A Neural Network Implementation for a Electronic Nose

  • Philip B James-Roxby
Conference paper


A new implementation of a multi-layer perceptron neural network is presented where activation levels within the network are encoded using Sigma-Delta modulation. Large, hardware networks can be constructed, which can be trained using the standard back-propagation algorithm. The network has been used to form a stand-alone electronic nose system capable of distinguishing between four odours.


Genetic Algorithm Finite State Machine Electronic Nose Host Computer Standard Genetic Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Gardner, J.W., Bartlett, P.N.: Sensors and Actuators B, vol 18, no 1-3, 211 (1993)Google Scholar
  2. [2]
    Shurmer, H.V.: IEE Proceedings, vol 37, pt G, no 3, 197 (1990)Google Scholar
  3. [3]
    Moriizumi, T.: Thin Solid Films, 160, 413 (1988)CrossRefGoogle Scholar
  4. [4]
    Bartlett, P.N., Archer, P.B.M, Ling-Chung, S.K: Sensors and Actuators, 19, 125 (1989)CrossRefGoogle Scholar
  5. [5]
    Uchimura, Hayashi, Kimura, Iwata: IEEE Trans. Acoustics, Speech and Sig.Proc, 36, 1899 (1986)CrossRefGoogle Scholar
  6. [6]
    Tomberg, J.E., Kaski, K. K. K.: IEEE J. of Solid-State Circuits, vol. 25. no. 5. 1277 (1990)CrossRefGoogle Scholar
  7. [7]
    Goldberg, D.E.: Genetic Algorithms in search, optimization and machine learning. Addison Wesley 1989MATHGoogle Scholar
  8. [8]
    Koza, J.R.: Genetic Programming. MIT Press 1992MATHGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Philip B James-Roxby
    • 1
  1. 1.UMISTManchesterEngland

Personalised recommendations