Caffeine is an important component that determines the quality of tea, and its rapid estimation is very much needed for the industry. In this pursuit, a near‐infrared (NIR) spectroscopy‐based technique for the estimation of caffeine is developed and presented in this paper. On the basis of responses of the different bonds present in caffeine, four specific wavelength windows—(a) 1075 to 1239.5 nm (C―H stretch second overtone); (b) 1339.25 to 1440.75 nm (C―H stretch and C―H deformation); (c) 1640.25 to 1700 nm (C―H stretch first overtone, ═CH & amp; ―CH3 asymmetric); and (d) 900 to 1700 nm (whole range of the spectrometer)—were analyzed in details for model development and to obtain the effective wavelength (EW). Five different preprocessing techniques followed by two regression techniques—(a) the partial least‐squares (PLS) and (b) the support vector regression (SVR) were implemented on raw data for analysis. Comparing all the models, the wavelength band of 1075 to 1239.5 nm and 1339.25 to 1440.75 nm were found to produce satisfactory results. The best discrimination result was obtained using the combination of standard normal variate (SNV) preprocessing with SVR at the 1075 to 1239.5 nm wavelength region. The SVR regression with 105 samples in the training set and 15 samples in the testing set resulted in the performance parameters as RMSECV = 0.134, RMSEP = 0.069, rcv2 = 0.869, rp2 = 0.65, and RPD = 5.626 at 1075 to 1239.5 nm, whereas the PLS model produced the best RMSECV = 0.287, RMSEP = 0.077, rcv2 = 0.637, rp2 = 0.675, and RPD = 5.218 at 1339.25 to 1440.75‐nm wavelength band.

中文翻译：

---

支持向量机回归选定波长区域的近红外光谱定量分析茶叶中的咖啡因

咖啡因是决定茶叶品质的重要成分，业界非常需要对其进行快速估算。为此，本文开发并介绍了一种基于近红外 (NIR) 光谱的咖啡因估计技术。根据咖啡因中不同键的响应，四个特定的波长窗口——(a) 1075 到 1239.5 nm（C-H 拉伸第二泛音）；(b) 1339.25 至 1440.75 nm（C-H 拉伸和 C-H 变形）；(c) 1640.25 至 1700 nm（C-H 拉伸第一泛音，=CH & amp; -CH3 不对称）；(d) 900 到 1700 nm（光谱仪的整个范围）——详细分析了模型开发和获得有效波长 (EW)。五种不同的预处理技术，然后是两种回归技术——（a）偏最小二乘法（PLS）和（b）支持向量回归（SVR）对原始数据进行分析。比较所有模型，发现 1075 至 1239.5 nm 和 1339.25 至 1440.75 nm 的波段产生了令人满意的结果。使用标准正态变量 (SNV) 预处理与 SVR 在 1075 至 1239.5 nm 波长区域的组合获得最佳区分结果。训练集中 105 个样本和测试集中 15 个样本的 SVR 回归导致性能参数为 RMSECV = 0.134、RMSEP = 0.069、rcv2 = 0.869、rp2 = 0.65 和 RPD = 5.626 在 1075 到 1239.5 nm 处。 PLS 模型在 1339 处产生了最好的 RMSECV = 0.287、RMSEP = 0.077、rcv2 = 0.637、rp2 = 0.675 和 RPD = 5.218。