Application of spectroscopy in the recognition of different producing area of waxberry
暂无分享,去创建一个
This research is to use spectroscopy data to determine the producing area of sampled waxberries. which are very similar in sizes and textures and color. and also very similar in taste. So, it is hard to tell where is the producing area of the given waxberry. In this research, 30 samples were chosen from each of the 4 kinds of waxberries. The producing areas are XianJu CiXi Nmghai and Lishui all in Zhejiang province. Firstly, spectroscopy were taken down by ASD FieldSpec (Handheld type, its spectrum is between 325-1075nm resolution is 3.5nm), and then its acidity measured by PH meter and sugar content by saccharin-meter. The following data process shows that the spectroscopy can record the whole information of one sample. By using wavelet transform and PCA analysis. the sampled waxberry producing area were recognized with higher correction than using the two chemical indices. acidity and sugar content index. In the 30 samples. 100 were used to build model, and let other 20 to forecast. less than 3 samples were forecasted wrongly. The PCA statistics told us that the relativity between the acidity and sugar index vector to the PCA vector extracted from the spectroscopy is greater than 0.84. Due to the large standard variance in one sampled set. the using of chemical indices to classify is not satisfying. This research demonstrates that the different producing areas of waxberry have evident differences in spectroscopy, though it is hard to tell them out by using hand or mouth.
[1] Zhang Guo-sheng. Application of neural network in discrimination of DMMP infrared spectra , 2004 .
[2] Lv Hongfei,et al. FTIR Spectrum of Hypericum and Triadenum with Reference to Their Identification , 2004 .
[3] Li Wei,et al. Study on Choosing Mother Wavelet for Signal Singularity Detection Based on MATLAB , 2004 .