Nano Science and Technology InstituteNano Science and Technology Institute
Nano Science and Technology Institute 2005 NSTI Nanotechnology Conference & Trade Show
Nanotech 2005
Bio Nano 2005
Business & Investment
Nano Impact Workshop
Program
Sessions
Sunday
Monday
Tuesday
Wednesday
Thursday
Index of Authors
Index of Keywords
Keynote Presentations
Confirmed Speakers
Participating Companies
Industry Focus Sessions
Nanotech Expo
Special Symposia
Conferences
Sponsors
Exhibitors
Venue 2005
Organization
Press Room
Subscribe
Site Map
Nanotech 2005 At A Glance
Nanotech Proceedings
Nanotechnology Proceedings
Global Partner
nano tech
Supporting Organizations
Nanotech 2005 Supporting Organization
Media Sponsors
Nanotech 2005 Medias Sponsors
Event Contact
696 San Ramon Valley Blvd., Ste. 423
Danville, CA 94526
Ph: (925) 353-5004
Fx: (925) 886-8461
E-mail:
 
 

An Algorithmic Approach to the Optimal Extraction of Signals from Intelligent Sensors

P.J. Boltryk, C.J. Harris and N.M. White
University of Southampton, UK

Keywords:
intelligent sensor, fault detection, condition monitoring, kernel, support vector machine

Abstract:
This paper describes current research into the development of an intelligent sensor architecture, where signal conditioning is performed onboard the sensor itself, in software. Our proposed architecture for an intelligent sensor uses data-based models of the sensor for signal conditioning and fault detection, so that the sensor is robust to sensor degradation and its processed output includes an estimate of uncertainty with each measurement value for higher level sensor management processes such as data fusion. We use a data-based kernel representation for the signal conditioning system, which avoids having to derive physical models of the sensor from first principles. A sparse realisation of the kernel model provides fast predictions and opportunities for efficient updating of the sensor model to enable reconfiguration of the sensor model based on incoming data. We show that these techniques have the ability to detect degradation in a MEMS sensor in real-time, using elevated temperatures in laboratory conditions.

Back to Program

Sessions Sunday Monday Tuesday Wednesday Thursday Authors

Nanotech 2005 Conference Program Abstract

 
Gold Sponsors
Nanotech Gold Sponsors
Silver Sponsors
Nanotech Silver Sponsors
Gold Key Sponsors
Nanotech Gold Key Sponsors
Nanotech Ventures Sponsors
Nanotech Ventures Sponsors
Sponsors
Nanotech Sponsors
News Headlines
NSTI Online Community
 
 

© Nano Science and Technology Institute, all rights reserved.
Terms of use | Privacy policy | Contact