Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, Republic of Korea.
Department of Chemistry and Research Institute for Convergence of Basic Science, Hanyang University, Seoul 04763, Republic of Korea.
Food Chem. 2020 Nov 30;331:127332. doi: 10.1016/j.foodchem.2020.127332. Epub 2020 Jun 14.
The utility of an autoencoder (AE) as a feature extraction tool for near-infrared (NIR) spectroscopy-based discrimination analysis has been explored and the discrimination of the geographic origins of 8 different agricultural products has been performed as the case study. The sample spectral features were broad and insufficient for component distinction due to considerable overlap of individual bands, so AE enabling of extracting the sample-descriptive features in the spectra would help to improve discrimination accuracy. For comparison, four different inputs of AE-extracted features, raw NIR spectra, principal component (PC) scores, and features extracted using locally linear embedding were employed for sample discrimination using support vector machine. The use of AE-extracted feature improved the accuracy in the discrimination of samples in all 8 products. The improvement was more substantial when the sample spectral features were indistinct. It demonstrates that AE is expandable for vibrational spectroscopic discriminant analysis of other samples with complex composition.
自动编码器（AE）作为基于近红外（NIR）光谱的判别分析的特征提取工具的效用已经得到了探索，并将其用于判别 8 种不同农产品的地理起源，作为案例研究。由于个别波段的大量重叠，样品光谱特征较宽且不足以进行成分区分，因此 AE 能够提取光谱中的样本描述特征将有助于提高判别精度。为了进行比较，使用支持向量机分别使用 AE 提取的特征、原始近红外光谱、主成分（PC）得分以及使用局部线性嵌入提取的特征作为四个不同的输入，对样本进行判别。在所有 8 种产品中，使用 AE 提取的特征均提高了样本判别的准确性。当样品光谱特征不明显时，改进更为显著。这表明 AE 可扩展用于其他具有复杂成分的振动光谱判别分析。
