摘要
应用可见/近红外光谱技术与感官评价信息融合实现冷藏条件下有鳞罗非鱼不同部位鱼肉挥发性盐基氮(TVB-N)的预测。通过便携式近红外光谱仪采集有鳞罗非鱼胸部、中部和尾部鱼肉在340~1063 nm的光谱数据,分别采用卷积平滑法、变量标准化、一阶(1st Der)和二阶(2nd Der)导数进行光谱预处理,利用连续投影算法(SPA)提取罗非鱼不同部位鱼肉的特征波长,建立鱼肉光谱与TVB-N偏最小二乘回归(PLSR)模型,结果表明尾部鱼肉的1st Der-SPA-PLSR模型预测均方根误差(RMSEP)=1.1295 mg/100 g,预测相关系数(Rp^2)=0.8998,预测结果高于其胸部和中部鱼肉模型,并稍高于尾部鱼肉全波段模型。因此,选择尾部鱼肉作为罗非鱼光谱采样区域。为进一步提高模型预测准确性,将尾部鱼肉特征光谱数据与感官评价进行信息融合。通过对比尾部鱼肉光谱、尾部鱼肉光谱与感官评价融合的SPA-PLSR、SPA-BP神经网络和SPA-偏最小二乘支持向量机(LS-SVM)模型,结果表明,尾部光谱和感官评价信息融合的SPA-LS-SVM模型预测结果为RMSEP=0.9701 mg/100 g,Rp^2=0.9255,能更准确预测罗非鱼冷藏条件下TVB-N变化。为冷藏过程中罗非鱼新鲜度预测方法提供了新的思路。
The information fusion of near infrared spectrum technology and sensory evaluation was applied to predict the freshness of different parts for tilapia with scales during chilled storage.Spectral signatures ofbreast, middle and tail region in the range of 340 ~ 1063 nm were extracted.Smoothing Savitzky- Golay （ SG ）, standard normal variate （ SNV ）, polynomial derivative filters（ 1 st Der and 2nd Der）were used for spectral pre-processing.Partial least square regression（PLSR） was used to correlate the whole wavelengths spectra with total volatile basic nitrogen （TVB-N ）.Optimal wavelengths of different tilapia positions were selected by successive projections algorithm （SPA） to develop new SPA- PLSR models, and the SPA- PI_SR predictive performances of tails position（ root mean square error of prediction（RMSEP） = 1.1295 mg/lO0 g, determination coefficient（ Rp=） =0.8998 ）was better than that of breast and middle region, and also better than whole wavelengths model of tails region.Therefore, tail region was selected as spectrum sampling area.In order to evaluate the comprehensively fish freshness and improve the accuracy of modei, spectral data and sensory evaluation were integrated for nondestructive measurement of freshness for tail region of tilapia based on PLSR, back- propagation artificial neural network （ BP- ANN ） and least squares support vector machines （ IS- SVM ）. Compared with single characteristic, information fusion of spectral data and sensory evaluation for LS-SVM had its superiority, which achieved accurate results with Rp2 of 0.9255, RMSEP of 0.9701 mg/100 g.This result indicated that information fusion by integrating spectral data and sensory evaluation could significantly improve the TVB-N prediction performance ,and it has tremendous potential in prediction of freshness in fish during chilled storage.
作者
史策
孙立涛
钱建平
韩帅
范蓓蕾
杨信廷
SHI Ce SUN Li-tao QIAN Jian-ping HAN Shuai FAN Bei-lei YANG Xin-ting(Beijing Research Center for Information Technology in Agriculture, Beijing 100097, China College of Electronic Information and Automation, Tianjin University of Science ＆ Technology,Tianjin 300222, China National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China National Engineering Laboratory for Agri-product Quality Traceabihty, Beijing 100097, China)
出处
《食品工业科技》
CAS
CSCD
北大核心
2017年第21期268-273,共6页
Science and Technology of Food Industry
基金
北京市自然科学基金项目(6174040)
北京市农林科学院青年科研基金(QNJJ201720)
国家重点研发计划(2016YFD0401205)
关键词
可见/近红外光谱技术
罗非鱼
新鲜度
预测模型
贮藏
信息融合
near infrm＇ed spectrum technology
tilapia
freshness
predictive model
storage
information fusion
