A new approach to discriminate varieties of tobacco using vis/near infrared spectra

Vis/near infrared reflectance spectroscopy appears to be a rapid and convenient non-destructive technique that can measure the quality and compositional attributes of many substances. Principal component analysis (PCA), which offered a qualitative analysis of tobacco samples, was used to analyze the clustering of tobacco samples. A new method combined wavelet transform (WT) with Artificial Neural Network (ANN) was presented to establish a discrimination model. The model regarded the compressed spectra data as the input of ANN, and 80 samples were selected randomly as calibration collection whereas the remaining 20 were being prediction collection. High correlation coefficient (r=0.999) was achieved, which was better than PCA-SRA-ANN and PLS-ANN. It indicated that WT combined with ANN is an available method for variety discrimination based on the Vis/NIR spectroscopy technology. Some sensitive wave bands were also analyzed to develop tobacco varieties discrimination apparatus through PLS models.