Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy

Chen, Cunwu; Yan, Hui; Baoyu, Han

doi:10.1590/0102-695x20142413387

Cited by 18 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of 200 samples including five cultivars of Chrysanthemum were classified using a multispectral imaging system in [ 31 ]. To identify three kinds of white Chrysanthemum , a near infrared spectroscopy system was employed to collect the spectra of 139 samples and 92 spectra were selected as calibration set to build the identification model in [ 32 ]. In this study, a total of 11,038 samples of seven Chrysanthemum varieties were classified using hyperspectral imaging technology.…”

Section: Discussionmentioning

confidence: 99%

Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network

Zhang

Bai

et al. 2018

Molecules

View full text Add to dashboard Cite

Rapid and accurate discrimination of Chrysanthemum varieties is very important for producers, consumers and market regulators. The feasibility of using hyperspectral imaging combined with deep convolutional neural network (DCNN) algorithm to identify Chrysanthemum varieties was studied in this paper. Hyperspectral images in the spectral range of 874–1734 nm were collected for 11,038 samples of seven varieties. Principal component analysis (PCA) was introduced for qualitative analysis. Score images of the first five PCs were used to explore the differences between different varieties. Second derivative (2nd derivative) method was employed to select optimal wavelengths. Support vector machine (SVM), logistic regression (LR), and DCNN were used to construct discriminant models using full wavelengths and optimal wavelengths. The results showed that all models based on full wavelengths achieved better performance than those based on optimal wavelengths. DCNN based on full wavelengths obtained the best results with an accuracy close to 100% on both training set and testing set. This optimal model was utilized to visualize the classification results. The overall results indicated that hyperspectral imaging combined with DCNN was a very powerful tool for rapid and accurate discrimination of Chrysanthemum varieties. The proposed method exhibited important potential for developing an online Chrysanthemum evaluation system.

show abstract

Section: Discussionmentioning

confidence: 99%

Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network

Zhang

Bai

et al. 2018

Molecules

View full text Add to dashboard Cite

show abstract

“…For example, in some traditional Chinese medicines multi-origin phenomena always exist, meaning that they originate from more than one species and share the same Chinese name [7]. In order to overcome these obstacles, researchers have paid much attention on the multi-aspect and multi-level characterization of traditional Chinese medicines based on diverse techniques and methods [8,9,10,11].…”

Section: Introductionmentioning

confidence: 99%

A Multi-Level Strategy Based on Metabolic and Molecular Genetic Approaches for the Characterization of Different Coptis Medicines Using HPLC-UV and RAD-seq Techniques

Zhong

Shen

et al. 2018

Molecules

View full text Add to dashboard Cite

Coptis plants (Ranunculaceae) to have played an important role in the prevention and treatment human diseases in Chinese history. In this study, a multi-level strategy based on metabolic and molecular genetic methods was performed for the characterization of four Coptis herbs (C. chinensis, C. deltoidea, C. omeiensis and C. teeta) using high performance liquid chromatography-ultraviolet (HPLC-UV) and restriction site-associated DNA sequencing (RAD-seq) techniques. Protoberberine alkaloids including berberine, palmatine, coptisine, epiberberine, columbamine, jatrorrhizine, magnoflorine and groenlandicine in rhizomes were identified and determined based on the HPLC-UV method. Among them, berberine was demonstrated as the most abundant compound in these plants. RAD-seq was applied to discover single nucleotide polymorphisms (SNPs) data. A total of 44,747,016 reads were generated and 2,443,407 SNPs were identified in regarding to four plants. Additionally, with respect to complicated metabolic and SNP data, multivariable statistical methods of principal component analysis (PCA) and hierarchical cluster analysis (HCA) were successively applied to interpret the structure characteristics. The metabolic variation and genetic relationship among different Coptis plants were successfully illustrated based on data visualization. Summarily, this comprehensive strategy has been proven as a reliable and effective approach to characterize Coptis plants, which can provide additional information for their quality assessment.

show abstract

“…Based on growing regions and processing methods, the main domestic varieties of medicinal C. morifolium are divided into “Hang-ju,” “Bo-ju,” “Qi-ju,” “Gong-ju,” “Ji-ju,” “Chu-ju,” “Huai-ju,” and “Chuan-ju” (Shao et al, 2010 ; Zhao et al, 2013 ). In China, some regions have become important producing areas, such as Tongxiang (Zhejiang Province), Yancheng (Jiangsu Province); Wuzhi (Henan Province), Chuzhou, and Sexian (An'hui Province) (Shao et al, 2010 ; Wang T. et al, 2013 ; Chen et al, 2014 ).…”

Section: Introductionmentioning

confidence: 99%

Development of SSR Markers and Assessment of Genetic Diversity in Medicinal Chrysanthemum morifolium Cultivars

Feng

et al. 2016

Front. Genet.

View full text Add to dashboard Cite

Chrysanthemum morifolium, is a well-known flowering plant worldwide, and has a high commercial, floricultural, and medicinal value. In this study, simple-sequence repeat (SSR) markers were generated from EST datasets and were applied to assess the genetic diversity among 32 cultivars. A total of 218 in silico SSR loci were identified from 7300 C. morifolium ESTs retrieved from GenBank. Of all SSR loci, 61.47% of them (134) were hexa-nucleotide repeats, followed by tri-nucleotide repeats (17.89%), di-nucleotide repeats (12.39%), tetra-nucleotide repeats (4.13%), and penta-nucleotide repeats (4.13%). In this study, 17 novel EST-SSR markers were verified. Along with 38 SSR markers reported previously, 55 C. morifolium SSR markers were selected for further genetic diversity analysis. PCR amplification of these EST-SSRs produced 1319 fragments, 1306 of which showed polymorphism. The average polymorphism information content of the SSR primer pairs was 0.972 (0.938–0.993), which showed high genetic diversity among C. morifolium cultivars. Based on SSR markers, 32 C. morifolium cultivars were separated into two main groups by partitioning of the clusters using the unweighted pair group method with arithmetic mean dendrogram, which was further supported by a principal coordinate analysis plot. Phylogenetic relationship among C. morifolium cultivars as revealed by SSR markers was highly consistent with the classification of medicinal C. morifolium populations according to their origin and ecological distribution. Our results demonstrated that SSR markers were highly reproducible and informative, and could be used to evaluate genetic diversity and relationships among medicinal C. morifolium cultivars.

show abstract

Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy

Cited by 18 publications

References 8 publications

Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network

Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network

A Multi-Level Strategy Based on Metabolic and Molecular Genetic Approaches for the Characterization of Different Coptis Medicines Using HPLC-UV and RAD-seq Techniques

Development of SSR Markers and Assessment of Genetic Diversity in Medicinal Chrysanthemum morifolium Cultivars

Contact Info

Product

Resources

About