猕猴桃硬度是判别其成熟度的关键指标,为了建立预测不同成熟期猕猴桃硬度的最优模型,采用光纤光谱(200~1 000 nm)采集系统获取不同成熟期"贵长"猕猴桃的反射光谱;基于全光谱数据分别构建了预测猕猴桃硬度的主成分回归(principal component regression,PCR)和偏最小二乘回归(partial least square regression,PLSR)模型;利用连续投影算法(successive projection algorithm,SPA)和竞争性自适应重加权算法(competitive adaptive reweighted sampling,CARS)提取特征波长,进而基于特征光谱构建了预测硬度的多元线性回归(multiple linear regression,MLR)模型。结果表明,采用CARS从1 024个全波段中提取了42个特征波长,不仅提升了预测模型的检测效率,而且建立的CARS-MLR模型具有最佳的校正性能和预测性能,其校正集决定系数R2C及其均方根误差(root mean square error of calibration,RMSEC)分别为0.91和1.27 kg/cm2,预测集决定系数R2P及其均方根误差(root mean square error of prediction,RMSEP)分别为0.85和1.57 kg/cm2,剩余预测偏差(residual predictive deviation,RPD)为2.64。结果表明,这说明基于光纤光谱技术预测猕猴桃硬度是可行的,CARS-MLR模型最佳。
The optical fiber spectroscopy (200-1 000 nm) acquisition system was used to collect reflectance spectra.And the principal component regression (PCR) and partial least square regression (PLSR) model were established which based on full spectra to predict the firmness of kiwifruit.Moreover,the successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to select characteristic wavelengths,respectively.Then the multiple linear regression (MLR) model was established based on selected characteristic spectra to predict the firmness.The results showed that 42 characteristic wavelengths extracted by CARS from 1 024 full wavelengths for the prediction of the firmness,and the working efficiency was obviously improved.Furthermore,CARS-MLR model had the best calibration ability (R2C=0.91,RMSEC=1.27 kg/cm2) and prediction ability (R2P=0.85,RMSEP=1.57 kg/cm2,RPD=2.64).Therefore,it's feasible to detect the firmness of kiwifruit by optical fiber spectroscopy and the CARS-MLR model was better.
[1] 张承,李明,龙友华,等.采前喷施壳聚糖复合膜对猕猴桃软腐病的防控及其保鲜作用[J].食品科学,2016,37(22):274-281.
[2] 孟庆龙,张艳,尚静.高光谱成像结合BP网络无损检测李子的硬度[J].激光与红外,2019,49(8):968-973.
[3] 王芹志,强锋,何建国,等.基于可见-近红外光谱预测灵武长枣脆度及模型优化[J].食品与发酵工业,2017,43(3):205-211.
[4] LI X L,WEI Y Z,XU J,et al.SSC and pH for sweet assessment and maturity classification of harvested cherry fruit based on NIR hyperspectral imaging technology[J].Postharvest Biology and Technology,2018,143:112-118.
[5] MA T,LI X Z,INAGAKI T,et al.Noncontact evaluation of soluble solids content in apples by near-infrared hyperspectral imaging[J].Journal of Food Engineering,2018,224:53-61.
[6] ZHANG D Y,XU L,WANG Q Y,et al.The optimal local model selection for robust and fast evaluation of soluble solid content in melon with thick peel and large size by VIS-NIR spectroscopy[J].Food Analytical Methods,2019,12(1):136-147.
[7] FAN S X,ZHANG B H,LI J B,et al.Prediction of soluble solids content of apple using the combination of spectra and textural features of hyperspectral reflectance imaging data[J].Postharvest Biology and Technology,2016,121:51-61.
[8] 邵园园,王永贤,玄冠涛,等.高光谱成像快速检测壳聚糖涂膜草莓可溶性固形物[J].农业工程学报,2019,35(18):245-254.
[9] XIE C Q,CHU B Q,HE Y.Prediction of banana color and firmness using a novel wavelengths selection method of hyperspectral imaging[J].Food Chemistry,2018,245:132-140.
[10] 孙炳新,匡立学,徐方旭,等.苹果脆度的近红外无损检测[J].食品与发酵工业,2013,39(5):185-189.
[11] 郭文川,董金磊.高光谱成像结合人工神经网络无损检测桃的硬度[J].光学精密工程,2015,23(6):1 530-1537.
[12] LI B,COBO-MEDINA M,LECOURT J,et al.Application of hyperspectral imaging for nondestructive measurement of plum quality attributes[J].Postharvest Biology and Technology,2018,141:8-15.
[13] FAN S X,HUANG W Q,GUO Z M,et al.Prediction of soluble solids content and firmness of pears using hyperspectral reflectance imaging[J].Food Analytical Methods,2015,8(8):1 936-1 946.
[14] YU X J,LU H D,WU D.Development of deep learning method for predicting firmness and soluble solid content of postharvest korla fragrant pear using VIS/NIR hyperspectral reflectance imaging[J].Postharvest Biology and Technology,2018,141:39-49.
[15] LEIVA-VALENZUELA G A,LU R F,AGUILERA J M.Prediction of firmness and soluble solids content of blueberries using hyperspectral reflectance imaging[J].Journal of Food Engineering,2013,115(1):91-98.
[16] 邵园园,王永贤,玄冠涛,等.高光谱成像的猕猴桃货架期快速预测[J].光谱学与光谱分析,2020,40(6):1 940-1 946.
[17] HU W H,SUN D W,BLASCO J.Rapid monitoring 1-MCP-induced modulation of sugars accumulation in ripening ‘Hayward’ kiwifruit by Vis/NIR hyperspectral imaging[J].Postharvest Biology and Technology,2017,125:168-180.
[18] 尚静,孟庆龙,张艳.基于紫外/可见光谱技术的李子硬度无损检测[J].包装工程,2020,41(3):51-56.
[19] NICOLAÏB M,BEULLENS K,BOBELYN E,et al.Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy:A review[J].Postharvest Biology and Technology,2007,46(2):99-118.
[20] GALVÃO R K H,ARAUJO M C U,JOSÉG E,et al.A method for calibration and validation subset partitioning[J].Talanta,2005,67(4):736-740.
