A Method of AppleS Storage Period Detection Using Sparse Principal Component Analysis Based on Near Infrared Spectroscopy

摘要：

　　Apple samples were investigated using near-infrared spectroscopy (NIRS).Combined with SPCA to analyze the near infrared spectral of apples, then extract features of apples organics absorption spectrum.The result shows that samples display absorption bands of molecular stretching vibrations in the 972-1001 nm region, which are ascribed to overtone vibrations of organic acids.Meanwhile, in the 1380-1422 nm region is related to water and carbohydrates.Make these spectra as the model input, and apple storage period identification model is established by SVM classification algorithm.The accuracy of the calibrating set and prediction set respectively were 96.25% and 95%.Experimental results showed the analytical spectral by SPCA can strengthen the interpretability of the model, minimize the modeling and improve the prediction accuracy.

关键词： Near-infrared Spectroscopy Sparse Principal Component Analysis apple storage period

作者: Jiao Liang Lin Min Huijun Liu Yongmei Huang

作者单位: College of Metrological Technology and Engineering, China Jiliang University, Hangzhou 310018,China

会议类型: 国际会议

会议名称: International Conference on Computational Science and Engineering Applications(CSEA2015)2015计算机科学与工程应用国际会议

会议地点: 三亚

会议语种:英文

页码: 695-700

在线出版日期: 2015-12-26（万方平台首次上网日期，不代表论文的发表时间）