Search

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Paris polyphylla is an important component of many Chinese patent medicines. Different kinds of paris polyphylla are very similar in shape but different in quality, making it difficult to identify. In response to this problem, this paper uses a stereo microscope to collect two kinds of cross- sectional microscopic images of fresh rhizome of the paris polyphylla to identify them. Based on the ResNeXt101 model, it proposes the ES-Net module combining an efficient channel attention network and a spatial attention module. The output of each part of the ResNeXt module is further input into the ES-Net module. The Mixup method is used for data enhancement. The experimental results show that the highest accuracy of the classification of the two kinds of the paris polyphylla images is 94.95%, which is 2.07 percentage points higher than the original ResNeXt101 model. The results show that the ES-Net module can effectively enhance the characteristic information extraction ability of the original model ResNeXt101 on the cross-sectional microscopic image of fresh rhizome of the Paris polyphylla. Therefore, it improves the classification accuracy for the paris polyphylla. The deep learning method proposed has practical value for automatic identification of fresh rhizome of the paris polyphylla. [ABSTRACT FROM AUTHOR]

This paper studied problem that the deep descriptors cannot provide the correlation between the features. This paper proposed a feature relevance fusion based deep hashing method to incorporate the relationship between different deep descriptors into the description of the image contents. Firstly, it extracted the feature maps from the pre-trained network and used for deep descriptor generation. Then, it mapped these descriptors to deep visual words, and also explored the frequent item set based on these deep visual words. Next, it concatenated deep visual words based image representation of discrete values and frequent item set based image representation of binary values to represent an image. Finally, it formulated an optimization based on the intra-class and inter-class similarities between images to obtain the optimal thresholds to convert the image representation into a binary string. Extensive experiments show that compared with some state-of-the-art methods, the proposed method can achieve satisfying retrieval performance in the holiday, Oxford and Paris image databases. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Henan Agricultural Sciences is the property of Editorial Board of Journal of Henan Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

[Objective] The present paper aimed to study the effect on the amount of rhizospheric soil microorganisms and soil enzyme activity of Parisbpolyphylla var.Yunnanens seedlings colonized by Arbuscular mycorrhizal (AM) Fungi. [Method] A pot experiment was conducted and 28 species of AM fungi were inoculated in the seedlings of Paris polyphylla var.yunnanensis. The number of culturable microbes in rhizosphere soil was calculated by the dilution method of plate counting, and the laboratory analysis was used to analyze soil enzyme activity. [Result] The mycorrhizal infection rate of the different AM Fungi treatment groups was in the range of 75% — 100%. The difference of rhizospheric soil microorganism quantity, biomass carbon and soil enzyme activity of Paris polyphylla var.yunnanensis seedlings colonized by different AM Fungi exist.Inoculation with AM fungi increased the number of culturable bacteria and actinomycetes, decreased the number of culturable fungi in rhizosphere soil, and increased the utilization rate of the soil microbial carbon source.It also changed the richness and homogeneity of species in soil and increased the biodiversity of soil. The activities of soil enzymes (protease, urease, phosphatase, catalase and sucrase) in the rhizosphere of Paris polyphylla var.yunnanensis seedlings were increased, especially the activities of phosphatase and sucrase. [Conclusion] AM fungi affected the rhizosphere soil microenvironment of Paris polyphylla var.yunnanensis seedlings in different degrees and provided important theoretical and practical values for the artificial cultivation and application of AM fungi. [ABSTRACT FROM AUTHOR]

[Objective]The present paper aims to compare the nucleosides contents between wild and cultivated Paris polyphylla Smith var. yunnanensis from different regions, and study whether the wild and cultivated varieties had quality equivalence. [Method]The content of 9 nucleosides in 16 wild varieties and 17 cultivated varieties was determined by HPLC, and evaluated by independent sample t test, cluster analysis and principal component analysis. [Result]The results of independent sample t test showed that there were significant differences in the contents of cytidine, thymidine and 2’-deoxyadenosine between the wild and cultivated varieties(Sig.<0.05), while there were no differences in the contents of the other six nucleosides(Sig.>0.05). The results of principal component analysis and cluster analysis showed that the wild and cultivated varieties could not be distinguished according to the difference of nucleoside content. [Conclusion]There was no significant difference in nucleoside content between wild and cultivated Paris polyphylla. And the cultivated Paris polyphylla could replace the wild Paris polyphylla. [ABSTRACT FROM AUTHOR]

Copyright of Society: Chinese Journal of Sociology / Shehui is the property of Society: Chinese Journal of Sociology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Mycosystema is the property of Mycosystema Editorial Board and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)