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