IMPORTANT NOTICE: We are putting the finishing touches to this new version of the repository; please bear with us! If you have any questions, please contact eprints.lincoln.ac.uk.

Combining linear filtering and radial basis function networks for accurate profile recovery

Pokric, B. and Allinson, N. M. and Bergstrom, E. T. and Goodall, D. M. (1999) Combining linear filtering and radial basis function networks for accurate profile recovery. IEE Proceedings - Vision, Image and Signal Processing, 153 (6). pp. 297-305. ISSN 1350-245X

Full content URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?...

Documents
Combining linear filtering and radial basis function networks for accurate profile recovery

Request a copy
[img] PDF
00827264.pdf - Whole Document
Restricted to Repository staff only

598kB
Item Type:Article
Item Status:Live Archive

Abstract

The efficient method presented for the accurate approximation of signal profiles corrupted by noise is based on a principled combination of linear and nonlinear processing. The nonlinear processing is realised using a radial basis network which is designed, trained and validated within the strict time constraints set by instrumentation requirements. The quality of profile approximation and the decision to use either linear or nonlinear processing are set by confidence limits which, in turn, are set by the best estimate of current system noise. The approach is described in terms of a novel capillary electrophoresis instrument with all processing implemented on a dedicated DSP subsystem

Additional Information:The efficient method presented for the accurate approximation of signal profiles corrupted by noise is based on a principled combination of linear and nonlinear processing. The nonlinear processing is realised using a radial basis network which is designed, trained and validated within the strict time constraints set by instrumentation requirements. The quality of profile approximation and the decision to use either linear or nonlinear processing are set by confidence limits which, in turn, are set by the best estimate of current system noise. The approach is described in terms of a novel capillary electrophoresis instrument with all processing implemented on a dedicated DSP subsystem
Keywords:electrophoresis, filtering theory, radial basis function networks
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:5130
Deposited On:02 May 2012 07:13

Repository Staff Only: item control page