Hyperspectral imaging coupled with multivariate methods for seed vitality estimation and forecast for Quercus variabilis

Pang, Lei; Wang, Jinghua; Men, Sen; Lei, Yan; Xiao, Jing

doi:10.1016/j.saa.2020.118888

Cited by 27 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most previous research has focused on the combination of a single ML model in MSI analysis [ 40 , 41 ]. In this study, a new SEL model, containing three-level models, was superior to all basic models according to the metrics of overall accuracy, kappa, sensitivity, specificity, and precision.…”

Section: Discussionmentioning

confidence: 99%

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

Jia

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Jia

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This study comparatively analyzed the nine kinds of spectral preprocessing methods including standard normal variate (SNV) correction, detrend (DET) correction, Savitzky–Golay (SG) smoothing correction, first derivative (1D), and their combinations. 15,16 Choose the most suitable pretreatment method according to the pretreatment effect. In particular, 1D eliminates baseline drift and rotation, thus separating the overlap of absorption peaks and achieving the elimination of background information.…”

Section: Methodsmentioning

confidence: 99%

Sugarbeet Seed Germination Prediction Using Hyperspectral Imaging Information Fusion

et al. 2023

View full text Add to dashboard Cite

Germination rate is important for seed selection and planting and quality. In this study, hyperspectral image technology integrated with germination tests was applied for feature association analysis and germination performance prediction of sugarbeet seeds. In this study, we proposed a nondestructive prediction method for sugarbeet seed germination. Sugarbeet seed was studied, and hyperspectral imaging (HIS) performed by binarization, morphology, and contour extraction was applied as a nondestructive and accurate technique to achieve single seed image segmentation. Comparative analysis of nine spectral pretreatment methods, SNV + 1D was used to process the average spectrum of sugarbeet seeds. Fourteen characteristic wavelengths were obtained by the Kullback–Leibler (KL) divergence, as the spectral characteristics of sugarbeet seeds. Principal component analysis (PCA) and material properties verified the validity of the extracted characteristic wavelengths. It was extracted of six image features of the hyperspectral image of a single seed obtained based on the gray-level co-occurrence matrix (GLCM). The spectral features, image features, and fusion features were used to establish partial least squares discriminant analysis (PLS-DA), CatBoost, and support vector machine radial-basis function (SVM-RBF) models respectively to predict the germination. The results showed that the prediction effect of fusion features was better than spectral features and image features. By comparing other models, the prediction results of the CatBoost model accuracy were up to 93.52%. The results indicated that, based on HSI and fusion features, the prediction of germinating sugarbeet seeds was more accurate and nondestructive.

show abstract

“…Використані нами спектроскопія відбиття у видимому діапазоні, колориметрія та флуоресценція розширюють методичну основу прижиттєвої діагностики адаптивних змін рослин і відповідають сучасному напряму дослідження функціонального стану та ідентифікації деревних культур із використанням комплексу неруйнівних спектральних методів (Pang et al, 2021).…”

Section: рис 2 диференційний спектр відбиття насіння Robinia Pseudoacacia L із техногенної зони відносно насіння з екологічно сприятливоїunclassified

Spectral parameters of Robinia pseudoacacia L. seeds in technogenic conditions of urban environment

Fedenko

2021

ean

View full text Add to dashboard Cite

Robinia pseudoacacia L. (black locust) is an invasive species with high activity in alien flora of Ukraine. Invasive potential of plants in unfavorable ecological conditions is due to the presence of adaptive mechanisms. One of the criteria for the invasive potential of foreign plants is considered to be seed productivity. For plants of black locust note a high level of seed productivity. However, it remains to be seen what factors ensure the formation of viable seeds in extreme environments. Among the factors that ensure the formation of viable plant seeds, note the barrier function of the seed coat relative to biotic and abiotic environmental factors. The physiological role of this protective barrier is realized due to the specific properties and component composition of the surface tissues of seeds. Among the metabolites with protective properties localized in the seed coat, consider proanthocyanidins (condensed tannins), which are formed during the biosynthesis of phenolic compounds. To objectively assess changes in the accumulation of proanthocyanidins in the seed coat, it is necessary to use non-destructive methods, because the isolation of these compounds destroys their native polymer structure. The influence of technogenic pollution of Dnipro city on the reflectance, colorimetric and fluorescent characteristics of Robinia pseudoacacia L. seeds is investigated in the work. Mature seeds of black locust were collected at monitoring sites in the Botanical Garden of Oles Honchar Dnipro National University (ecologically favorable zone) and at some points of linear roadside plantations of one of the main highways. It was found that the chronic effect of aerogenic pollutants on black locust plants caused an increased accumulation of proanthocyanidins in the seed coat, which may be due to changes in the biosynthesis of these compounds at the stage of oxidative polymerization of flavonoid subunits. Markers of this reaction of plants are the change of position and increase of intensity of maxima in the reflectance spectra of visible region, increase of value of dominant wavelength, decrease of conditional purity of color tone and colorimetric coefficients, increase of intensity of maxima in seed fluorescence spectra. The protective effect of these adaptive changes is associated with the strengthening of the barrier function of the seed coat to adverse environmental factors to maintain the viability of the seeds under the negative impact of technogenic pollution.

show abstract

Hyperspectral imaging coupled with multivariate methods for seed vitality estimation and forecast for Quercus variabilis

Cited by 27 publications

References 40 publications

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

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

Sugarbeet Seed Germination Prediction Using Hyperspectral Imaging Information Fusion

Spectral parameters of Robinia pseudoacacia L. seeds in technogenic conditions of urban environment

Contact Info

Product

Resources

About