Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy
Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy
复制标题
使用成像光谱技术对日本海鲜产品的热处理进行无创传感
DOI：
10.1111/ijfs.12863
复制
发表时间：
2015
影响因子：
3.3
通讯作者：
S.
中科院分区：
文献类型：
--
作者：
ElMasry;G.;Nakauchi;S.
研究了成像光谱法用于非接触式热处理传感的潜力。将样品在100、120、140、160、180和200 ° C下热处理至45、50、55、60、65、70、75和80 ° C的核心温度，然后迅速冷却并在900 - 2500 nm的短波近红外光谱范围内成像。使用整个光谱范围以及使用最重要的波长开发了偏最小二乘（PLS）回归模型，以预测核心温度（TC）和热历史（TH），分别产生合理的精度水平（= 0.86和RMSEP = 3.9 ° C）和（= 0.83和RMSEP = 0.29分钟）。此外，开发了逐步线性判别分析（LDA）模型，用于识别核心温度达到65 ° C阈值的样品。LDA模型在校准集和验证集的总体分类准确率为93.75%。然后以像素方式应用所产生的判别函数来产生可理解的分类图，以高精度展示样本之间的差异。
The potential of imaging spectroscopy for noncontact sensing of thermal treatments experienced on Japanesekamabokowas investigated. Samples were thermally treated at 100, 120, 140, 160, 180 and 200 °C to core temperatures of 45, 50, 55, 60, 65, 70, 75 and 80 °C and then promptly cooled and imaged in the short-wave near infrared spectral range of 900–2500 nm. Partial least square (PLS) regression models were developed using the whole spectral range as well as using the most important wavelengths to predict the core temperature (TC) and thermal history (TH) yielding a reasonable level of accuracy of (= 0.86 and RMSEP = 3.9 °C) and (= 0.83 and RMSEP = 0.29 min), respectively. Moreover, a stepwise linear discriminant analysis (LDA) model was developed for identifying samples whose core temperatures reached a threshold of 65 °C. The LDA model yielded overall classification accuracy of 93.75% in both calibration and validation sets. The resulting discrimination function was then applied in a pixel-wise manner to produce understandable classification maps to exhibit the difference among samples with high accuracy.