检索结果-内蒙古大学图书馆

Transformers-sklearn: a toolkit for medical language understanding with transformer-based models

BMC MEDICAL INFORMATICS AND DECISION MAKING 2021年第SUPPL 2期21卷 90-90页

作者： Yang, Feihong wang, xuwen Ma, Hetong Li, Jiao Chinese Acad Med Sci Peking Union Med Coll Inst Med Informat & Lib 3rd Yabao Rd Beijing 100020 Peoples R China

Background Transformer is an attention-based architecture proven the state-of-the-art model in natural language processing (NLP). To reduce the difficulty of beginning to use transformer-based models in medical language understanding and expand the capability of the scikit-learn toolkit in deep learning, we proposed an easy to learn Python toolkit named transformers-sklearn. By wrapping the interfaces of transformers in only three functions (i.e., fit, score, and predict), transformers-sklearn combines the advantages of the transformers and scikit-learn toolkits. Methods In transformers-sklearn, three Python classes were implemented, namely, BERTologyClassifier for the classification task, BERTologyNERClassifier for the named entity recognition (NER) task, and BERTologyRegressor for the regression task. Each class contains three methods, i.e., fit for fine-tuning transformer-based models with the training dataset, score for evaluating the performance of the fine-tuned model, and predict for predicting the labels of the test dataset. transformers-sklearn is a user-friendly toolkit that (1) Is customizable via a few parameters (e.g., model_name_or_path and model_type), (2) Supports multilingual NLP tasks, and (3) Requires less coding. The input data format is automatically generated by transformers-sklearn with the annotated corpus. Newcomers only need to prepare the dataset. The model framework and training methods are predefined in transformers-sklearn. Results We collected four open-source medical language datasets, including TrialClassification for Chinese medical trial text multi label classification, BC5CDR for English biomedical text name entity recognition, DiabetesNER for Chinese diabetes entity recognition and BIOSSES for English biomedical sentence similarity estimation. In the four medical NLP tasks, the average code size of our script is 45 lines/task, which is one-sixth the size of transformers' script. The experimental results show that transformers-skl

关键词： Transformer NLP Toolkit Deep Learning Medical Language Understanding

来源：评论

学校读者我要写书评

暂无评论

基于流-热-固耦合的水冷壁应力场数值模拟研究

引用

沈阳工程学院学报（自然科学版） 2023年第3期19卷 24-28,33页

作者：张进赵旭王许稳华能集团辽宁分公司华能丹东电厂辽宁东港118300 桂林电子科技大学机电工程学院广西桂林541004

锅炉水冷壁向火侧内烟气与水冷壁管内饱和水之间的传热,使水冷壁管间、水冷壁管与鳍片间、水冷壁向火侧和背火侧间产生较大的热应力。本文通过数值模拟获得垂直膜式水冷壁管屏在较高炉膛温度下的温度场和应力场分布,获悉了水冷壁管内压... 详细信息

锅炉水冷壁向火侧内烟气与水冷壁管内饱和水之间的传热,使水冷壁管间、水冷壁管与鳍片间、水冷壁向火侧和背火侧间产生较大的热应力。本文通过数值模拟获得垂直膜式水冷壁管屏在较高炉膛温度下的温度场和应力场分布,获悉了水冷壁管内压力及温度决定了水冷壁热应力的大小及分布,得知了水冷壁管与鳍片拉裂的原因是锅炉热负荷在短时间内的交替变化,其计算结果为水冷壁在发生热应力拉裂破坏条件下的改进及合理应对拉裂事故提供了方向。

关键词：水冷壁热应力数值模拟流固耦合水平烟道

来源：评论

学校读者我要写书评

暂无评论

Functional characterization of TBL genes revealed the role of GhTBL7 and GhTBL58 in cotton fiber elongation

引用

INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES 2023年第1期241卷 124571页

作者： Kabir, Nosheen wang, xuwen Lu, Lili Qanmber, Ghulam Liu, Le Si, Aijun Zhang, Lian Cao, Wei Yang, Zuoren Yu, Yu Liu, Zhao Zhengzhou Univ Sch Agr Sci State Key Lab Cotton Biol Zhengzhou Res Base Zhengzhou 450001 Henan Peoples R China Chinese Acad Agr Sci Inst Cotton Res State Key Lab Cotton Biol Anyang 455000 Henan Peoples R China Xinjiang Acad Agr & Reclamat Sci Cotton Res Inst Key Lab China Northwestern Inland Reg Minist Agr & Rural Affairs Shihezi 832003 Peoples R China Chinese Acad Agr Sci Western Agr Res Ctr Changji 831100 Peoples R China

TBL (Trichome Birefringence Like) gene family members are involved in trichome initiation and xylan acetylation in several plant species. In our research, we identified 102 TBLs from G. hirsutum. The phylogenetic tree classified TBL genes into five groups. Collinearity analysis of TBL genes indicated 136 paralogous gene pairs in G. hirsutum. Gene duplication indicated that WGD or segmental duplication contributed to the GhTBL gene family expansion. Promoter cis-elements of GhTBLs were related to growth and development, seed-specific regulation, light, and stress responses. GhTBL genes (GhTBL7, GhTBL15, GhTBL21, GhTBL25, GhTBL45, GhTBL54, GhTBL67, GhTBL72, and GhTBL77) exhibited upregulated response under exposure to cold, heat, NaCl, and PEG. GhTBL genes exhibited high expression during fiber development stages. Two GhTBL genes (GhTBL7 and GhTBL58) showed differential expression at 10 DPA fiber, as 10 DPA is a fast fiber elongation stage and fiber elongation is a very important stage of cotton fiber development. Subcellular localization of GhTBL7 and GhTBL58 revealed that these genes reside inside the cell membrane. Promoter GUS activity of GhTBL7 and GhTBL58 exhibited deep staining in roots. To further validate the role of these genes in cotton fiber elongation, we silenced these genes and observed a significant reduction in the fiber length at 10 DPA. In conclusion, the functional study of cell membrane-associated genes (GhTBL7 and GhTBL58) showed deep staining in root tissues and potential function during cotton fiber elongation at 10 DPA fiber.

关键词： G hirsutum TBL Fiber development Phylogenetic analysis Gene silencing

来源：评论

学校读者我要写书评

暂无评论

Preparation and Properties of Pyrotechnic Binder Encapsulated α-AlH3 Composites by Solvent/Anti-solvent Method

引用

CHEMNANOMAT 2023年第5期9卷

作者： Shi, Zhe Lu, Taojie Hu, Yinghui Xu, Yidong wang, xuwen Wu, Zhuo Zheng, Jian Zhang, Jian Zhu, Zhaoyang Lin, Kaifeng Yang, Yulin Harbin Inst Technol Sch Chem & Chem Engn MIIT Key Lab Crit Mat Technol New Energy Convers & Harbin 150001 Peoples R China Hubei Inst Aerosp Chemotechnol Sci & Technol Aerosp Chem Power Lab Xiangyang 441003 Hubei Peoples R China China Aerosp Sci & Technol Corp 16 Fucheng Rd Beijing 100048 Peoples R China

Alpha-aluminum hydride (a-AlH3) is an ideal energetic combustion agent, but its poor stability and safety limit its application. Therefore, we prepare different composites by using the solvent/anti-solvent method to coat different pyrotechnic binders on the surface of a-AlH3. The vacuum stability test show that the minimum outgassing of Shellac-coated a-AlH3 composite is only 1.2 mL/g at 50 ? for 6 days. Due to the good electrical insulation properties of Viton, Viton-coated a-AlH3 composite have the highest E-50 value of electrostatic sensitivity. In addition, the pyrotechnic binders coating not only protects the activity of the a-AlH3 but also effectively increases its burning rate. Viton-coated a-AlH3 composite have more gaseous products and maximum flame area during combustion. This study illustrates that a-AlH3 coated with pyrotechnic binders is a means to address its stability and safety, laying the foundation for its application in solid propellants.

关键词： Pyrotechnic binder alpha-AlH3 Stability Safety Solid propellant

来源：评论

学校读者我要写书评

暂无评论

Dynamic analysis of floating wind turbines subjected to deterministic wind gusts

Dynamic analysis of floating wind turbines subjected to dete...

引用

作者： wang, xuwen Aalto University

学位级别：硕士

A wind turbine converts kinematic energy to electrical energy, and can be designed from onshore to offshore operation, then from shallow water to deep water. Compared to onshore wind turbines, floating wind turbines face more complicated environment conditions. To guarantee stability of floating wind turbines in various environment conditions, extreme wind and wave loads should be studied. This thesis focuses on the dynamic response in time domain under extreme deterministic wind gusts, in a return period of 50 years, for which simulations are carried out in order to assess the turbine’s performance and build a database: softwares SIMA, FAST and Matlab are used for the task. Based on equations of motion of platform, a simplified dynamic wind turbine model inspired by the DTU 10-MW RWT is built in Matlab to study extreme response subjected to deterministic gusts defined in DNV-OSJ103: Design of Floating Wind Turbine Structures. The simple model includes generator torque and a blade pitch control system converted from the NREL 5-MW turbine source code in FAST, written in Fortran. Extreme loads on the mooring system can be assessed by surge and pitch offsets of the platform in the output. Contrasting results from SIMA and Matlab and analyzing different gust shapes, the extreme (worst) deterministic gust are found.

关键词： wind turbine dynamic response deterministic gust Matlab SIMA FAST

来源：评论

学校读者我要写书评

暂无评论

Metabolomics coupled with SystemsDock reveal the protective effect and the potential active components of Naozhenning granule against traumatic brain injury

引用

JOURNAL OF ETHNOPHARMACOLOGY 2020年 246卷 112247-000页

作者： Cao, Jianhua Duan, Yahui Liu, Yanzhi Liu, Haixia Wei, Chunhong wang, Jiang Qin, Xuemei wang, xuwen Li, Zhenyu Shanxi Univ Modern Res Ctr Tradit Chinese Med Taiyuan 030006 Shanxi Peoples R China Shanxi Univ Coll Chem & Chem Engn Taiyuan 030006 Shanxi Peoples R China Shanxi Zhendong Ante Biol Pharmaceut Co Ltd Jinzhong 030600 Peoples R China

Ethnopharmacological relevance: Naozhenning granule (NZN), a widely traditional Chinese medicine (TCM) prescription with a long history of clinical, which is mainly used in the treatment of concussion, cerebral post-traumatic syndrome, consists of Di Huang (Radix of Rehmannia glutinosa (Gaertn.) DC.), Dang Gui (Radix of Angelica sinensis (Olio.) Diels), Chen Pi (Pericarpium of Citrus reticulata Blanco), Dan shen (Radix of Salvia Miltiorrhiza Bunge.), Di Long (Pheretima aspergillum (E. Perrier)), Mu Dan Pi (Cortex of Paeonia suffruticosa Andrews), Suan Zao Ren (Semen of Ziziphus jujuba Mill.), Chuan Xiong (Rhizoma of Ligusticum striatum DC.), Zhu Ru (Phyllostachys nigra (Lodd. Ex Lindl.) Munro), Bai Zi Ren (Semen of Platycladus orientalis (L.) Franco) and Fu Ling (sclerotium of Poria cocos (Schw.)Wolf). Aim of the study: This study aimed to unravel the mechanism and material basis of NZN against traumatic brain injury. Materials and methods: In this study, a H-1 nuclear magnetic resonance (NMR) based metabolomic approach combined with systemsDock was employed to study the protective effect of NZN against traumatic brain injury using a cerebral concussion rat model. The morris water maze test and biochemical indexes were used to evaluate the efficacy of NZN. Results: The results of morris water maze test suggested NZN can improve the spatial learning and memory of model rats, and the superoxide dismutas (SOD) and malonyldialdehyde (MDA) level indicated that the effect of NZN was related with the regulation of oxidative stress. Multivariate analysis revealed that the effect of NZN was related with regulation of 18 brain metabolites, and the corresponding metabolic pathways were further revealed by MetPA analysis. 13 serum absorbed components were found to hit the targets both related with the metabolic regulation and cerebral trauma through systemsDock-aided molecular docking experiments, and these compounds might be served as the active compounds in NZN against cerebr

关键词： Naozhenning granule Cerebral concussion Metabolomics Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Encapsulated boron-based energetic spherical composites with improved reaction efficiency and combustion performance

引用

CHEMICAL ENGINEERING JOURNAL 2022年第Part1期433卷 134478-134478页

作者： Hu, Yinghui wang, xuwen Zhang, Jian Zhu, Zhaoyang Ren, Xiaoting Yang, Yulin Lin, Kaifeng Pang, Aimin Shuai, Yong Harbin Inst Technol Sch Chem & Chem Engn MIIT Key Lab Crit Mat Technol New Energy Convers Harbin 150001 Peoples R China Harbin Inst Technol Sch Energy Sci & Engn Harbin 150001 Peoples R China Hubei Inst Aerosp Chemotechnol Sci & Technol Aerosp Chem Power Lab Xiangyang 441003 Hubei Peoples R China

The low energy release efficiency seriously hinders the application of Boron (B) powder as metal fuel in solid propellants. To overcome this issue, a series of B-based spherical composites were produced by encapsulating B based metastable intermixed composites (MICs) with ammonium perchlorate (AP) by a solvent evaporation induced self-assembly (EISA) method in this work. A self-developed combustion system containing an ignition pool, indicator light, and high-speed camera to precisely monitor ignition delay and burning times was utilized. The EISA-prepared B/Bii(2)O(3)/AP spherical composites showed higher combustion temperature (1435 ?) and shorter ignition delay time (379 & PLUSMN;25 ms) than the physically mixed sample (1264 ? and 1035 & PLUSMN;63 ms). The isolated reaction units of spherical B/Bi2O3/AP composite accelerated heat transfer and accumulation and reduced sintering and agglomeration, thus promoting the combustion efficiency of B powder. This study presents a promising strategy by doping and encapsulating process to increase the combustion performance of B-based metal fuel.

关键词： Boron-based Energetic Composites Encapsulated Structure EISA Method Combustion Performance Reaction Mechanism

来源：评论

学校读者我要写书评

暂无评论

健康教育对高血压、糖尿病人群流感、肺炎疫苗接种率的影响分析

引用

公共卫生与预防医学 2024年第4期35卷 133-136页

作者：钱星王旭雯修仕信江苏省无锡市疾病预防控制中心江苏无锡214023

目的评价健康教育对高血压、糖尿病人群流感、肺炎疫苗接种知信行的影响。方法采用多阶段随机抽样方法选取研究对象,开展健康教育并随访,通过自身对照干预前后疾病和疫苗认知及接种情况。结果干预后末次随访时有2.45%的研究对象接种... 详细信息

目的评价健康教育对高血压、糖尿病人群流感、肺炎疫苗接种知信行的影响。方法采用多阶段随机抽样方法选取研究对象,开展健康教育并随访,通过自身对照干预前后疾病和疫苗认知及接种情况。结果干预后末次随访时有2.45%的研究对象接种了流感疫苗,高于干预前的0.74%(P<0.05),9.81%的研究对象接种了肺炎疫苗,高于干预前的0.49%(P<0.05)。3次随访中认为高血压和糖尿病患者更容易患肺炎的分别占32.37%、41.00%、38.11%,均高于干预前的30.36%(P<0.05);认为患肺炎会加重高血压、糖尿病病情的分别占37.22%、44.92%、41.39%,均高于干预前的35.80%(P<0.05);认为有必要接种疫苗的分别占40.02%、52.62%、50.02%,总体高于干预前的40.07%(P<0.05)。结论高血压、糖尿病人群对流感和肺炎疫苗的认知、接种意愿和接种率均较低,针对性健康教育的干预措施可以提高人群疫苗预防接种的知信行水平,提高人群的疫苗接种率。

关键词：高血压糖尿病流感疫苗肺炎疫苗健康教育

来源：评论

学校读者我要写书评

暂无评论

Identifying concepts from medical images via transfer learning and image retrieval

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2019年第4期16卷 1978-1991页

作者： wang, xuwen Zhang, Yu Guo, Zhen Li, Jiao Chinese Acad Med Sci Inst Med Informat & Lib Peking Union Med Coll Beijing 100020 Peoples R China

Automatically identifying semantic concepts from medical images provides multimodal insights for clinical research. To study the effectiveness of concept detection on large scale medical images, we reconstructed over 230,000 medical image-concepts pairs collected from the ImageCLEFcaption 2018 evaluation task. A transfer learning-based multi-label classification model was used to predict multiple high-frequency concepts for medical images. Semantically relevant concepts of visually similar medical images were identified by the image retrieval-based topic model. The results showed that the transfer learning method achieved F1 score of 0.1298, which was comparable with the state of art methods in the ImageCLEFcaption tasks. The image retrieval-based method contributed to the recall performance but reduced the overall F1 score, since the retrieval results of the search engine introduced irrelevant concepts. Although our proposed method achieved second-best performance in the concept detection subtask of ImageCLEFcaption 2018, there will be plenty of further work to improve the concept detection with better understanding the medical images.

关键词： concept detection transfer learning multi-label classification medical image retrieval LDA

来源：评论

学校读者我要写书评

暂无评论

Process Parameters Analysis and Artificial Neural Network Prediction for Color Variation after Laser Induced Ti-6Al-4V Surface Coloring

SSRN

引用

SSRN 2023年

作者： Zhou, Kai Wu, Xin Zeng, Hui Che, Xingbang wang, xuwen Xiao, Han Yang, Can Yang, Huan Ruan, Shuangchen Li, Chunbo Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen518118 China School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China DH Automation Technology Co. Ltd Shenzhen518110 China Key Laboratory of Advanced Optical Precision Manufacturing Technology Guangdong Higher Education Institutes Shenzhen Technology University Shenzhen518118 China

Metal surface coloring process is considered as a process with strong technical influence because its’ advantage in improving the appearance of metal, identifying metal products with information, preventing corrosion of metal substrate, excellent color stability and other characteristics. Laser induced metal coloring is expected to become a metal coloring process with stability and efficiency for its quickly response in producing bright colors on the metal matrix by simply setting the process parameters. The process is simple and with excellent efficiency and accuracy. At present, in the field of laser induced coloring, the main method is to find the corresponding relationship between laser energy density and color formation with a large number of laser parameters, the main limit in this method comes from lacking convenience to reproduce color s within costing a great deal of time. How to establish the nonlinear relationship between metal coloring process and specific color formation is still a challenge. Here, we observed thousands of laser-induced Ti-6Al-4V coloring test data in efficient way, based on the color evaluation index of CIE1976 color system and the theory of Multilayer Perceptron algorithm. It is proved that the color produced by the laser is highly matched with the color predicted by training of Multi-layer Perceptron algorithm. The precision difference brought by different algorithm strategies is compared, attempted to find the algorithm strategy that is capable of predicting color formation with high accuracy. This study provides a feasible method for the application of laser coloring to the industrial field. © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：