation is proposed and a suitable technique for automatic generation of analogue performance models using support vector machines is presented. The analogue system's behaviour is specified using VHDL-AMS descriptions. Practical application of the technique is demonstrated with a case study of automated analogue performance model generation for an analogue filter.
Ren, Xianqiang
c7f83e76-c48c-4690-86e3-f5fddb5e2198
Kazmierski, Tom
a97d7958-40c3-413f-924d-84545216092a
2005
Ren, Xianqiang
c7f83e76-c48c-4690-86e3-f5fddb5e2198
Kazmierski, Tom
a97d7958-40c3-413f-924d-84545216092a
Ren, Xianqiang and Kazmierski, Tom
(2005)
Linearly graded behavioural analogue performance models using support vector machines and VHDL-AMS.
Forum on specification and design languages, Lausanne, Switzerland.
Record type:
Conference or Workshop Item
(Other)
Abstract
A concept of linearly graded statistical models for analogue performance evaluation is proposed and a suitable technique for automatic generation of analogue performance models using support vector machines is presented. The analogue system's behaviour is specified using VHDL-AMS descriptions. Practical application of the technique is demonstrated with a case study of automated analogue performance model generation for an analogue filter.
This record has no associated files available for download.
More information
Published date: 2005
Additional Information:
Event Dates: 2005.09.27 - 2005.09.30
Venue - Dates:
Forum on specification and design languages, Lausanne, Switzerland, 2005-01-01
Organisations:
EEE
Identifiers
Local EPrints ID: 264618
URI: http://eprints.soton.ac.uk/id/eprint/264618
PURE UUID: 43095816-c814-4642-9cc2-18df6e0f99b6
Catalogue record
Date deposited: 03 Oct 2007
Last modified: 10 Dec 2021 21:48
Export record
Contributors
Author:
Xianqiang Ren
Author:
Tom Kazmierski
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics