%0 Journal Article %A MENG Qinglong %A SHANG Jing %A HUANG Renshuai %A CHEN Lutao %A ZHANG Yan %T Nondestructive detection of soluble solids content in apple by visible-near infrared spectroscopy %D %R 10.13995/j.cnki.11-1802/ts.023710 %J Food and Fermentation Industries %P 205-209 %V 46 %N 19 %X A model of predicting soluble solids content (SSC) of apple by visible-near infrared (Vis/NIR) spectroscopy was established and optimized. The hyperspectral images of 120 “Fuji” apples over 400-1 000 nm were obtained by hyperspectral imaging acquisition system. The effectiveness of the prediction model with pretreatment by second derivative, standard normal variation and multi-scatter calibration was compared and evaluated. Then the successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS) methods were used to conduct data mining. Moreover, BP model and multiple linear regression(MLR) model were established based on characteristic spectra. The results showed that BP model with pretreatment by SD was superior to full spectra and other spectral pretreatments. And SPA-BP model based on characteristic spectra had an excellent prediction ability. The correlation coefficient rp and root mean square error of prediction (RMSEP) were 0.87 and 0.52, respectively. These results indicated that it's feasible to determine SSC of apples by Vis/NIR spectroscopy. %U http://sf1970.cnif.cn/EN/10.13995/j.cnki.11-1802/ts.023710