检索结果-南通市图书馆

Transfer learning-based encoder-decoder model with visual explanations for infrastructure crack segmentation:New open database and comprehensive evaluation

引用

Underground Space 2024年第4期17卷 60-81页

作者： Fangyu Liu Wenqi Ding Yafei Qiao Linbing Wang Illinois Center for Transporation Department of Civil and Environmental EngineeringUniversity of Illinois Urbana-ChampaignIllinois 61801USA Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Key Laboratory of Geotechnical and Underground Engineering of the Ministry of Education Tongji UniversityShanghai 200092China School of Environmental CivilAgricultural and Mechanical EngineeringUniversity of GeorgiaGeorgia 30602USA

Contemporary demands necessitate the swift and accurate detection of cracks in critical infrastructures,including tunnels and *** study proposed a transfer learning-based encoder-decoder method with visual explanations for infrastructure crack ***,a vast dataset containing 7089 images was developed,comprising diverse conditions—simple and complex crack patterns as well as clean and rough ***,leveraging transfer learning,an encoder-decoder model with visual explanations was formulated,utilizing varied pre-trained convolutional neural network(CNN)as the *** explanations were achieved through gradient-weighted class activation mapping(Grad-CAM)to interpret the CNN segmentation ***,accuracy,complexity(computation and model),and memory usage assessed CNN feasibility in practical *** performance was gauged via prediction and visual *** investigation encompassed hyperparameters,data augmentation,deep learning from scratch *** learning,segmentation model architectures,segmentation model encoders,and encoder pre-training *** underscored transfer learning’s potency in enhancing CNN accuracy for crack segmentation,surpassing deep learning from ***,encoder classification accuracy bore no significant correlation with CNN segmentation *** all tested models,UNet-EfficientNet_B7 excelled in crack segmentation,harmonizing accuracy,complexity,memory usage,prediction,and visual explanation.

关键词： Crack segmentation Transfer learning Visual explanation Infrastructure database

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Discrimination of polysorbate 20 by high-performance liquid chromatography-charged aerosol detection and characterization for components by expanding compound database and library

引用

Journal of Pharmaceutical Analysis 2024年第5期14卷 722-732页

作者： Shi-Qi Wang Xun Zhao Li-Jun Zhang Yue-Mei Zhao Lei Chen Jin-Lin Zhang Bao-Cheng Wang Sheng Tang Tom Yuan Yaozuo Yuan Mei Zhang Hian Kee Lee Hai-Wei Shi Jiangsu Institute for Food and Drug Control Nanjing210019China School of Pharmacy China Pharmaceutical UniversityNanjing211112China School of Pharmacy Nanjing University of Chinese MedicineNanjing210046China Chinese Pharmacopoeia Commission Beijing100061China Nanjing Well Pharmaceutical Group Co. Ltd.Nanjing210018China School of Environmental and Chemical Engineering Jiangsu University of Science and TechnologyZhenjiangJiangsu212003China University of Massachusetts Amherst Amherst01003USA Department of Chemistry National University of SingaporeSingapore117543Singapore

Analyzing polysorbate 20(PS20)composition and the impact of each component on stability and safety is crucial due to formulation variations and individual *** similar structures and polarities of PS20 components make accurate separation,identification,and quantification *** this work,a high-resolution quantitative method was developed using single-dimensional high-performance liquid chromatography(HPLC)with charged aerosol detection(CAD)to separate 18 key components with multiple *** separated components were characterized by ultra-high-performance liquid chromatography-quadrupole time-of-flight mass spectrometry(UHPLC-Q-TOF-MS)with an identical gradient as the HPLC-CAD *** polysorbate compound database and library were expanded over 7-time compared to the commercial *** method investigated differences in PS20 samples from various origins and grades for different dosage forms to evaluate the composition-process ***-Q-TOF-MS identified 1329 to 1511 compounds in 4 batches of PS20 from different *** method observed the impact of 4 degradation conditions on peak components,identifying stable components and their tendencies to ***-CAD and UHPLC-Q-TOF-MS results provided insights into fingerprint differences,distinguishing quasi products.

关键词： Polysorbate 20 Component database Discrimination Degradation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

NCAD v1.0: a database for non-coding variant annotation and interpretation

引用

Journal of Genetics and Genomics 2024年第2期51卷 230-242页

作者： Xiaoshu Feng Sihan Liu Ke Li Fengxiao Bu Huijun Yuan Institute of Rare Diseases West China HospitalSichuan UniversityChengduSichuan 610044China

The application of whole genome sequencing is expanding in clinical diagnostics across various genetic disorders, and the significance of non-coding variants in penetrant diseases is increasingly being demonstrated. Therefore, it is urgent to improve the diagnostic yield by exploring the pathogenic mechanisms of variants in non-coding regions. However, the interpretation of non-coding variants remains a significant challenge, due to the complex functional regulatory mechanisms of non-coding regions and the current limitations of available databases and tools. Hence, we develop the non-coding variant annotation database (NCAD, http://***/), encompassing comprehensive insights into 665,679,194 variants, regulatory elements, and element interaction details. Integrating data from 96 sources, spanning both GRCh37 and GRCh38 versions, NCAD v1.0 provides vital information to support the genetic diagnosis of non-coding variants, including allele frequencies of 12 diverse populations, with a particular focus on the population frequency information for 230,235,698 variants in 20,964 Chinese individuals. Moreover, it offers prediction scores for variant functionality, five categories of regulatory elements, and four types of non-coding RNAs. With its rich data and comprehensive coverage, NCAD serves as a valuable platform, empowering researchers and clinicians with profound insights into non-coding regulatory mechanisms while facilitating the interpretation of non-coding variants.

关键词： Non-coding variants Annotation Variant interpretation database

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

BreedingAIDB: A database integrating crop genome-to-phenotype paired data with machine learning tools applicable to breeding

引用

Plant Communications 2024年第7期5卷 12-15页

作者： Zijie Shen Enhui Shen Kun Yang Zuoqian Fan Qian-Hao Zhu Longjiang Fan Chu-Yu Ye Hainan Institute Zhejiang UniversitySanya 572025China Institute of Crop Science&Institute of Bioinformatics College of Agriculture&BiotechnologyZhejiang UniversityHangzhou 310058China CSIRO Agriculture and Food CanberraACT 2601Australia

Machine learning(ML)is one of the key technologies for next-generation breeding,and“big data”is the cornerstone for development of ML algorithms that are applicable to crop breeding ***,there is a shortage of databases containing phenotype data and corresponding genomic data,i.e.,genome-to-phenotype(G2P)paired data,that can be used in the development of ML algorithms for *** fill this gap,we constructed a user-friendly database named the BreedingAIDB(http://***/BreedingAIDB)to provide breeders and ML experts with easily accessible G2P paired data for crops,as well as ML tools.

关键词： database learning breeding

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

PlantCFG:A comprehensive database with web tools for analyzing candidate flowering genes in multiple plants

引用

Plant Communications 2024年第2期5卷 11-14页

作者： Dongxu Liu Jiawei Li Shengbo Wang Tingting Huang Fangting Tao Yuchen Lin Wei Lin Xinle Zhao Yiming Huang Yupeng Jia Zhiquan Yang Chengfang Luo Qiang Zhu Wing-Kin Sung Jian Wu Qing-Yong Yang National Key Laboratory of Crop Genetic Improvement Hubei Hongshan LaboratoryHuazhong Agricultural UniversityWuhan 430070China Hubei Key Laboratory of Agricultural Bioinformatics College of InformaticsHuazhong Agricultural UniversityWuhan 430070China Hong Kong Genome Institute Hong Kong Science ParkShatinHong KongChina State Key Laboratory of Biocontrol School of Life SciencesSun Yat-Sen UniversityGuangzhou 510275China School of Life Sciences University of Science and Technology of ChinaHefei 230026China Key Laboratory of Plant Functional Genomics of the Ministry of Education Yangzhou UniversityYangzhou 225009China

Dear Editor,The transition from the vegetative to the reproductive phase of plant development,known as the floral transition,plays important roles in the plant life *** is a vulnerable but crucial phase for building crop yield,and proper timing of this period is therefore vital for obtaining optimal yields(Jung and Muller,2009).Analysis of flowering time is currently an important research topic in several fields,including plant molecular genetics,evolutionary biology,ecology,and crop breeding(Huang et al.,2011).

关键词： database web breeding

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

RLKdb:A comprehensively curated database of plant receptor-like kinase

引用

Molecular Plant 2024年第4期17卷 513-515页

作者： Zhiyuan Yin Jinding Liu Daolong Dou Department of Plant Pathology Nanjing Agricultural UniversityNanjing 210095China Academy for Advanced Interdisciplinary Studies Nanjing Agricultural UniversityNanjing 210095China

Dear Editor,Since the first plant receptor-like kinase(RLK)gene ZmPK1 was cloned from Zea mays in 1990(Walker and Zhang,1990),this large gene family has been extensively studied and shown to play crucial roles in growth,development,and immunity(Tang et al.,2017).RLKs are widespread in the plant ***,biological functions of most RLKs remain largely elusive(Dievart et al.,2020).Given RLKs share a conserved monophyletic RLK/Pelle kinase domain,RLKs in several model plants are classified into distinct families by extracellular domains(Shiu and Bleecker,2001).However,independent domain shuffling in specific lineages drives the origin of novel families,which raises a question what is the landscape of RLKs across the entire plant kingdom?Previously,sequence-homology-based methods have been widely used for RLK identification and classification,which might miss distantly related proteins with similar structures and potential novel families not mentioned in the *** academic community urgently requires a dedicated database for a systematic overview of the RLK gene family,providing data support for in-depth research on RLK ***,we used a topology-based method to accurately isolate the RLKomes from *** obtained RLKomes were further classified into(sub)families based on extracellular *** con-structed a comprehensively curated plant RLK database(https://***/rlkdb),which contains valuable re-sources for investigating the origin and evolution of the RLK fam-ily and multiple online tools for personalized analysis.

关键词： database comprehensive origin

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Unraveling the stereoscopic gene transcriptional landscape of zebrafish using Fish SED,a fish spatial expression database with multispecies scalability

引用

Science China(Life Sciences) 2024年第4期67卷 843-846页

作者： Cheng Guo Weidong Ye Danying Cao Mijuan Shi Wanting Zhang Yingyin Cheng Yaping Wang Xiao-Qin Xia Institute of Hydrobiology Chinese Academy of SciencesWuhan 430072China College of Advanced Agricultural Sciences University of Chinese Academy of SciencesBeijingChina The Innovative Academy of Seed Design Chinese Academy of SciencesBeijing 100101China

Dear Editor,The expression profile demonstrates how each gene was expressed in the target tissue or cell at a given *** heterogeneity is a biological concept characterized by the presence of numerous cells with varying functions and expression profiles within organ/tissue *** is also cell-to-cell signaling,which implies that the extracellular environment and spatial location influence intracellular transcription,resulting in spatial heterogeneity of gene expression within the same cell type.

关键词： landscape fish database

来源：

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

database of open-framework aluminophosphate syntheses:introduction and application(Ⅰ)

引用

Science China Chemistry 2009年第11期52卷 1734-1738页

作者： YAN Yan1,LI JiYang1,QI Miao2,ZHANG Xiao1,YU JiHong1 & XU RuRen1 1 State Key Laboratory of Inorganic Synthesis and Preparative Chemistry,Jilin University,Changchun 130012,China 2 Department of Chemistry,Northeast Normal University,Changchun 130117,China State Key Laboratory of Inorganic Synthesis and Preparative Chemistry Jilin University Changchun China Department of Chemistry Northeast Normal University Changchun China

The database of open-framework aluminophosphate(AlPO) syntheses has been established,which includes about 1600 synthetic *** analysis has been done on the basis of the framework composition,structure dimension,pore ring,and organic *** database will serve as useful guidance for the rational synthesis of microporous functional materials.

关键词： aluminophosphates open framework synthesis database

来源：

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

Optimizing and extending ion dielectric polarizability database for microwave frequencies using machine learning methods

引用

npj Computational Materials 2023年第1期9卷 977-986页

作者： Jincheng Qin Zhifu Liu Mingsheng Ma Yongxiang Li CAS Key Laboratory of Inorganic Functional Materials and Devices Shanghai Institute of CeramicsChinese Academy of Sciences201899 ShanghaiChina Center of Materials Sciences and Optoelectronics Engineering University of Chinese Academy of Sciences100049 BeijingChina

Permittivity at microwave frequencies determines the practical applications of microwave dielectric *** accuracy and universality of the permittivity prediction by Clausius–Mossotti equation depends on the dielectric polarizability(αD)*** most influentialαD database put forward by Shannon is facing three challenges in the 5 G era:(1)Few data,(2)Simplistic relation and(3)Low frequency(kHz–MHz)***,we optimized and extended the Shannon’s database for microwave frequencies by the four-stage multiple linear regression and support vector machine *** comparison with the conventional database,the optimized and extended databases achieved higher accuracy and expanded the amount of data from 60 to more than ***,we analyzed the relationships betweenαD and ion characteristics,including ionic radius(IR),atomic number(N),valence state(V)and coordination number(CN).We found that the positive cubic law of“αD~IR3”discussed in Shannon’s work was valid for the IR changed by the N,but invalid for the change caused by the CN.

关键词： database microwave dielectric

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Maintaining Discovered Frequent Itemsets： Cases for Changeable database and Support

引用

Journal of Computer Science & Technology 2003年第5期18卷 648-658页

作者：杜孝平唐世渭牧之内顕文 School of Electronics Engineering and Computer Science Peking University Beijing 100871 P.R. ChinaCollege of Software Beijing University of Aeronautics and Astronautics Beijing 100083 P.R. China School of Electronics Engineering and Computer Science Peking University Beijing 100871 P.R. China Graduate School of Information Science Kyushu University Fukuoka 812-8581 Japan

Mining frequent itemsets from large databases has played an essential role inmany data mining tasks. It is also important to maintain the discovered frequent itemsets forthese data mining tasks when the database is updated. All algorithms proposed so far for the maintenance of discovered frequent itemsets are only performed with a fixed minimum support,which is the same as that used to obtain the discovered frequent itemsets. That is, users cannot change the minimum support even if the new results are unsatisfactory to the users. In thispaper two new complementary algorithms, FMP (First Maintaining Process) and RMP (Repeated Maintaining Process), are proposed to maintain discovered frequent itemsets in the case that new transaction data are added to a transaction database. Both algorithms allow users to change theminimum support for the maintenance processes. FMP is used for the first maintaining process, andwhen the result derived from the FMP is unsatisfactory, RMP will be performed repeatedly untilsatisfactory results are obtained. The proposed algorithms re-use the previous results to cut downthe cost of maintenance. Extensive experiments have been conducted to assess the performance of the algorithms. The experimental results show that the proposed algorithms are very resultful compared with the previous mining and maintenance algorithms for maintenance of discovered frequent itemsets.

关键词： frequent itemset association rule algorithm data mining database

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：