Evolutionary computation enhancement of olfactory system model

Recent electron microscopy work on rat olfactory system anatomy suggests a structural basis for grouping input stimuli before processing to classify odors. For a simulated nose, the number of inputs per group is a design parameter. Previous results indicate that improvements in classification accuracy can be made by grouping inputs, but such an increase is expensive in terms of hardware and speed. This paper demonstrates that use of evolutionary algorithms (EA) to tune PCNN factoring parameters improves accuracy significantly, with a reasonable processing time, so an increase in inputs per group is not needed.

[1]  Clark S. Lindsey,et al.  Wavelets and signal processing , 1996, Defense + Commercial Sensing.

[2]  John L. Johnson,et al.  Pulse coupled neural networks (PCNN), wavelets and radial basis functions: olfactory sensor applications , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[3]  L. Heimer,et al.  Synaptic distribution of centripetal and centrifugal nerve fibres in the olfactory system of the rat. An experimental anatomical study. , 1968, Journal of anatomy.

[4]  M. L. Padgett,et al.  The inverted multilayer perceptron as a consistency measuring device in neuroanatomical image analysis. , 1998, Brain research. Brain research protocols.

[5]  Steven K. Rogers,et al.  Physiologically motivated image fusion using pulse-coupled neural networks , 1996, Defense + Commercial Sensing.

[6]  John L. Johnson,et al.  Pulse-coupled neural networks (PCNN) and new approaches to biosensor applications , 1998, Defense, Security, and Sensing.

[7]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[8]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[9]  Mary Lou Padgett,et al.  Feature-level signal processing for near-real-time odor identification , 1998, Defense, Security, and Sensing.

[10]  Thomas Lindblad,et al.  Parameter adaptation in a simplified pulse-coupled neural network , 1999, Other Conferences.

[11]  Gilbert Syswerda,et al.  A Study of Reproduction in Generational and Steady State Genetic Algorithms , 1990, FOGA.

[12]  J. L. Johnson.  Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images. , 1994, Applied optics.

[13]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .

[14]  Kalyanmoy Deb,et al.  A Comparative Analysis of Selection Schemes Used in Genetic Algorithms , 1990, FOGA.

[15]  John L. Johnson,et al.  Guest Editorial Overview Of Pulse Coupled Neural Network (PCNN) Special Issue , 1999, IEEE Trans. Neural Networks.

[16]  M. L. Padgett,et al.  Pulse coupled neural networks (PCNN) and wavelets: biosensor applications , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[17]  Reinhard Eckhorn,et al.  Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

[18]  M. L. Padgett,et al.  Multiscale image factorization , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[19]  M. L. Padgett,et al.  The lateral and medial compartments of the olfactory tubercle and their relation to olfactory-related input as determined by artificial neural network analysis , 1997, Brain Research.