Applications of the self-organising feature map neural network in community data analysis

Freedom from restrictive assumptions that underlie many quantitative techniques make neural networks attractive for ecological investigations. The potential of the self organising feature map (SOFM) neural network for the classification, and to a lesser extent, ordination of vegetation data was investigated. The SOFM output was shown to correspond closely to classifications obtained from three alternative clustering algorithms, with similar samples located close together in the SOFM output space. Moreover, the classes were distributed spatially in the SOFM output by their relative similarity. This was evident with comparison against classifications derived at various levels of a hierarchical classification that revealed that the classes aggregated during each step of the hierarchical classification also tended to lie close together in the SOFM output space. As a consequence, the spatial distribution of classes in the SOFM output may represent the data in a manner similar to an ordination analysis. Some evidence for this inference is provided by comparison with the results of a standard ordination analysis.

[1]  N. C. Kenkel,et al.  Nonlinear Ordination Using Flexible Shortest Path Adjustment of Ecological Distances , 1987 .

[2]  P. Greig-Smith The development of numerical classification and ordination , 1980 .

[3]  Derek A. Roff,et al.  DISTRIBUTION-FREE AND ROBUST STATISTICAL METHODS: VIABLE ALTERNATIVES TO PARAMETRIC STATISTICS? , 1993 .

[4]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[5]  S. Lek,et al.  The use of artificial neural networks to predict the presence of small‐bodied fish in a river , 1997 .

[6]  Niels G. Waller,et al.  A comparison of the classification capabilities of the 1-dimensional kohonen neural network with two pratitioning and three hierarchical cluster analysis algorithms , 1998 .

[7]  Sovan Lek,et al.  Improved estimation, using neural networks, of the food consumption of fish populations , 1995 .

[8]  Robert J. Schalkoff,et al.  Pattern recognition - statistical, structural and neural approaches , 1991 .

[9]  Miguel Equihua,et al.  Fuzzy clustering of ecological data. , 1990 .

[10]  Susanna T. Y. Tong,et al.  The use of non-metric multidimensional scaling as an ordination technique in resource survey and evaluation: a case study from southeast Spain , 1992 .

[11]  D B Kell,et al.  Rapid identification using pyrolysis mass spectrometry and artificial neural networks of Propionibacterium acnes isolated from dogs. , 1994, The Journal of applied bacteriology.

[12]  Pierre Demartines,et al.  Data Analysis: How to Compare Kohonen Neural Networks to Other Techniques? , 1991, IWANN.

[13]  Young-Seuk Park,et al.  Patternizing communities by using an artificial neural network , 1996 .

[14]  Holger R. Maier,et al.  The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study , 1998 .

[15]  Giles M. Foody,et al.  Fuzzy modelling of vegetation from remotely sensed imagery , 1996 .

[16]  R. Ragade,et al.  Ecosystem analysis using fuzzy set theory , 1982 .

[17]  Mark W. Denny,et al.  The largest, smallest, highest, lowest, longest, and shortest: extremes in ecology , 1993 .