A learning approach to identification of nonlinear physiological systems using wiener models

Xingjian Jing, Natalia Angarita-Jaimes, David Simpson, Robert Allen, Philip Newland

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


The Wiener model is a natural description of many physiological systems. Although there have been a number of algorithms proposed for the identification of Wiener models, most of the existing approaches were developed under some restrictive assumptions of the system such as a white noise input, part or full invertibility of the nonlinearity, or known nonlinearity. In this study a new recursive algorithm based on Lyapunov stability theory is presented for the identification of Wiener systems with unknown and noninvertible nonlinearity and noisy data. The new algorithm can guarantee global convergence of the estimation error to a small region around zero and is as easy to implement as the well-known back propagation algorithm. Theoretical analysis and example studies show the effectiveness and advantages of the proposed method compared with the earlier approaches.
Original languageEnglish
Title of host publicationBIOSIGNALS 2011 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing
Number of pages5
Publication statusPublished - 18 Jul 2011
EventInternational Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2011 - Rome, Italy
Duration: 26 Jan 201129 Jan 2011


ConferenceInternational Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2011


  • Lyapunov stability
  • Neuronal modelling
  • Noisy data
  • Noninvertible nonlinearity
  • Wiener models

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering

Cite this