检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Roh, Daeyoung Han, Donghee Kim, Daehee Han, Keejun Yi, Mun Graduate School of Data Science KAIST Korea Republic of School of Computer Engineering Hansung University Korea Republic of Department of Industrial and Systems Engineering KAIST Korea Republic of

Hypergraphs provide a superior modeling framework for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, overcoming the limitations of traditional homogeneous graphs. However, there have been few studies on hypergraph-based contrastive learning, and existing graph-based contrastive learning methods have not been able to fully exploit the high-order correlation information in hypergraphs. Here, we propose a Hypergraph Fine-grained contrastive learning (HyFi) method designed to exploit the complex high-dimensional information inherent in hypergraphs. While avoiding traditional graph augmentation methods that corrupt the hypergraph topology, the proposed method provides a simple and efficient learning augmentation function by adding noise to node features. Furthermore, we expands beyond the traditional dichotomous relationship between positive and negative samples in contrastive learning by introducing a new relationship of weak positives. It demonstrates the importance of fine-graining positive samples in contrastive learning. Therefore, HyFi is able to produce high-quality embeddings, and outperforms both supervised and unsupervised baselines in average rank on node classification across 10 datasets. Our approach effectively exploits high-dimensional hypergraph information, shows significant improvement over existing graph-based contrastive learning methods, and is efficient in terms of training speed and GPU memory cost. The source code is available at https://***/Noverse0/***. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 2024 IEEE Open Conference of Electrical, Electronic and Information sciences (eStream’ 2024)

Proceedings of the 2024 IEEE Open Conference of Electrical, ...

引用

Electrical, Electronic and Information sciences (eStream), Open Conference of

作者： Dalius Navakauskas Ćarūnas Paulikas Tomyslav Sledevič Dainius Udris Department of Electronic Systems Vilnius Lithuania Department of Computer Science and Communications Technologies Vilnius Lithuania Department of Electrical Engineering Vilnius Lithuania

ISBN: (数字)9798350352412

ISBN: (纸本)9798350352429

We are very glad to welcome our colleagues - young scientists, researchers and practitioners to the 11-th IEEE Open Conference of Electrical, Electronic and Information sciences (eStream‘ 2024), held in Vilnius Gediminas Technical University (VILNIUS TECH), Vilnius, Lithuania, on 25 April 2024. The eStream conferences aim to disseminate the research achievements between worldwide groups of scientists and engineers working in different areas of science to reach more tight relationships and generate new ideas for joint projects or other means of collaboration.

关键词： Collaboration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Accuracy in Cardiovascular Disease Diagnosis: A Hybrid Approach Using RFAP Feature Selection and Random Forest Modeling 4

Enhancing Predictive Accuracy in Cardiovascular Disease Diag...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Pasupuleti, Vikram Thuraka, Bharadwaj Kodete, Chandra Shikhi Priyadarshini, V. Kumar Tirumanadham, Koti Mani Shariff, Vahiduddin Eastern Illinois University School of Technology CharlestonIL61920 United States Northwest Missouri State University School of Computer Science and Information Systems MaryvilleMO64468 United States SRKR Engineering College Department of CSE Bhimavaram India Sir C R Reddy College of Engineering Department of CSE Eluru India

ISBN: (纸本)9798331515720

Cardiovascular disease remains one of the leading causes of death all over the world and is characterized by ailments affecting cardiovascular structures, such as the heart failure, arrhythmia, and coronary artery diseases. It has multiple roots based on genetic influences on the disease, meals, drinks, physical inactivity, or presence of other diseases including hypertension, and diabetes. Heart diseases are still rampant in the world despite the development in the research on diseases and in healthcare. This is mainly because of the increasing average life span of individuals as well as increased cases of urbanization and adoption of poor-quality diets and leading inactive or sedentary lives. Such problems further escalate due to shortcomings in healthcare provision and preventive options by socioeconomic differences, especially affecting the needy populace. Hence, there is a rising focus on using complex technologies such as artifices and machine intelligence, along with big data analytics and predictive models, in handling these issues. These methodologies utilize computational methods and large-scale data to enhance risk assessment, optimize treatment pathways, and alleviate the overall burden of cardiac disease on healthcare systems and individuals. The concentration of this research is on the systematic application of rigorous data preprocessing, class imbalance correction using techniques such as SMOTE, and outlier management using methods such as IQR, in order to improve the effectiveness of predictive modelling. This study intends to improve predictive accuracy and model generalizability, thereby contributing to improvements in healthcare decision-making and patient care outcomes, by utilizing the RFAP hybrid technique for feature selection and Random Forest for modelling. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Multi-VM-Workloads Learning-based Forecasting Model for Resilient Server Management in Industry Clouds

引用

Procedia computer science 2025年 260卷 923-929页

作者： Deepika Saxena Ashutosh Kumar Singh Division of Information Systems University of Aizu Aizuwakamatsu 965-0006 Fukushima Japan Department of Computer Science and Engineering Indian Institute of Information Technology Bhopal Bhopal 462003 Madhya Pradesh India

Forecasting server contention in large-scale cloud data center networks is crucial for efficient cloud resource management. The existing research primarily focuses on single-task machine learning methods for predicting resource-constrained VM failures, which often results in lower accuracy and higher computational costs. To overcome these challenges, this paper introduces a novel approach aimed at enhancing resilient server management in industry clouds. The proposed approach develops Multi-tasks-Learning-based Long Short-Term Memory for multiple VMs workload forecasting model named MVL-LSTM to simultaneously learn resource requirements of all VM hosted on a common server. It facilitates a single-step forecasting of workload resource requirements for all VM segments hosted on a server within a cluster. Experimental results using real-world Google Cluster VM datasets demonstrate that MVL-LSTM significantly improves forecasting accuracy while achieving faster execution and higher energy efficiency compared to existing single-task machine learning algorithms. Specifically, MVL-LSTM model achieves a 15% reduction in processing time and a 50% decrease in energy consumption compared with LSTM-based approach.

关键词： Cloud computing VM failure prediction MVL-LSTM Server management

来源：评论

学校读者我要写书评

暂无评论

Heavy-traffic optimal size- and state-aware dispatching 24

Heavy-traffic optimal size- and state-aware dispatching

引用

2024 ACM SIGMETRICS/IFIP Performance Conference on Measurement and Modeling of computer systems, SIGMETRICS/PERFORMANCE 2024

作者： Xie, Runhan Grosof, Isaac Scully, Ziv Department of Industrial Engineering and Operations Research University of California Berkeley BerkeleyCA United States Carnegie Mellon University Computer Science Department PittsburghPA United States Georgia Institute of Technology School of Industrial and Systems Engineering AtlantaGA United States School of Operations Research and Information Engineering Cornell University IthacaNY United States

ISBN: (纸本)9798400706240

We study the problem of dispatching jobs to multiple FCFS (First-Come, First-Served) queues. We consider the case where the dispatcher is size-aware, meaning it learns the size (i.e. service time) of each job as it arrives;and state-aware, meaning it always knows the amount of work (i.e. total remaining service time) at each queue. While size- and state-aware dispatching to FCFS queues has been extensively studied, little is known about optimal dispatching for the objective of minimizing mean delay. In this work, we propose the first size- and state-aware dispatching policy, called CARD (Controlled Asymmetry Reduces Delay), that provably minimizes mean delay in heavy traffic. This work summarizes our full paper. © 2024 Copyright held by the owner/author(s).

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Pediatric Bone Age Prediction Using Deep Learning

Pediatric Bone Age Prediction Using Deep Learning

引用

International Conference on computer and Information Technology (ICCIT)

作者： Al Zadid Sultan Bin Habib Md. Ekramul Islam Md Asif Bin Syed Md Younus Ahamed Tanpia Tasnim Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown USA Department of Computer Science & Engineering Stamford University Bangladesh Dhaka Bangladesh Department of Industrial and Management Systems Engineering West Virginia University Morgantown USA Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh

Pediatric bone age prediction is a crucial task in clinical practice that can help diagnose endocrine disorders and provide insight into a child’s growth and development. However, conventional bone age prediction methods are often labor-intensive and require specialized radiological expertise. This paper presents a Deep Learning (DL)-based approach to pediatric bone age prediction using EfficientNet with Additive Attention, a state-of-the-art neural network architecture for image classification and regression tasks. The method utilizes over 12,000 X-ray images from the RSNA bone age dataset. It involves image preprocessing, transforming them into three-channel images, and training a Convolutional Neural Network (CNN) to automatically learn the features of hand bone images. This approach provides a more effective and accurate solution for predicting bone age, which is critical in diagnosing pediatric endocrine diseases. This work uses two variations of the EfficientNet model (B0 and B4), where EfficientNetB4 is also finetuned with the Additive Attention mechanism. These three models predict the age for the original age, and their comparison is shown in curves. The predicted ages depict that in most cases, EfficientNetB4 and EfficientNetB4 with Additive Attention (EN-AA) successfully predicted the bone ages more accurately regarding the original age, and their performance was better than the EfficientNetB0. Specific performance metrics are provided to underscore this improvement. Learning curves for training and validation loss confirm effective learning without overfitting or underfitting, further validating our approach’s efficacy in pediatric endocrine disease diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniAdapter: All-in-One Control for Flexible Video Generation

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 6059-6073页

作者： Wang, Cong Hu, Panwen Zhao, Haoyu Guo, Yuanfan Gu, Jiaxi Dong, Xiao Han, Jianhua Xu, Hang Liang, Xiaodan Chinese University of Hong Kong Hong Kong School of Science and Engineering Shenzhen China Fudan University School of Computer Science and Technology Shanghai China Huawei Noah'ark Lab Shanghai201206 China Sun Yat-Sen University School of Artificial Intelligence Zhuhai Campus Zhuhai519082 China Shenzhen Campus of Sun Yat-sen University School of Intelligent Systems Engineering Guangdong No. 66 Gongchang Road Guangming District Shenzhen518107 China Peng Cheng Laboratory and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

Condition-based video generation aims to create video content based on given information that describes specific subjects. However, most existing works can only utilize a single condition to guide the denoising process, thereby limiting their applicability to specific scenarios. Although some works attempt to accommodate multiple conditions within one framework, they often require multiple encoders, leading to inefficiencies in integrating multi-condition features. In this work, we present a framework that, with the support of the proposed Unified Adapter (UniAdapter), enables simultaneous multi-condition control of video generation within a single model. To effectively merge these conditions, we propose a novel Probabilistic Multi-condition Concatenator (PMC) module, which employs a unified encoder to accommodate multiple conditions and concatenate condition features at the pixel level to achieve fine-grained control. Following the PMC module, we employ 2D down-sampling blocks to refine features for injection into the Video Diffusion Model (VDM). Moreover, our UniAdapter is designed to be model-agnostic and compatible with any U-Net-based VDM, offering a versatile solution for improving video generation quality. Experimental results on public benchmarks UCF-101 and MSR-VTT show that our method achieves superior results in both quantitative and qualitative evaluations. © 2025 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Empowering the adoption of blockchain-based cryptocurrency as a payment method: A user-friendly educational approach

IET Blockchain

引用

IET Blockchain 2025年第1期5卷

作者： Alrehaili, Ahmed White, Martin Beloff, Natalia University of Sussex School of Engineering and Informatics Informatics Brighton United Kingdom Islamic University of Madinah College of Computing and Information Systems Computer Science Department Medina Saudi Arabia

Organizations are adopting technological innovations to transform payment systems due to challenges with traditional methods, such as slow speed and high fees. These challenges have prompted a shift towards blockchain-based cryptocurrencies. However, cryptocurrency adoption for payments remains limited, especially in Saudi Arabia. This study adapts the technology acceptance model to explore cryptocurrency adoption through the blockchain-based cryptocurrency as a payment method in Saudi Arabia (BCAP-SA) model. Factors within the model are assessed using an experimental vignette-task methodology and surveys. A key component is an educational package, offering comprehensive materials to explain blockchain technology. The findings confirm the reliability of surveys. Most model factors are statistically significant in influencing users’ intention to use cryptocurrency. The study finds that perceived ease of use, perceived usefulness, and perceived trust significantly impact participants’ intentions. Additionally, low transaction fees and age are the most influential factors on the technology acceptance model's core constructs. Statistical analysis indicates that decentralization and anonymity were insignificant and thus excluded from the revised BCAP-SA model. These findings highlight the potential to enhance cryptocurrency adoption in Saudi Arabia. The study's insights can guide strategies to promote wider cryptocurrency usage in the region. © 2025 The Author(s). IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： blockchain platforms blockchains cryptocurrencies models and analysis

来源：评论

学校读者我要写书评

暂无评论

Encryption Algorithm for Securing Non-Disclosure Agreements in Outsourcing Offshore Software Maintenance

引用

computers, Materials & Continua 2022年第11期73卷 3827-3845页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Nadeem Iqbal Nazri Kama Azri Azmi Ahmad Salman Khan Yasir Mahmood Assad Alzayed Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala TerengganuMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Advanced Informatics Department Razak Faculty of Technology and InformaticsUniversiti Teknologi Malaysia54100Kuala LumpurMalaysia Computer Science and Information Systems Department College of Business Studies Public Authority for Applied Education and Training(PAAET)AdailiyaKuwait

Properly created and securely communicated,non-disclosure agreement(NDA)can resolve most of the common disputes related to outsourcing of offshore software maintenance(OSMO).Occasionally,these NDAs are in the form of *** the work is done offshore,these agreements or images must be shared through the Internet or stored over the *** breach of privacy,on the other hand,is a potential threat for the image owners as both the Internet and cloud servers are not void of *** article proposes a novel algorithm for securing the NDAs in the form of *** an agreement is signed between the two parties,it will be encrypted before sending to the cloud server or travelling through the public network,the *** the image is input to the algorithm,its pixels would be scrambled through the set of randomly generated rectangles for an arbitrary amount of *** confusion effects have been realized through an XOR operation between the confused image,and chaotic ***,5D multi-wing hyperchaotic system has been employed to spawn the chaotic vectors due to good properties of chaoticity it *** machine experimentation and the security analysis through a comprehensive set of validation metric vividly demonstrate the robustness,defiance to the multifarious threats and the prospects for some real-world application of the proposed encryption algorithm for the NDA images.

关键词： Non-disclosure agreement encryption decryption secret key chaoticmap confusion diffusion

来源：评论

学校读者我要写书评

暂无评论

Visualizing Student Attention in Smart Classrooms: A Preliminary Study 15

Visualizing Student Attention in Smart Classrooms: A Prelimi...

引用

15th International Conference on Innovations in Information Technology, IIT 2023

作者： Parambil, Medha Mohan Ambali Alhammadi, Amna Mohammed Abdulla Alnajjar, Fady Trabelsi, Zouheir Ali, Luqman Swavaf, Muhammed United Arab Emirate University Department of Information Systems and Security College of IT Al Ain United Arab Emirates United Arab Emirate University Department of Computer Science and Software Engineering College of IT Al Ain United Arab Emirates

ISBN: (纸本)9798350382396

In recent years, there has been a swift progression in employing novel methods in classrooms to enhance students' academic achievements, especially in line with the growing digitization of education. Such methods often encompass systems like facial recognition to monitor various aspects of students, including attendance, emotional states, and attention. These tools are capable of evaluating students' presence and engagement in class, offering quantifiable metrics regarding their concentration and emotions. However, a prominent challenge has been the translation of this data into an accessible form that enables educators to assess and enhance their teaching techniques swiftly. Our suggested solution tackles this issue by offering a real-Time visual depiction of students' classroom status through different visualization techniques. These visual aids allow teachers to promptly recognize trends in student focus, thus aiding in the strategic alteration of teaching styles. Furthermore, these visual representations can be tailored to display various metrics and applied to tasks beyond monitoring attention, like overseeing attendance or assessing student progress. By integrating these advanced visualizations into the educational process, both teaching efficacy and the learning experience for students and teachers alike can be substantially elevated. © 2023 IEEE.

关键词： Students

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：