欧亚国际

最近，科学家利用VideometerLab多光谱成像系统发表了题为Spectroscopy and imaging technologies coupled with machine learning for the assessment of the microbiological spoilage associated to ready-to-eat leafy vegetables的文章，这是该设备在此领域发表的系列文章之一。

光谱和成像技术结合机器学习评估即食叶菜的微生物腐败

摘要

基于Tsakanikas等人（2018）的新数据和以前使用的实验数据，本研究进行了传感器和机器学习方法的比较评估，用于评估即食叶菜类蔬菜（小菠菜和火箭）的微生物腐败。研究了采用了傅里叶变换红外光谱（FTIR）、近红外光谱（NIR）、可见光谱（VIS）和多光谱成像（MSI）方法。评估了两种数据分割方法和两种算法，即偏最小二乘回归和支持向量回归（SVR）。就小菠菜而言，当对随机选择的样品进行模型试验时，性能优于或类似于根据动态温度数据进行试验时获得的性能，这取决于应用的分析技术。这两种应用算法在大多数小菠菜案例中模型性能相似。至于芝麻菜，随机数据分割方法在几乎所有传感器/算法组合的情况下都表现出相当好的结果。此外，SVR算法导致FTIR、VIS和NIR传感器的模型性能显著或略好，这取决于数据划分方法。PLSR算法为MSI传感器提供了更好的模型。总的来说，小菠菜的微生物腐败通过主要通过来自可见光传感器的模型得到了更好的评估，而FTIR和MSI更适合用于芝麻菜。根据这项研究的结果，每种蔬菜都需要不同的传感器和计算分析应用，这表明没有一种分析方法/算法的单一组合可以成功地应用于所有食品和整个食品供应链。

不同的算法在小菠菜中模型性能相似

两种测试算法在芝麻菜上模型性能不同

经测试的数据分割方案对这两种蔬菜显示出不同的响应

测试传感器对这两种蔬菜的适用性不同

每种蔬菜都需要一个独特的数据分析工作流程

Spectroscopy and imaging technologies coupled with machine learning for the assessment of the microbiological spoilage associated to ready-to-eat leafy vegetables

Highlights

Different algorithms yielded similar model performances in baby spinach.

The two tested algorithms showed different model performances in rocket.

The tested data partition schemes showed different responses for the two vegetables.

The suitability of the tested sensors was different for the two vegetables.

A distinct data analysis workflow is needed for each vegetable type.

Abstract

Based on both new and previously utilized by Tsakanikas et al. (2018) experimental data, the present study provides a comparative assessment of sensors and machine learning approaches for evalsuating the microbiological spoilage of ready-to-eat leafy vegetables (baby spinach and rocket). Fourier-transform infrared (FTIR), near-infrared (NIR), visible (VIS) spectroscopy and multispectral imaging (MSI) were used. Two data partitioning approaches and two algorithms, namely partial least squares regression and support vector regression (SVR), were evalsuated. Concerning baby spinach, when model testing was performed on samples randomly selected, the performance was better than or similar to the one attained when testing was performed based on dynamic temperatures data, depending on the applied analytical technology. The two applied algorithms yielded similar model performances for the majority of baby spinach cases. Regarding rocket, the random data partitioning approach performed considerably better results in almost all cases of sensor/algorithm combination. Furthermore, SVR algorithm resulted in considerably or slightly better model performances for the FTIR, VIS and NIR sensors, depending on the data partitioning approach. However, PLSR algorithm provided better models for the MSI sensor. Overall, the microbiological spoilage of baby spinach was better assessed by models derived mainly from the VIS sensor, while FTIR and MSI were more suitable in rocket. According to the findings of this study, a distinct sensor and computational analysis application is needed for each vegetable type, suggesting that there is not a single combination of analytical approach/algorithm that could be applied successfully in all food products and throughout the food supply chain.