Models fused with successive CARS-PLS for measurement of the soluble solids content of Chinese bayberry by vis-NIRS technology

Yuan, Lei; Mao, Fei; Huang, Guangzao; Chen, Xiaojing; Wu, Di; Li, Shaojia; Zhou, Xinqi; Jiang, Qiaojun; Lin, Dingpeng; He, Ruyi

doi:10.1016/j.postharvbio.2020.111308

Cited by 36 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the chromaticity frequency sequence extracted from each chromaticity of each dried Hami jujube image is a 256-dimensional vector, variable information that is highly related to the moisture content of the dried Hami jujube can be filtered out, thereby simplifying the model, and improving the operation of the model effectiveness. Here, CARS method (Huang et al 2020;Yuan et al 2020) is used to optimise the feature variables in the chrominance frequency sequence of 150 Hami jujube images.…”

Section: Models and Methodsmentioning

confidence: 99%

Moisture content assessment of dried Hami jujube using image colour analysis

Ma¹,

Li²,

Li³

et al. 2022

Czech J. Food Sci.

View full text Add to dashboard Cite

To investigate the feasibility of image colour information in predicting the moisture content of dried Hami jujube, the images were obtained under different colour space models, and the colour model component mean and chromaticity frequency sequences of R, G, B, H, S, V, L*, a* and b* were extracted through image analysis. After optimising the colour model component mean and chromaticity frequency sequence, the model was established and compared. The results showed that the GA-ELM (genetic algorithm - extreme learning machine) model established by CARS (competitive adaptive reweighted sampling) method to optimise 12 chromaticity features of S chromaticity frequency sequence had the best prediction effect, with R<sub>c</sub> of 0.917, R<sub>p</sub> of 0.934 and residual predictive deviation (RPD) of 2.507. Therefore, the colour image information can accurately predict the moisture content of dried Hami jujube.

show abstract

Section: Models and Methodsmentioning

confidence: 99%

Moisture content assessment of dried Hami jujube using image colour analysis

Ma¹,

Li²,

Li³

et al. 2022

Czech J. Food Sci.

View full text Add to dashboard Cite

show abstract

“…The edible parts (pulp) of the berries were washed with deionised water, blended in a juicer and filtered through a 400-mesh filter cloth. The soluble solids content (SSC) in the Chinese bayberry juice was measured using a pocket refractometer (ATAGO Co., Ltd., Tokyo, Japan) with an accuracy of 0.001 Brix ( Yuan et al, 2020 ). The titratable acidity content (TAC) of Chinese bayberry juice samples was titrated by adding 1.0M sodium hydroxide (NaOH) and phenolphthalein ( Lobit et al, 2002 ).…”

Section: Methodsmentioning

confidence: 99%

An Insect- and Rain-Proof Net Raises the Production and Quality of Chinese Bayberry by Preventing Damage From Insects and Altering Bacterial Communities

Tian

Huang³

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

Chinese bayberry (Myrica rubra) is a popular, nutrient- and antioxidant-rich fruit in Asia. However, it is susceptible to Drosophila during ripening, which disrupts production and causes economic loss. This study compared the effects of insecticides, insect-proof nets (IPNs), and insect- and rain-proof nets (IRPNs) on Chinese bayberry production and quality. Drosophila was absent in fruits from IPN- or IRPN-treated trees but only significantly reduced by insecticides. IPNs and IRPNs significantly increased fruit diameter, weight, edible rate and the Brix/acid ratio, and IRPNs had the strongest effect. Analysis of 16S rDNA showed that fruits collected from differently treated trees had unique bacterial communities. In IRPN fruits, Acetobacter and Gluconobacter were significantly decreased, reducing sugar consumption and disease; in addition, PICRUSt analysis predicted imputed functional profiles related to carbohydrate and nitrogen metabolism and mineral transport for fruit growth and development. This study proposed the use of IRPNs for improving Chinese bayberry production and quality.

show abstract

“…The use of all data to construct a model is complex and time-consuming, while noise and unnecessary information also influence the accuracy and robustness of the model [37]. Currently, the methods of feature processing in machine learning are mainly divided into two types: feature dimensionality reduction and feature selection (include filtering, embedding, and wrapping method) [13]. In this paper, feature dimensionality reduction [20] and feature selection were performed respectively using Principal Component Analysis (PCA) [38], t-distributed stochastic neighbor embedding (t-SNE) [39,40], and random forest-recursive feature elimination (RF-RFE).…”

Section: Feature Selectionmentioning

confidence: 99%

“…NIRS [12], a molecular spectra, can comprehensively characterize structural information of the energy level from molecular vibration and reflect the frequency doubling and frequency absorption of hydrogen groups in organic compounds from the vibration of electric dipole moment [13]. Currently, NIRS has been extensively applied for monitoring and classifying tea [14].…”

Section: Introductionmentioning

confidence: 99%

Reliable Identification of Oolong Tea Species: Nondestructive Testing Classification Based on Fluorescence Hyperspectral Technology and Machine Learning

Huang

et al. 2021

Agriculture

View full text Add to dashboard Cite

A rapid and nondestructive tea classification method is of great significance in today’s research. This study uses fluorescence hyperspectral technology and machine learning to distinguish Oolong tea by analyzing the spectral features of tea in the wavelength ranging from 475 to 1100 nm. The spectral data are preprocessed by multivariate scattering correction (MSC) and standard normal variable (SNV), which can effectively reduce the impact of baseline drift and tilt. Then principal component analysis (PCA) and t-distribution random neighborhood embedding (t-SNE) are adopted for feature dimensionality reduction and visual display. Random Forest-Recursive Feature Elimination (RF-RFE) is used for feature selection. Decision Tree (DT), Random Forest Classification (RFC), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are used to establish the classification model. The results show that MSC-RF-RFE-SVM is the best model for the classification of Oolong tea in which the accuracy of the training set and test set is 100% and 98.73%, respectively. It can be concluded that fluorescence hyperspectral technology and machine learning are feasible to classify Oolong tea.

show abstract

Models fused with successive CARS-PLS for measurement of the soluble solids content of Chinese bayberry by vis-NIRS technology

Cited by 36 publications

References 29 publications

Moisture content assessment of dried Hami jujube using image colour analysis

Moisture content assessment of dried Hami jujube using image colour analysis

An Insect- and Rain-Proof Net Raises the Production and Quality of Chinese Bayberry by Preventing Damage From Insects and Altering Bacterial Communities

Reliable Identification of Oolong Tea Species: Nondestructive Testing Classification Based on Fluorescence Hyperspectral Technology and Machine Learning

Contact Info

Product

Resources

About