检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Ching-Hsuan Liu Chih-Ming Chen Jing-Kai Lou Ming-Feng Tsai Jiun-Lang Huang Chuan-Ju Wang Data Science Degree Program National Taiwan University Academia Sinica Taiwan Research Center for Information Technology Innovation Academia Sinica KKCompany Taiwan Department of Computer Science National Chengchi University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This paper introduces SARA, a semantic-assisted reinforced active learning framework for enhancing entity alignment (EA) under limited supervision scenarios. SARA addresses the challenges of EA in real-world scenarios, including knowledge graph heterogeneity and limited training ground truth. SARA effectively selects valuable entity pairs with limited labeled data by combining reinforced active learning and semantic information. It utilizes a pair-wise language model based on Sentence-BERT to learn informative name embeddings that capture entity name semantics. These embeddings are combined with structural embeddings and trained using a novel semantic-assisted alignment loss. Extensive experiments on benchmark datasets and a real-world dataset demonstrate the superiority of SARA over existing approaches, particularly in limited labeled data scenarios. The paper also provides insights into fine-tuning strategies, presents ablation studies, and conducts sensitivity analyses to validate the effectiveness of SARA.

关键词： Training Sensitivity analysis Semantics Neural networks Knowledge graphs Benchmark testing data models

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of University Teaching Equipment Management Information System

引用

Journal of Cyber Security 2021年第3期3卷 177-185页

作者： Yu Xue Xiang Jiao Chishe Wang Huanlun Chen Moayad Aloqaily School of Computer and Software Nanjing University of Information Science and TechnologyNanjingChina Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of TechnologyNanjingChina Faculty of Engineering Al Ain UniversityAl AinUnited Arab Emirates NUIST Students’Platform for Innovation and Entrepreneurship Training Program NanjingChina

Teaching equipment management is an important factor for colleges and universities to improve their teaching level,and its management level directly affects the service life and efficiency of teaching *** in recent years,our university recruitment of students scale is increasing year by year,the size of the corresponding teaching equipment is also growing,therefore to develop a teaching equipment management information system is necessary,not only can help universities to effective use of the existing teaching resources,also can update scrap equipment,related equipment maintenance,and build a good learning environment to students and to the improvement of the teaching quality of colleges and universities play a reliable safeguard *** paper first introduces some common development tools,and then analyzes the user functional requirements and data requirements of the system,and analyzes the feasibility of the system development from many aspects,finally based on B/S mode,using Java language,JSP technology and MySQL database design and implementation of a teaching equipment management information *** main functional modules of the system include equipment basic information management,equipment loan and return information management,equipment maintenance information management,equipment scrap information management,the interface of each functional module is shown in the paper.

关键词： Information systems teaching equipment management system analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Enterprise Recruitment Mini program

引用

Journal of Cyber Security 2021年第3期3卷 125-132页

作者： Yu Xue Nan Wei Junyang Han Chishe Wang Moayad Aloqaily School of Computer and Software Nanjing University of Information Science and TechnologyNanjingChina Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of TechnologyNanjingChina Faculty of Engineering Al Ain UniversityAl AinUnited Arab Emirates NUIST Students’Platform for Innovation and Entrepreneurship Training Program NanjingChina

Since the 21st century,the Internet has been updated and developed at an alarming *** the same time,WeChat applets are constantly improving and introducing new *** an enterprise recruitment system based on WeChat applets for the majority of job seekers and recruiter users,provide job seekers with easy-to-reach employment opportunities,and provide a convenient and clear screening environment for job *** front-end part of the applet is developed using WeChat developer tools,and the back-end system is developed using *** Spring Boot+Spring MVC framework,implemented in Java *** is managed using MySql *** function of this company’s recruitment applet is similar to the ordinary traditional native recruitment *** achieves basic functions such as job search,job search,collection of jobs,delivery of resumes,viewing of the job search process,recruitment of job information,screening of job resumes,notification of interviews,etc.

关键词： Mini-program recruitment WeChat developer tools MyEclipse

来源：评论

学校读者我要写书评

暂无评论

Research on the Spillover Effects of Digital Transformation on the Sustainable Growth of Green Schools

引用

Proceedings of Business and Economic Studies 2023年第6期6卷 16-23页

作者： Yiting Qiu Qiuhua Chen Poh Soon Joseph Ng Zhejiang Technical Institute of Economics Hangzhou 3018Zhejiang ProvinceChina Innovation and Technology Program Engineering and Quantity SurveyingINTI International UniversityNilai 71800Negeri SembilanMalaysia Faculty of Data Science and Information Technology INTI International UniversityNilai 71800Negeri SembilanMalaysia

The development of society and the advancement of science and technology have led to the widespread integration of digital transformation in the field of ***,the current establishment of green schools faces various challenges,including non-environmental building facilities,high renovation costs,low organizational management efficiency,high energy consumption,outdated office tools,and insufficient environmental awareness among teachers and *** thorough research and analysis,it becomes evident that digital technology can play a pivotal role in addressing these challenges and contribute to all aspects of green school *** incorporation of digital thinking concepts is essential for the construction of ecologically civilized campuses and inclusive *** process of digital design and transformation proves instrumental in optimizing both software and hardware facilities within the campus,thereby reducing energy ***,comprehensive digital teaching management enhances overall efficiency in management and service *** digital teaching and learning models emerge as transformative tools,providing new avenues to create low-carbon,green classrooms for both teachers and *** exploring the application of digital transformation in establishing green schools and examining the resulting spillover effects,valuable insights can be *** insights,in turn,serve as reference points for building diversified digital technology paths on campus and fostering the creation of green schools.

关键词： Digital transformation Green schools Spillover effect

来源：评论

学校读者我要写书评

暂无评论

TreeXGNN: can gradient-boosted decision trees help boost heterogeneous graph neural networks?

TreeXGNN: can gradient-boosted decision trees help boost het...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ming-Yi Hong Shih-Yen Chang Hao-Wei Hsu Yi-Hsiang Huang Chih-Yu Wang Che Lin Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Graph neural networks are a promising deep learning method that can apply graph structures to various tasks. In real-world scenarios, we often have heterogeneous graphs, wherein different node and edge types capture complex interactions between nodes. High-dimensional node features provide rich information about the target nodes. Conventional heterogeneous graph neural networks (HGNN) focus more on graph structures than node features and may have difficulties extracting knowledge from complex node features. In this study, we propose a novel framework, the tree-boosted heterogeneous graph neural network abbreviated as TreeXGNN, which could efficiently and automatically extract target node features via gradient-boosted decision trees (GBDT). It integrates community structure information with proper fusion modules and a shared feature space design on HGNN. We achieved state-of-the-art performance on the three well-known heterogeneous graph benchmark datasets, IMDB, DBLP, and ACM, and significantly improved performance compared to previous studies. Our work paves the foundation for integrating tree-based models to boost HGNNs for general community analysis.

关键词： Training Knowledge engineering Deep learning Signal processing Feature extraction Graph neural networks Decision trees

来源：评论

学校读者我要写书评

暂无评论

Association between outdoor air pollutant exposure and refractive error changes: A retrospective clinical practice study

引用

Scientific Reports 2025年第1期15卷 1-12页

作者： Huang, Yu-Te Tien, Peng-Tai Chen, Jamie Jiin-Yi Wu, Ming-Yen Meng, Ping-Ping Yip, Hei-Tung Lin, Hui-Ju Yang, Tse-Yen Wan, Lei Eye Center China Medical University Hospital China Medical University Taichung 404327 Taiwan School of Medicine China Medical University Taichung 404328 Taiwan Management office for Health Data China Medical University Hospital Taichung 404327 Taiwan College of Medicine China Medical University Taichung 404328 Taiwan School of Chinese Medicine College of Chinese Medicine China Medical University No. 91 XueShi Road Taichung 404328 Taiwan Molecular and Genomic Epidemiology Center Department of Medical Research China Medical University Hospital Taichung 404327 Taiwan Department of Medical Laboratory Science and Biotechnology College of Medical and Health Science Asia University Taichung 413305 Taiwan Center for General Education China Medical University No. 100 Section 1 JingMao Road Taichung 406040 Taiwan Master Program of Digital Health Innovation College of Humanities and Sciences China Medical University Taichung 406040 Taiwan Department of Obstetrics and Gynecology China Medical University Hospital Taichung 404327 Taiwan

In recent decades, the impact of air pollution on eye health has been emphasized, but the effect of air pollution on changes in refractive error is still unknown. A comprehensive retrospective cohort study was conducted to address this, utilizing the China Medical University Hospital Clinical Research data Repository (CMUH-CRDR). It included 4,399 participants aged 6–12 years, with 2,166 females and 2,223 males, who visited the ophthalmology department between 2003 and 2019, ensuring a robust and representative sample. The mean age was 7.04 years (± 2.20), and the change in refractive error was highest in subjects aged between 7 and 9. Cumulative exposure to delicate particulate matter (PM_2.5), carbon monoxide (CO), nitrogen oxides (NOx), ozone (O₃), and sulfur dioxide (SO₂) from the index date to the end of the follow-up was calculated to examine the association between air pollutants and myopia progression. The study found a clear dose-effect relationship, as the change in refractive error progressively increased with higher levels of PM_2.5, CO, and O₃, with exposure to the highest levels resulting in a considerably significant change (p < 0.05). For every quantile increase in PM_2.5, CO, NOx, O₃, and SO₂, the average change in refractive error decreased by approximately 0.3 D. Among the five air pollutants analyzed, CO had the most significant effect with just one unit increase. PM_2.5 had the most significant impact on refractive error in patients among different age groups (age 5–6, β: − 0.40;age 7–9, β: − 0.47;age 10–12, β: − 0.35). In conclusion, exposure to air pollutants, including PM_2.5, CO, SO₂, NOx, and O₃, increases the risk of myopic progression in children aged between 6 and 12 years old, emphasizing the need for better air quality control measures to protect children’s eye health and prevent myopia progression. © The Autho

关键词： Air pollution Health data Myopia PM2.5 Refractive error

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to Lung Nodule Growth Prediction using CT image combined with Demographic and image features 23

A deep learning approach to Lung Nodule Growth Prediction us...

引用

7th International Conference on Medical and Health Informatics, ICMHI 2023

作者： Li, Ai-Hsien Adams Nguyen, Duc-Khanh Lai, Yen-Jun Chien, Ting-Ying Chiu, Yen-Ling Chan, Chien-Lung Yang, Pan-Chyr Division of Cardiology Far Eastern Memorial Hospital Taipei220 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan Department of Information Management Yuan Ze University Taoyuan320 Taiwan Department of Radiology Far Eastern Memorial Hospital Taipei220 Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital Taipei Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan320 Taiwan Institute of Biomedical Sciences Academia Sinica Taipei106 Taiwan Department of Internal Medicine College of Medicine National Taiwan University Taipei100 Taiwan Center of Genomic Medicine National Taiwan University Taipei100 Taiwan

ISBN: (纸本)9798400700712

Lung cancer remains a significant global public health concern, being the leading cause of cancer-related deaths worldwide. Despite recent medical advancements, the disease still has a high mortality rate, making early detection and treatment critical for improving patient outcomes. Accurate prediction of nodule growth is key to early lung cancer treatment, but current assessments offer unclear indications of future growth, leading physicians to recommend costly and anxiety-provoking follow-up appointments every 3 to 12 months. To address this need, this study develops an ensemble deep learning approach that combines demographic data with existing CT images to predict whether lung nodules will grow, potentially reducing unnecessary examinations and easing the burden on patients. Our study, conducted on 862 patients with 1004 nodules, produced promising preliminary results with Accuracy, Sensitivity, Precision, F1 Score, and AUC of 0.66, 0.66, 0.67, 0.66, and 0.71, respectively. The proposed method provides a promising support system to empower patients to make informed decisions about seeking medical attention and helps physicians facilitate early treatment regimens, leading to improved patient outcomes and potentially saving lives. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Structural analysis based on unsupervised learning: Search for a characteristic low-dimensional space by local structures in atomistic simulations

引用

Physical Review B 2022年第7期105卷 075107-075107页

作者： Ryo Tamura Momo Matsuda Jianbo Lin Yasunori Futamura Tetsuya Sakurai Tsuyoshi Miyazaki International Center for Materials Nanoarchitectonics National Institute for Materials Science Tsukuba 305-0044 Japan Research and Services Division of Materials Data and Integrated System National Institute for Materials Science Tsukuba 305-0044 Japan Graduate School of Frontier Sciences The University of Tokyo Chiba 277-8568 Japan Department of Computer Science University of Tsukuba Tsukuba 305-8573 Japan Center for Artificial Intelligence University of Tsukuba Tsukuba 305-8573 Japan Master's/Doctoral Program in Life Science Innovation University of Tsukuba Tsukuba 305-8577 Japan

Owing to the advances in computational techniques and the increase in computational power, atomistic simulations of materials can simulate large systems with higher accuracy. Complex phenomena can be observed in such state-of-the-art atomistic simulations. However, it has become increasingly difficult to understand what is actually happening and mechanisms, for example, in molecular dynamics (MD) simulations. We propose an unsupervised machine learning method to analyze the local structure around a target atom. The proposed method, which uses the two-step locality preserving projections (TS-LPP), can find a low-dimensional space wherein the distributions of data points for each atom or groups of atoms can be properly captured. We demonstrate that the method is effective for analyzing the MD simulations of crystalline, liquid, and amorphous states and the melt-quench process from the perspective of local structures. The proposed method is demonstrated on a silicon single-component system, a silicon-germanium binary system, and a copper single-component system.

关键词： Amorphous materials Machine learning Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Randomized Spline Trees for Functional data Classification: Theory and Application to Environmental Time Series

arXiv

引用

arXiv 2024年

作者： Riccio, Donato Maturo, Fabrizio Romano, Elvira Machine Learning Engineer and Student in the Data Science Master’s Degree Program The University of Campania Luigi Vanvitelli Caserta Italy Department of Economics Statistics and Business Faculty of Technological and Innovation Sciences Universitas Mercatorum Rome Italy Department of Mathematics and Physics University of Campania Luigi Vanvitelli Caserta Italy

Functional data analysis (FDA) and ensemble learning can be powerful tools for analyzing complex environmental time series. Recent literature has highlighted the key role of diversity in enhancing accuracy and reducing variance in ensemble *** paper introduces Randomized Spline Trees (RST), a novel algorithm that bridges these two approaches by incorporating randomized functional representations into the Random Forest framework. RST generates diverse functional representations of input data using randomized B-spline parameters, creating an ensemble of decision trees trained on these varied representations. We provide a theoretical analysis of how this functional diversity contributes to reducing generalization error and present empirical evaluations on six environmental time series classification tasks from the UCR Time Series Archive. Results show that RST variants outperform standard Random Forests and Gradient Boosting on most datasets, improving classification accuracy by up to 14%. The success of RST demonstrates the potential of adaptive functional representations in capturing complex temporal patterns in environmental data. This work contributes to the growing field of machine learning techniques focused on functional data and opens new avenues for research in environmental time series *** Codes 62M10, 68T05, 65D07, 68T10 © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

ZokorDB: tissue specific regulatory network annotation for non-coding elements of plateau zokor

引用

Quantitative Biology 2020年第1期8卷 43-50页

作者： Jingxue Xin Junjun Hao Lang Chen Tao Zhang Lei Li Luonan Chen Wenmin Zhao Xuemei Lu Peng Shi Yong Wang CEMS NCMISMDISAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China State Key Laboratory of Genetic Resources and Evolution Laboratory of Evolutionary and Functional GenomicsKunming Institute of ZoologyChinese Academy of SciencesKunming 650223China Key Laboratory of Systems Biology Innovation Center for Cell Signaling NetworkInstitute of Biochemistry and Cell BiologyShanghai Institutes for Biological SciencesChinese Academy of SciencesShanghai 200031China Beijing Institute of Genomics Chinese Academy of SciencesBeijing 100101China Center for Excellence in Animal Evolution and Genetics Chinese Academy of SciencesKunming 650223China Department of Statistics Department of Biomedical Data ScienceBio-X ProgramStanford UniversityStanfordCA 94305USA University of Chinese Academy of Sciences Beijing 100049China

Background:Plateau zokor inhabits in sealed burrows from 2,000 to 4,200 meters at Qinghai-Tibet *** extreme living env ironment makes it a great model to study animal adaptation to hypoxia,low temperature,and high carbon dioxide ***:We provide an integrated resource,ZokorDB,for tissue specific regulatory network annotation for *** is based on a high-quality draft genome of a plateau zokor at 3,300 m and its transcriptional profiles in brain,heart,liver,kidney,and *** conserved non-coding elements of zokor are annotated by their nearest genes and upstream transcriptional factor motif binding ***:ZokorDB provides a general draft gene regulatory network(GRN),Le?potential transcription factor(TF)binds to non-coding regulatory elements and regulates the expression of target genes(TG).Furthermore,we refined the GRN by incorporating matched RNA-seq and DNase-seq data from mouse ENCODE project and reconstructed five tissue-specific regulatory ***:A web-based,open-access database is developed for easily searching,visualizing,and downloading the annotation and *** pipeline of non-coding region annotation for zokor will be useful for other non-model *** is free available at the website(***/zokordb/).

关键词： tissue specific regulatory network non-coding element plateau zokor non-model species

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：