Abstract:Visible and near-infrared reflectance spectroscopy (NIRS) was applied in the discrimination of bayberry juice varieties. Characteristics of the pattern were analyzed by partial least square. Through full cross validation, nine principal components presenting important information of spectra were confirmed as the best number of principal components. Then, these nine principal components were taken as the input of BP neural network. Through the training and prediction, three different varieties of bayberry juice were classified according to the outputs of BP neural network. Besides, the work on building mathematic model and optimizing the algorithm was completed. In the process of BP neural network modeling, 60 samples were gained from the local market and each species has 20 samples. Fifty one samples were used as the training set and the reminder samples (total 9 samples) formed the prediction set. With a proper network training parameter, a 100% accuracy was obtained by BP neural network. Thus, it is concluded that PLS analysis combined with BP neural network is an available alternative for pattern recognition based on the spectroscopy technology.
Key words:Partial least square;BP neural network;Pattern recognition;Bayberry juice;Spectroscopy technology
岑海燕,鲍一丹*,何勇. 基于光谱技术的杨梅汁品种快速鉴别方法的研究[J]. 光谱学与光谱分析, 2007, 27(03): 503-506.
CEN Hai-yan, BAO Yi-dan*,HE Yong. Fast Discrimination of Varieties of Bayberry Juice Based on Spectroscopy Technology. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(03): 503-506.
[1] Zhang Wang-shu, Chen Kun-song, Zhang Bo, et al. Postharvest Biology and Technology, 2005, 37: 241. [2] He Yong, Li Xiao-li, Shao Yong-ni. Lecture Notes in Computer Science, 2005, 3809: 1053. [3] TANG Yan-feng, ZHANG Zhuo-yong, FAN Guo-qiang(汤彦丰,张卓勇,范国强). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2005, 25(4): 521. [4] LIU Shu-hua, ZHANG Xue-gong, ZHOU Qun, et al(刘沭华,张学工,周 群, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2005, 25(6): 878. [5] HE Yong, FENG Shui-juan, LI Xiao-li, et al(何 勇,冯水娟,李晓丽,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(11):2021. [6] Cheng J, Liu QS, Lu H Q, et al. Pattern Recognition, 2006, 39: 81. [7] Haykin S. Neural Network-A Comprehensive Foundation, 1994, 1: 44. [8] He Yong, Song Hai-yan, Pereira A G, et al. Lecture Notes in Computer Science, 2005, 3644: 859. [9] TANG Qi-yi, FENG Ming-guang(唐启义,冯明光). DPS Data Processing System for Practical Statistics(实用统计分析及其DPS数据处理系统). Beijing: Science Press(北京:科学出版社),2002. [10] LU Wan-zhen, YUAN Hong-fu, XU Guang-tong, et al(陆婉珍,袁洪福,徐广通,等). Modern Near-Infrared Spectroscopy Analysis Technology(现代近红外光谱分析技术), 2000, 167.