Abstract：
Pomegranate molasses is made from concentrated pomegranate juice with nothing added. Due to its nutritional value, limitation in production, and high production cost, this product may be adulterated by date syrup. This study was done to differentiate various types of pomegranate molasses and investigate the possibility of nonauthenticity detection in pomegranate molasses samples using the hyperspectral imaging (HSI) technique compared with physicochemical measurement analysis. The physicochemical properties (brix index, sucrose, acidity, ash content, pH, and formalin index) of 24 samples were measured as the reference analysis method, and it was found that the formalin index was a good factor for pomegranate molasses authenticity evaluation. Additionally, an HSI system (400-1000 nm) was used as a nondestructive and rapid screening method to capture spectral data of the samples. The evolutionary wavelength selection algorithm was applied to select effective wavelengths in sample clustering based on the obtained Davies-Bouldin index. Next, principal component analysis was used to visually interpret the spectral data of the sample when using the selected wavelengths and the whole spectra of the samples. Finally, an automatic clustering algorithm by the artificial bee colony as an unsupervised method was developed for the clustering of the authentic and nonauthentic samples. The method did not need descriptively labeled samples and obtained agreed satisfactorily with the degree of nonauthenticity in the samples. This study showed that the developed HSI technique coupled with an automatic clustering algorithm could detect date syrup nonauthenticity in pomegranate samples from the level of 5% adulteration.
摘要：
石榴糖蜜由浓缩石榴汁制成，不加任何东西。由于其营养价值，限制生产，生产成本高，本产品可能掺有椰枣糖浆。这项研究旨在区分各种类型的石榴糖蜜，并研究使用高光谱成像（HSI）技术与物理化学测量分析相比，对石榴糖蜜样品进行非真实性检测的可能性。物理化学性质(白利糖度指数，蔗糖,酸度,灰分含量,pH值,和福尔马林指数)的24个样品作为参考分析方法进行测量，结果表明，福尔马林指数是石榴糖蜜真伪评价的良好因子。此外,使用HSI系统（400-1000nm）作为非破坏性和快速筛选方法来捕获样品的光谱数据。基于获得的Davies-Bouldin指数，应用进化波长选择算法选择样本聚类中的有效波长。接下来,当使用选定的波长和样品的整个光谱时，主成分分析用于直观地解释样品的光谱数据。最后,开发了一种由人工蜂群作为无监督方法的自动聚类算法，用于对真实和非真实样本进行聚类。该方法不需要描述性标记的样品，并且获得的样品的非真实性程度令人满意。这项研究表明，开发的HSI技术与自动聚类算法相结合，可以从5％掺假的水平检测石榴样品中的日期糖浆不真实性。
