http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Study on Recognition Method of Adhering Bars Based on Support Vector Machine
Guohua Liu,Liangyu Li,Bingle Liu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.9
It is difficult to track, count and separate the moving bars at a high speed on production line for their overlap and accumulation. Therefore, it is necessary to establish a reliable, practical recognition and segmentation mechanism for the adhered bars. A new solution to the problem of bars adhesion is proposed: a support vector machine is constructed to recognize the adhesion type of bars by the feature vectors of training samples. The geometric feature values and moment feature values based on Blob regions in images are extracted, which is the input feature vector of support vector machine. The trained classifier is used for identifying the adhesion type of bars in images. Finally, classification and recognition is carried by support vector machine. The experimental results show that the recognition accuracy based RBF kernel achieves 100%. The method is feasible and effective for the recognition and segmentation of the adhered bars.
Diqiu Liu,Qin Zhao,Xiuming Cui,Rui Chen,Xin Li,Bingling Qiu,Feng Ge 한국유전학회 2019 Genes & Genomics Vol.41 No.12
Background Panax notoginseng is a famous Chinese herbal medicine, but the root rot disease mainly caused by Fusarium solani severely reduces the yield and quality of its medicinal materials. Objective The defense priming in P. notoginseng through exogenous application of signaling molecule will supply theoretical support for the exogenous regulation of disease resistance in P. notoginseng. Methods In this study, the exogenous application of methyl jasmonate (MeJA) increased P. notoginseng’s resistance to F. solani. Furthermore, the P. notoginseng transcriptome during F. solani infection was investigated through next-generation sequencing to uncover the resistance mechanism of P. notogingseng induced by MeJA. Results The de novo assembly of transcriptome sequences produced 80,551 unigenes, and 36,771 of these unigenes were annotated by at least one database. A differentially expressed gene analysis revealed that a large number of genes related to terpenoid backbone biosynthesis, phenylalanine metabolism, and plant–pathogen interactions were predominantly upregulated by MeJA. Moreover, jasmonic acid (JA) biosynthesis-related genes and the JA signaling pathway genes, such as linoleate 13S-lipoxygenase, allene oxide cyclase, allene oxide synthase, TIFY, defensin, and pathogenesis-related proteins, showed increased transcriptional levels after inoculation with F. solani. Notably, according to the gene expression analysis, JA and ethylene signaling pathways may act synergistically to positively regulate the defense responses of P. notoginseng to F. solani. Conclusion JA signaling appears to play a vital role in P. notoginseng responses to F. solani infection, which will be helpful in improving the disease resistance of P. notoginseng cultivars as well as in developing an environmentally friendly biological control method for root rot disease.