检索结果-南通市图书馆

Bearing Fault Diagnosis Based on Deep Discriminative Adversarial Domain Adaptation Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2619-2640页

作者： Jinxi Guo Kai Chen Jiehui Liu Yuhao Ma Jie Wu Yaochun Wu Xiaofeng Xue Jianshen Li School of Mechanical and Equipment Engineering Hebei University of EngineeringHandan056000China college of Mechanical Engineering Anyang Institute of TechnologyAnyang455000China Department of Mechanical and Electrical Engineering Yuncheng UniversityYuncheng044000China

Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasingattention and achieved some results. It might lead to insufficient performance for using transfer learning alone andcause misclassification of target samples for domain bias when building deep models to learn domain-invariantfeatures. To address the above problems, a deep discriminative adversarial domain adaptation neural networkfor the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstlyconverted into frequency domain data by Fast Fourier Transform, and an improved deep convolutional neuralnetwork with wide first-layer kernels is used as a feature extractor to extract deep fault features. Then, domaininvariant features are learned from the fault data with correlation alignment-based domain adversarial ***, to enhance the discriminative property of features, discriminative feature learning is embeddedinto this network to make the features compact, as well as separable between classes within the class. Finally, theperformance and anti-noise capability of the proposedmethod are evaluated using two sets of bearing fault *** results demonstrate that the proposed method is capable of handling domain offset caused by differentworkingconditions and maintaining more than 97.53% accuracy on various transfer tasks. Furthermore, the proposedmethod can achieve high diagnostic accuracy under varying noise levels.

关键词： Fault diagnosis transfer learning domain adaptation discriminative feature learning correlation alignment

Transcriptional landscape of cotton roots in response to salt stress at single-cell resolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plant Communications 2024年第2期5卷 46-66页

作者： Pengtao Li Qiankun Liu Yangyang Wei Chaozhu Xing Zhongping Xu Fang Ding Yuling Liu Quanwei Lu Nan Hu Tao Wang Xiangqian Zhu Shuang Cheng Zhaoguo Li Zilin Zhao Yanfang Li Jiangping Han Xiaoyan Cai Zhongli Zhou Kunbo Wang Baohong Zhang Fang Liu Shuangxia Jin Renhai Peng college of Biology and Food Engineering Anyang Institute of TechnologyAnyangHenan 455000China State Key Laboratory of Cotton Biology Institute of Cotton ResearchChinese Academy of Agricultural SciencesAnyangHenan 455000China Research Base Anyang Institute of TechnologyState Key Laboratory of Cotton BiologyAnyang 455000HenanChina School of Life Sciences Zhengzhou UniversityZhengzhouHenan 450001China Hubei Hongshan Laboratory National Key Laboratory of Crop Genetic ImprovementHuazhong Agricultural UniversityWuhanHubeiChina Hubei Key Laboratory of Plant Pathology Huazhong Agricultural UniversityWuhanHubei 430070China Department of Biology East Carolina UniversityGreenvilleNC 27858USA

Increasing soil salinization has led to severe reductions in plant yield and quality,and investigating the mo-lecular mechanism of salt stress response is therefore an urgent *** this study,we systematically analyzed the response of cotton roots to salt stress using single-cell transcriptomics technology;56281 high-quality cells were obtained from 5-day-old lateral root tips of Gossypium arboreum under natural growth conditions and different salt *** cell types with an array of novel marker genes were identified and confirmed by in situ RNA hybridization,and pseudotime analysis of some specific cell types revealed their potential differentiation *** changes in cell numbers under salt stress were observed for outer epidermal and inner endodermal cells,which were significantly enriched in response to stress,amide biosynthetic process,glutathione metabolism,and glycolysis/*** of differentially expressed genes identified in multiple comparisons revealed other functional ag-gregations concentrated on plant-type primary cell wall biogenesis,defense response,phenylpropanoid biosynthesis,and metabolic *** candidate differentially expressed genes encoding transcrip-tion factors or associated with plant hormones also responsive to salt stress were identified,and the func-tion of Ga03G2153,annotated as auxin-responsive GH3.6,was confirmed by virus-induced gene *** GaGH3.6-silenced plants showed a severe stress-susceptible phenotype,and physiological and biochemical measurements indicated that they suffered more significant oxidative *** results suggest that GaGH3.6 might participate in cotton salt tolerance by regulating redox *** thus construct a transcriptional atlas of salt-stressed cotton roots at single-cell resolution,enabling us to explore cellular heterogeneity and differentiation trajectories and providing valuable insights into the mo-lecular mechanisms that underlie plan

关键词： cotton salt stress scRNA-seq root cell types virus-induced gene silencing

Inferring the spin distribution of binary black holes using deep learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics C 2024年第10期48卷 275-283页

作者： Li Tang Xi-Long Fan School of Math and Physics Mianyang Teachers'CollegeMianyang 621000China School of Physics and Technology Wuhan UniversityWuhan 430072 China

The spin characteristics of black holes offer valuable insights into the evolutionary pathways of their progenitor *** is crucial for understanding the broader population properties of black *** hierarchical Bayesian inference techniques employed to discern these properties often demand substantial time,and consensus regarding the spin distribution of binary black hole(BBH)systems remains *** this study,leveraging observations from GWTC-3,we adopted a machine learning approach to infer the spin distribution of black holes within BBH ***,we developed a deep neural network(DNN)and trained it using data generated from a Beta *** training strategy,involving the segregation of data into 10 bins,not only expedites model training but also enhances the versatility and adaptability of the DNN to accommodate the growing volume of gravitational wave *** Monte Carlo-bootstrap(MC-bootstrap)to generate observation-simulated samples,we derived spin distribution parameters:α=1.3_(-0.18)^(+0.25),β=1.70_(-0.29)^(+0.24)for the larger BH sample and α=1.37_(-0.20)^(+0.31),β=1.63_(-0.20)^(+0.30) for the smaller BH *** our constraints,the distributions of component spin magnitudes suggest the likelihood of both black holes in the BBH merger possessing non-zero spin.

关键词： gravitational wave black hole merges deep learning

Genome-wide association mapping and genomic prediction of stalk rot in two mid-altitude tropical maize populations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Crop Journal 2024年第2期12卷 558-568页

作者： Junqiao Song Angela Pacheco Amos Alakonya Andrea S.Cruz-Morales Carlos Muoz-Zavala Jingtao Qu Chunping Wang Xuecai Zhang Felix San Vicente Thanda Dhliwayo college of Agronomy Henan University of Science and TechnologyLuoyang 471000HenanChina International Maize and Wheat Improvement Center(CIMMYT) El BatanMexico anyang Academy of Agricultural Sciences Anyang 455000HenanChina CIMMYT-China Specialty Maize Research Center Crop Breedingand Cultivation Research InstituteShanghai Academy of Agricultural SciencesShanghai 201403China

Maize stalk rot reduces grain yield and *** about the genetics of resistance to maize stalk rot could help breeders design effective breeding strategies for the *** prediction may be a more effective breeding strategy for stalk-rot resistance than marker-assisted *** performed a genome-wide association study(GWAS)and genomic prediction of resistance in testcross hybrids of 677 inbred lines from the Tuxpe?o and non-Tuxpe?o heterotic pools grown in three environments and genotyped with 200,681 single-nucleotide polymorphisms(SNPs).Eighteen SNPs associated with stalk rot shared genomic regions with gene families previously associated with plant biotic and abiotic *** favorable SNP haplotypes traced to tropical than to temperate progenitors of the inbred *** genotype-by-environment(G×E)interaction increased genomic prediction accuracy.

关键词： Maize stalk rot Genome-wide association mapping Haplotype analysis Genomic prediction G×E interaction

Widespread incomplete lineage sorting and introgression shaped adaptive radiation in the Gossypium genus

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Plant Communications 2024年第2期5卷 185-197页

作者： Yanchao Xu Yangyang Wei Zhongli Zhou Xiaoyan Cai Scott ABoden Muhammad Jawad Umer Luqman BSafdar Yuling Liu Dingsha Jin Yuqing Hou Yuhong Wang Sarah Brooke Wall Kunbo Wang Shuxun Yu Baohong Zhang Renhai Peng Fang Liu National Key Laboratory of Cotton Bio-breeding and Integrated Utilization Institute of Cotton ResearchChinese Academy of Agricultural SciencesAnyang 455000China college of Plant Science and Technology Huazhong Agricultural UniversityWuhan 40070China college of Biology and Food Engineering Anyang Institute of TechnologyAnyang 455000China National Nanfan Research Institute(Sanya) Chinese Academy of Agricultural SciencesSanya 572024China School of Agriculture Food and WineUniversity of AdelaideAdelaideSA 5005Australia Sanya Institute Hainan Academy of Agricultural SciencesSanya 572000China Department of Biology East Carolina UniversityGreenvilleNC 27858USA School of Agricultural Sciences Zhengzhou UniversityZhengzhou 450001China

Cotton(Gossypium)stands as a crucial economic crop,serving as the primary source of naturalfiber for the textile ***,the evolutionary mechanisms driving speciation within the Gossypium genus remain *** this investigation,we leveraged 25 Gossypium genomes and introduced four novel assem-blies—***,***,***,and ***(Gklo)—to delve into the speciation history of this ***,we encountered intricate phylogenies potentially stemming from *** complexities are further compounded by incomplete lineage sorting(ILS),a factor likely to have been instrumental in shaping the swift diversification of *** focus subsequently shifted to the rapid radiation episode during a concise period in Gossypium *** a recently diverged lineage comprising ***,Gklo,and ***,we constructed afinely detailed ILS ***,this analysis revealed the non-random distribution of ILS regions across the reference Gklo ***,we identified signs of robust natural selection influencing specific ILS *** variations per-taining to speciation emerged between the closely related sister species Gklo and ***-mately 15.74%of speciation structural variation genes and 12.04%of speciation-associated genes were esti-mated to intersect with ILS *** enrich our understanding of the role of ILS in adaptive radiation,shedding fresh light on the intricate speciation history of the Gossypium genus.

关键词： cotton speciation Gossypium genus incomplete lineage sorting ILS phylogenetic analysis gene tree resolution

Modulation of charge in C_(9)N_(4) monolayer for a highcapacity hydrogen storage as a switchable strategy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of physics 2024年第4期19卷 47-55页

作者： Lin Ju Junxian Liu Minghui Wang Shenbo Yang Shuli Liu School of Physics and Electric Engineering Anyang Normal UniversityAnyang 455000China School of Mechanical Medical and Process EngineeringQueensland University of TechnologyBrisbane QLD 4001Australia Hongzhiwei Technology(Shanghai)Co.Ltd. 1599 Xinjinqiao RoadPudongShanghai 201206China

Developing advanced hydrogen storage materials with high capacity and efficient reversibility is a crucial aspect for utilizing hydrogen source as a promising alternate to fossil *** this paper,we have systematically investigated the hydrogen storage properties of neutral and negatively charged C_(9)N_(4) monolayer based on density functional theory(DFT).Our foundings indicate that injecting additional electrons into the adsorbent significantly boosts the adsorption capacity of C_(9)N_(4) monolayer to H2 *** gravimetric density of negatively charged C_(9)N_(4) monolayer can reach up to 10.80 wt% when fully covered with *** other hydrogen storage methods,the storage and release processes happen automatically upon introducing or removing extra ***,these operations can be easily adjusted through activating or deactivating the charging *** a result,the method is easily reversible and has tunable kinetics without requiring particular ***,C_(9)N_(4) is proved to be a suitable candidate for efficient electron injection/release due to its well electrical *** work can serve as a valuable guide in the quest for a novel category of materials for hydrogen storage with high capacity.

关键词： hydrogen storage C_(9)N_(4)monolayer charge modulation density functional theory

Proteomic study of vitreous in proliferative diabetic retinopathy patients after treatment with aflibercept:a quantitative analysis based on 4D label-free technique

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2024年第4期17卷 676-685页

作者： Ting-Ting Feng Xiang Gao An-Ran Liang Bo-Wen Zhao Guang-Hui He Song Chen Clinical college of Ophthalmology Tianjin Medical UniversityTianjin 300070China Tianjin Key Laboratory of Ophthalmology and Visual Science Tianjin Eye InstituteTianjin Eye HospitalTianjin 300020China Key Laboratory of Ophthalmology Anyang Eye HospitalAnyang 455000Henan ProvinceChina Department of Ophthalmology Jining No.1 People’s HospitalJining 272011Shandong ProvinceChina

AIM:To identify different metabolites,proteins and related pathways to elucidate the causes of proliferative diabetic retinopathy(PDR)and resistance to anti-vascular endothelial growth factor(VEGF)drugs,and to provide biomarkers for the diagnosis and treatment of ***:Vitreous specimens from patients with diabetic retinopathy were collected and analyzed by Liquid Chromatography-Mass Spectrometry(LC-MS/MS)analyses based on 4D label-free *** differentially expressed proteins(DEPs),Gene Ontology(GO),Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway representation and protein interactions were ***:A total of 12 samples were *** proteomics results showed that a total of 58 proteins were identified as DEPs,of which 47 proteins were up-regulated and 11 proteins were *** found that C1q and tumor necrosis factor related protein 5(C1QTNF5),Clusterin(CLU),tissue inhibitor of metal protease 1(TIMP1)and signal regulatory protein alpha(SIRPα)can all be specifically regulated after aflibercept *** functional analysis showed that some DEPs are related to changes in inflammatory regulatory pathways caused by *** addition,protein-protein interaction(PPI)network evaluation revealed that TIMP1 plays a central role in neural *** addition,CD47/SIRPαmay become a key target to resolve anti-VEGF drug resistance in ***:Proteomic analysis is an approach of choice to explore the molecular mechanisms of *** data show that multiple proteins are differentially changed in PDR patients after intravitreal injection of aflibercept,among which C1QTNF5,CLU,TIMP1 and SIRPαmay become targets for future treatment of PDR and resolution of anti-VEGF resistance.

关键词： vitreous proliferative diabetic retinopathy proteome 4D label-free

Prediction of Wordle Scores Based on ARIMA and LSTM Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Applied Mathematics and Physics 2024年第2期12卷 543-553页

作者： Biyun Chen Wenqiang Li college of Information Engineering Yancheng Teachers University Yancheng China

This paper examines the effectiveness of the Differential autoregressive integrated moving average (ARIMA) model in comparison to the Long Short Term Memory (LSTM) neural network model for predicting Wordle user-reported scores. The ARIMA and LSTM models were trained using Wordle data from Twitter between 7th January 2022 and 31st December 2022. User-reported scores were predicted using evaluation metrics such as MSE, RMSE, R2, and MAE. Various regression models, including XG-Boost and Random Forest, were used to conduct comparison experiments. The MSE, RMSE, R2, and MAE values for the ARIMA(0,1,1) and LSTM models are 0.000, 0.010, 0.998, and 0.006, and 0.000, 0.024, 0.987, and 0.013, respectively. The results indicate that the ARIMA model is more suitable for predicting Wordle user scores than the LSTM model.

关键词： Time Series ARIMA LSTM Wordle Prediction

Intelligent In-Vehicle Safety System Based on Yolov5

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第3期12卷 207-218页

作者： Biyun Chen Wei Cai Jinwen Zhu college of Computer Information and Engineering Yancheng Teachers University Yancheng China

In order to reduce the occurrence of traffic accidents and assist drivers to avoid dangerous driving. This paper presents a smart in-vehicle safety system that utilises the Yolov5 algorithm. Yolov5 algorithm is used to anticipate driver fatigue and distraction behaviours, and remind drivers to pay attention to safe driving in time. The system continuously splits the frames and analyses the frame content through the video feedback from the front camera, compared to the traditional machine learning, Yolov5’s mosaic data is enhanced, resulting in a batch size enhancement of 92.3%, and it also uses the Drop Block mechanism to prevent overfitting. The hardware of this system uses STM32 microcontroller and uses system DMA interrupt control and buzzer alarm device to warn about dangerous driving behaviour.

关键词： Behaviour Detection STM32 Pyside2 Yolov5 Dlib Open Source Library Perclos Model