来自中国农业大学的科学家利用VideometerLab多光谱成像系统，发表了题为“Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning”的文章，文章发表于期刊Sensors (Basel). 2022 Oct; 22(19): 7521。 

基于多光谱成像和叠加集成学习的三种苜蓿单种子鉴定

摘要

多光谱成像（MSI）已成为种子鉴定中一种新的快速无损检测方法。以往的研究通常集中于MSI数据分析中的单一模型，该模型总是采用所有特征，并增加了效率风险和系统成本风险。在本研究中，我们开发了一个堆叠集成学习（SEL）模型，用于成功识别镰刀苜蓿（Medicago falcata）、杂交苜蓿和紫花苜蓿的单个种子。SEL采用三层结构，即0级，以主成分分析（PCA）、线性判别分析（LDA）和二次判别分析（QDA）作为降维和特征提取（DRFE）模型；1级，支持向量机（SVM）、多元逻辑回归（MLR）、具有弹性网正则化的广义线性模型（GLMNET）和极限梯度增强（XGBoost）作为基础学习级；三级，XGBoost作为元学习者。研究确认，基于光谱特征以及形态学和光谱特征的组合，SEL模型的总体准确度、kappa、精密度、敏感性、特异性和敏感性值均显著高于单独的基本模型。此外，我们还开发了特征过滤过程，并成功地从33个特征中选择了5个最佳特征，这些特征对应于种子中叶绿素、花青素、脂肪和水分的含量。在MSI数据分析中的SEL模型为种子识别提供了一种新的方法，并且特征滤波过程可能广泛用于低成本和窄通道传感器的开发。 

关键词：镰刀苜蓿、杂交苜蓿和紫花苜蓿、种子识别、叠加集成学习、多光谱成像

Sensors (Basel). 2022 Oct; 22(19): 7521. 

Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning

Zhicheng Jia, Ming Sun, Chengming Ou, Shoujiang Sun, Chunli Mao, Liu Hong, Juan Wang, Manli Li, Shangang Jia, and Peisheng Mao* 

Abstract

Multispectral imaging (MSI) has become a new fast and non-destructive detection method in seed identification. Previous research has usually focused on single models in MSI data analysis, which always employed all features and increased the risk to efficiency and that of system cost. In this study, we developed a stacking ensemble learning (SEL) model for successfully identifying a single seed of sickle alfalfa (Medicago falcata), hybrid alfalfa (M. varia), and alfalfa (M. sativa). SEL adopted a three-layer structure, i.e., level 0 with principal component analysis (PCA), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) as models of dimensionality reduction and feature extraction (DRFE); level 1 with support vector machine (SVM), multiple logistic regression (MLR), generalized linear models with elastic net regularization (GLMNET), and eXtreme Gradient Boosting (XGBoost) as basic learners; and level 3 with XGBoost as meta-learner. We confirmed that the values of overall accuracy, kappa, precision, sensitivity, specificity, and sensitivity in the SEL model were all significantly higher than those in basic models alone, based on both spectral features and a combination of morphological and spectral features. Furthermore, we also developed a feature filtering process and successfully selected 5 optimal features out of 33 ones, which corresponded to the contents of chlorophyll, anthocyanin, fat, and moisture in seeds. Our SEL model in MSI data analysis provided a new way for seed identification, and the feature filter process potentially could be used widely for development of a low-cost and narrow-channel sensor. 

Keywords: M. falcata, M. varia, M. sativa, seed identification, stacking ensemble learning, multispectral imaging