Background: In this study, 20 samples of soybean, both transgenic and conventional cultivars, which were planted in two different regions, Londrina and Ponta Grossa, both located at Paraná, Brazil, were analysed. In order to verify whether the inorganic compound levels in soybeans varied with the region of planting, K, P, Ca, Mg, S, Zn, Mn, Fe, Cu and B contents were analysed by an artificial neural network self-organising map.
Results: It was observed that with a topology 10 × 10, 8000 epochs, initial learning rate of 0.1 and initial neighbourhood ratio of 4.5, the network was able to differentiate samples according to region of origin. Among all of the variables analysed by the artificial neural network, the elements Zn, Ca and Mn were those which most contributed to the classification of the samples.
Conclusion: The results indicated that samples planted in these two regions differ in their mineral content; however, conventional and transgenic samples grown in the same region show no difference in mineral contents in the grain.
Keywords: Kohonen self-organising map; artificial neural networks; soybean minerals; synaptic adaptation; topological neighbourhood; unsupervised learning.
© 2015 Society of Chemical Industry.