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

作     者：Pokric, B Allinson, NM Bergström, ET Goodall, DM 

作者机构：UMIST Dept Elect & Elect Engn Manchester M60 1QD Lancs England Univ York Dept Chem York YO10 5DD N Yorkshire England 

出 版 物：《IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING》 (IEE Proc Vision Image Signal Proc)

年 卷 期：1999年第146卷第6期

页      面：297-305页

核心收录：

主　　题：signal processing electrophoresis filtering theory capillary electrophoresis instrument radial basis function networks accurate profile recovery DSP subsystem Neural computing techniques Digital signal processing nonlinear processing noise Filtering methods in signal processing signal profiles approximation linear processing confidence limits linear filtering 

摘      要：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.