可见-近红外光谱用于鲜食葡萄感官偏好的检测

水果内部品质影响着消费者的感官偏好，直接决定消费者的购买倾向。为此，可见-近红外光谱技术检测巨峰葡萄内部品质以及感官偏好等级。试验比较了漫反射、透射两种光谱采集方式对葡萄内部品质的检测准确性，结果表明透射光谱更能表征巨峰葡萄的内部品质信息，偏最小二乘(PLS)模型对鲜食葡萄可溶性固形物、总酸度的预测均方根误差分别为0.598%brix，0.048 g·L-1。将鲜食葡萄的透射光谱主成分信息与消费者的感官偏好等级之间建立非线性分类模型，得到主成分法结合极限学习机(PCA-ELM)模型分类准确率最好，为78.7%。结果认为反映水果内部信息的光谱可用于消费者感官偏好的初步分类，但其间关系还有待进一步研究。

Inspection of the Sensory Preference for Table Grape with Visual-Near Infrared Spectroscopy

The sensory preference of consumer was influenced by the internal qualities of f ruit,which directly determined the tendency of consumer's purchase.The visu al-near infrared spectroscopy was employed to inspect the internal qualities of"kyoho" table grape and the grade of the sensory preference,aiming to provide the fruit with superior qualities for consumers.Spectra in diffuse r eflection and transmission acquisition mode were comparatively conducted to meas ure the internal qualities of table grape.Results show that the transmission sp ectra had a better capacity to characterize the internal information of grape be rries,and the partial least square (PLS) model was optimized to measure sugar c ontent (SC) and total acidity (TA) with root mean square error of prediction (RM SEP) of 0.598％brix,0.048 g·L-1 respectively.Three nonlinear classifi cation methods were comparatively investigated between the sensory preference of customers and the principal component of transmittance spectra of table grape,and the extreme learning machine combined with principal component analysis (PCA-ELM) model obtained the best performance with the classification accuracy of 78.7％.It was concluded that spectra characterized the internal information of f ruit could be used to preliminarily grade the sensory preference of consumers,h owever,the relationship between them requires further study.