Study on the identification and evaluation of growth years for Paris polyphylla var. yunnanensis using deep learning combined with 2DCOS

Yue, JiaQi; Li, Zhimin; Zuo, Zhiyan; Zhao, Yanli; Zhang, Ji; Wang, Yuanzhong

doi:10.1016/j.saa.2021.120033

Cited by 31 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synchronous 2D‐COS images with different colors had similar results. In different color of image, although the synchronous 2D‐COS images of different colors have great visual differences, the modeling results are almost the same 22 . In different preprocessed methods of spectra, the preprocessed spectra did not necessarily improve the accuracy of the model, even some preprocessed spectra reduce the accuracy of the model 23 .…”

Section: Resultsmentioning

confidence: 93%

“…In different color of image, although the synchronous 2D-COS images of different colors have great visual differences, the modeling results are almost the same. 22 In different preprocessed methods of spectra, the preprocessed spectra did not necessarily improve the accuracy of the model, even some preprocessed spectra reduce the accuracy of the model. 23 The results show that 2D-COS has higher accuracy than one-dimensional spectra, and excellent accuracy was also achieved without preprocessing of the spectra.…”

Section: Synchronous Two-dimensional Correlation Spectroscopy Images ...mentioning

confidence: 98%

See 1 more Smart Citation

ResNet models for rapid identification of species and geographical origin of wild boletes from Yunnan, and MaxEnt model for delineation of potential distribution

Chen

Liu

et al. 2022

Journal of Chemometrics

View full text Add to dashboard Cite

Yunnan is known for its rich biodiversity and is known as the Wild Mushroom Kingdom. Boletes are a world-renowned wild edible mushroom, with unique sensory characteristics, nutritional value and medicinal value extraordinary.However, the species and geographical origin of boletes influence their price and quality. In this study, a method was developed to identify species and geographical origin simultaneously. Therefore, Fourier transform near-infrared (FT-NIR) data sets of boletes were collected and converted to two-dimensional correlation spectroscopy (2D-COS). On this basis, the species and geographic origins of boletes were identified using Residual neural network (ResNet) image analysis model. The results showed that FT-NIR could identify boletes species and geographical origins, 7000-4000 cm À1 band was more suitable for species identification, 7000-5300 cm À1 band was more suitable for geographical origins identification. In addition, the environmental factors with high contribution to the distribution of boletes were screened based on the maximum entropy (MaxEnt) model. This allows characterization of the potential geographic distribution of boletes. The results showed that precipitation factors played a vital role in its distribution and might even be responsible for the difference in chemical composition.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Synchronous Two-dimensional Correlation Spectroscopy Images ...mentioning

confidence: 98%

ResNet models for rapid identification of species and geographical origin of wild boletes from Yunnan, and MaxEnt model for delineation of potential distribution

Chen

Liu

et al. 2022

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…ResNet is the first classification network that surpasses human accuracy in classification tasks ( Russakovsky et al, 2015 ). At present, the ResNet-based classification model has been widely used in plant image research, such as plant age judgment ( Yue et al, 2021 ), flowering pattern analysis ( Jiang et al, 2020 ), and root image analysis ( Wang et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Multi-Information Model for Large-Flowered Chrysanthemum Cultivar Recognition and Classification

Wang

Tian²,

Zhang³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

The traditional Chinese large-flowered chrysanthemum is one of the cultivar groups of chrysanthemum (Chrysanthemum × morifolium Ramat.) with great morphological variation based on many cultivars. Some experts have established several large-flowered chrysanthemum classification systems by using the method of comparative morphology. However, for many cultivars, accurate recognition and classification are still a problem. Combined with the comparative morphological traits of selected samples, we proposed a multi-information model based on deep learning to recognize and classify large-flowered chrysanthemum. In this study, we collected the images of 213 large-flowered chrysanthemum cultivars in two consecutive years, 2018 and 2019. Based on the 2018 dataset, we constructed a multi-information classification model using non-pre-trained ResNet18 as the backbone network. The model achieves 70.62% top-5 test accuracy for the 2019 dataset. We explored the ability of image features to represent the characteristics of large-flowered chrysanthemum. The affinity propagation (AP) clustering shows that the features are sufficient to discriminate flower colors. The principal component analysis (PCA) shows the petal type has a better interpretation than the flower type. The training sample processing, model training scheme, and learning rate adjustment method affected the convergence and generalization of the model. The non-pre-trained model overcomes the problem of focusing on texture by ignoring colors with the ImageNet pre-trained model. These results lay a foundation for the automated recognition and classification of large-flowered chrysanthemum cultivars based on image classification.

show abstract

“…29,30 It was developed mainly based on compounds' structural information to analyze the overall chemical composition, combined with chemometrics to identify and predict the Chinese herbal materials and to evaluate the quality by analyzing the model effect. [31][32][33] In qualitative and quantitative analysis based on IR spectroscopy, it is often combined with chemometric methods to explore the linear correlation between the overlapping spectra and the chemical composition of the sample. 34 Variable selection is one of the important steps in chemometric methods, which is mainly applied to eliminate redundant and collinear information to reduce the computing tasks and model dimensions, improving model performance.…”

Section: Introductionmentioning

confidence: 99%

“…Infrared (IR) spectroscopy has been widely applied in the identification of Chinese herbal materials owing to its characteristics of being non‐destructive and fast, and it can be used to obtain the main structural information of the sample's chemical composition 29,30 . It was developed mainly based on compounds’ structural information to analyze the overall chemical composition, combined with chemometrics to identify and predict the Chinese herbal materials and to evaluate the quality by analyzing the model effect 31–33 . In qualitative and quantitative analysis based on IR spectroscopy, it is often combined with chemometric methods to explore the linear correlation between the overlapping spectra and the chemical composition of the sample 34 .…”

Section: Introductionmentioning

confidence: 99%

Anticoagulant activity analysis and origin identification of Panax notoginseng using HPLC and ATR‐FTIR spectroscopy

Cui

Liu

et al. 2022

Phytochemical Analysis

View full text Add to dashboard Cite

Introduction Panax notoginseng is one of the traditional precious and bulk‐traded medicinal materials in China. Its anticoagulant activity is related to its saponin composition. However, the correlation between saponins and anticoagulant activities in P. notoginseng from different origins and identification of the origins have been rarely reported. Objectives We aimed to analyze the correlation of components and activities of P. notoginseng from different origins and develop a rapid P. notoginseng origin identification method. Materials and methods Pharmacological experiments, HPLC, and ATR‐FTIR spectroscopy (variable selection) combined with chemometrics methods of P. notoginseng main roots from four different origins (359 individuals) in Yunnan Province were conducted. Results The pharmacological experiments and HPLC showed that the saponin content of P. notoginseng main roots was not significantly different. It was the highest in main roots from Wenshan Prefecture (9.86%). The coagulation time was prolonged to observe the strongest effect (4.99 s), and the anticoagulant activity was positively correlated with the contents of the three saponins. The content of ginsenoside Rg1 had the greatest influence on the anticoagulant effect. The results of spectroscopy combined with chemometrics show that the variable selection method could extract a small number of variables containing valid information and improve the performance of the model. The variable importance in projection has the best ability to identify the origins of P. notoginseng; the accuracy of the training set and the test set was 0.975 and 0.984, respectively. Conclusion This method is a powerful analytical tool for the activity analysis and identification of Chinese medicinal materials from different origins.

show abstract

Study on the identification and evaluation of growth years for Paris polyphylla var. yunnanensis using deep learning combined with 2DCOS

Cited by 31 publications

References 35 publications

ResNet models for rapid identification of species and geographical origin of wild boletes from Yunnan, and MaxEnt model for delineation of potential distribution

ResNet models for rapid identification of species and geographical origin of wild boletes from Yunnan, and MaxEnt model for delineation of potential distribution

Multi-Information Model for Large-Flowered Chrysanthemum Cultivar Recognition and Classification

Anticoagulant activity analysis and origin identification of Panax notoginseng using HPLC and ATR‐FTIR spectroscopy

Contact Info

Product

Resources

About