Classification of flue-cured and Burley tobacco types with artificial neural networks (ANNs) were studied. Burley tobacco was further classified as either grown in the USA or grown outside the USA. The input data were in the form of near infrared (NIR) spectra, each spectrum containing 19 points. The number of flue-cured and Burley samples were 654 and 959, respectively. The number of native and non-native tobacco samples were 266 and 267, respectively. The models selected for this research were a quadratic classifier, a back-propagation network and a linear network. The results of the calibration model and the true performance for classifying tobacco species were (100%, 100%), (99.38%, 99.39%) and (95.19%, 99.26%) for the quadratic classifier, back-propagation network and linear network, respectively. The identification of native tobacco and its true performance were (100%, 100%) using a quadratic classifier, (89.12%, 88.46%) using a back-propagation network and (80.68%, 79.62%) using a linear network.

Two artificial neural network models were used to estimate the nicotine in tobacco: (i) a back-propagation network and (ii) a linear network. The back-propagation network consisted of an input layer, an output layer and one hidden layer. The linear network consisted of an input layer and an output layer. Both networks used the generalised delta rule for learning. Performances of both networks were compared to the multiple linear regression method MLR of calibration. The nicotine content in tobacco samples was estimated for two different data sets. Data set A contained 110 near infrared (NIR) spectra each consisting of reflected energy at eight wavelengths. Data set B consisted of 200 NIR spectra with each spectrum having 840 spectral data points. The Fast Fourier transformation was applied to data set B in order to compress each spectrum into 13 Fourier coefficients. For data set A, the linear regression model gave better results followed by the back-propagation network which was followed by the linear network. The true performance of the linear regression model was better than the back-propagation and the linear networks by 14.0% and 18.1%, respectively. For data set B, the back-propagation network gave the best result followed by MLR and the linear network. Both the linear network and MLR models gave almost the same results. The true performance of the back-propagation network model was better than the MLR and linear network by 35.14%.

No abstract

No abstract