Raman spectrometry and neural networks for the classification of wood types. 2. Kohonen self-organizing map

One- and two-dimensional Kohonen self-organizing maps (SOMs) were successfu lly used for the unsupervised differentiation of the Fourier transform Rama n spectra of hardwoods from softwoods. The SOMs were also applied to differ entiate temperate woods from tropical woods, and results showed that the tw o types of woods could only be partly differentiated. A semi-quantitative m ethod that is based on the Euclidean distances of the weight matrix has bee n developed to assist the automatic clustering of the neurons in a two-dime nsional SOM. (C) 1999 Elsevier Science B.V. All rights reserved.