Mishra Puneet, Marini Federico, Brouwer Bastiaan, Roger Jean Michel, Biancolillo Alessandra, Woltering Ernst, Echtelt Esther Hogeveen-van
Wageningen Food and Biobased Research, Bornse Weilanden 9, P.O. Box 17, 6700AA, Wageningen, the Netherlands.
Department of Chemistry, University of Rome "La Sapienza", Piazzale Aldo Moro 5, 00185, Rome, Italy.
Talanta. 2021 Feb 1;223(Pt 2):121733. doi: 10.1016/j.talanta.2020.121733. Epub 2020 Oct 13.
Near infrared (NIR) spectroscopy allows rapid estimation of quality traits in fresh fruit. Several portable spectrometers are available in the market as a low-cost solution to perform NIR spectroscopy. However, portable spectrometers, being lower in cost than a benchtop counterpart, do not cover the complete near infrared (NIR) spectral range. Often portable sensors either use silicon-based visible and NIR detector to cover 400-1000 nm, or InGaAs-based short wave infrared (SWIR) detector covering the 900-1700 nm. However, these two spectral regions carry complementary information, since the 400-1000 nm interval captures the color and 3rd overtones of most functional group vibrations, while the 1st and the 2nd overtones of the same transitions fall in the 1000-1700 nm range. To exploit such complementarity, sequential data fusion strategies were used to fuse the data from two portable spectrometers, i.e., Felix F750 (400-1000 nm) and the DLP NIR Scan Nano (900-1700 nm). In particular, two different sequential fusion approaches were used, namely sequential orthogonalized partial-least squares (SO-PLS) regression and sequential orthogonalized covariate selection (SO-CovSel). SO-PLS improved the prediction of moisture content (MC) and soluble solids content (SSC) in pear fruit, leading to an accuracy which was not obtainable with models built on any of the two spectral data set individually. Instead, SO-CovSel was used to select the key wavelengths from both the spectral ranges mostly correlated to quality parameters of pear fruit. Sequential fusion of the data from the two portable spectrometers led to an improved model prediction (higher R and lower RMSEP) of MC and SSC in pear fruit: compared to the models built with the DLP NIR Scan Nano (the worst individual block) where SO-PLS showed an increase in R up to 56% and a corresponding 47% decrease in RMSEP. Differences were less pronounced to the use of Felix data alone, but still the R was increased by 2.5% and the RMSEP was reduced by 6.5%. Sequential data fusion is not limited to NIR data but it can be considered as a general tool for integrating information from multiple sensors.
近红外（NIR）光谱法可快速估算新鲜水果的品质特征。市场上有几种便携式光谱仪作为执行近红外光谱分析的低成本解决方案。然而，便携式光谱仪成本低于台式光谱仪，无法覆盖完整的近红外（NIR）光谱范围。便携式传感器通常要么使用基于硅的可见和近红外探测器来覆盖400 - 1000纳米，要么使用基于铟镓砷的短波红外（SWIR）探测器覆盖900 - 1700纳米。然而，这两个光谱区域携带互补信息，因为400 - 1000纳米区间捕捉了大多数官能团振动的颜色和第三泛音，而相同跃迁的第一和第二泛音落在1000 - 1700纳米范围内。为了利用这种互补性，采用顺序数据融合策略来融合来自两台便携式光谱仪的数据，即Felix F750（约400 - 1000纳米）和DLP NIR Scan Nano（约900 - 1700纳米）。具体而言，使用了两种不同的顺序融合方法，即顺序正交化偏最小二乘法（SO - PLS）回归和顺序正交化协变量选择（SO - CovSel）。SO - PLS改进了梨果实中水分含量（MC）和可溶性固形物含量（SSC）的预测，得到了单独基于两个光谱数据集之一建立的模型无法获得的准确度。相反，SO - CovSel用于从两个光谱范围中选择与梨果实品质参数最相关的关键波长。来自两台便携式光谱仪的数据顺序融合导致梨果实中MC和SSC的模型预测得到改善（更高的R和更低的RMSEP）：与使用DLP NIR Scan Nano（最差的单个模块）建立的模型相比，SO - PLS显示R增加高达56%，RMSEP相应降低47%。与单独使用Felix数据相比，差异不太明显，但R仍增加了2.5%，RMSEP降低了6.5%。顺序数据融合不仅限于近红外数据，它可被视为整合来自多个传感器信息的通用工具。
