检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in design

作者： Zheng Dong Ruijia Zhang Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Shandong Engineering Research Center of Big Data Applied Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Image-text matching is an important and challenging task in the field of multimedia analysis, aimed at bridging the semantic gap between visual content and language descriptions. Although this field has significant implications for enhancing cross-modal interaction, most previous work still faces challenges in accurately aligning images with text descriptions, especially when dealing with images containing rich semantic information. To address this issue, we propose a novel context-aware image-text matching model that extracts and summarizes visual region information aligned with multiple text descriptions from a single image. Specifically, we designed an adaptive context-aware self-attention module to extract representations of visual regions and text words. By controlling the complementary semantic relationships within each modality, our model can adaptively capture contextual information for each modality. We then introduce a Transformer-based encoder layer to extract features at multiple levels and aggregate region-level features into image-level features. Finally, fine-grained word-region alignment is conducted to match image features with corresponding text features. To evaluate the effectiveness of our method, we conducted extensive experiments on two benchmark datasets, Flickr30K and MS-COCO. The experimental results show that our model outper-forms several state-of-the-art baselines in image-text matching tasks, demonstrating the effectiveness and practicality of our model in handline cross-modal retrieval tasks.

关键词： Measurement Visualization Adaptation models Federated learning Semantics Transformers Feature extraction Faces Context modeling Cross modal retrieval

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Deep Reinforcement Learning Framework for Detecting and Mitigating DDoS Attacks in IoT Networks

A Multi-Agent Deep Reinforcement Learning Framework for Dete...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Bhushan Shaharkar Tanusha Mittal Krishna Chaitanya Sunkara Vishal Shukla Ishan Desai Ujal Mookherjee Department of Information Technology Walchand Institute of Technology Solapur India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Data Center Design & Modeling AL/ML Expert Oracle Cloud Engineering Raleigh USA Department of Mechanical Engineering Ramdeobaba University Nagpur India Department of Electrical Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Post Limda India Faculty of Law Symbiosis Law School Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

The rise of Internet of Things (IoT) networks has introduced new opportunities for innovation but also increased vulnerability to cyberattacks, particularly Distributed Denial-of-Service (DDoS) attacks. Traditional detection and mitigation mechanisms often struggle to handle the dynamic and distributed nature of IoT systems. In this study, we propose a Multi-Agent Deep Reinforcement Learning (MADRL) framework designed to detect and mitigate DDoS attacks in IoT networks in real-time. The framework consists of multiple collaborative agents, each deployed at different network layers or nodes, trained using deep reinforcement learning to identify attack patterns and take immediate mitigation actions. Through cooperative learning, these agents adapt to evolving attack strategies and optimize defense policies. Experimental evaluations demonstrate that the proposed MADRL framework outperforms traditional techniques by achieving higher detection accuracy, faster response times, and reduced false positive rates. Our results indicate that this framework can effectively secure IoT networks against complex DDoS attacks, maintaining network stability and availability.

关键词： Wireless communication Technological innovation Accuracy Prevention and mitigation Collaboration Denial-of-service attack Deep reinforcement learning Stability analysis Time factors Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Subspace learning using low-rank latent representation learning and perturbation theorem: Unsupervised gene selection

引用

Computers in Biology and Medicine 2025年 185卷 109567-109567页

作者： Moslemi, Amir Naeini, Fariborz Baghaei Department of Physics Toronto Metropolitan University ON Canada School of Software Design & Data Science Seneca Polytechnic TorontoONM4N 3M5 Canada Physical Sciences Sunnybrook Health Sciences Centre TorontoONM4N 3M5 Canada Faculty of Engineering Computing and the Environment Kingston University Penrhyn Road Campus Kingston Upon Thames LondonKT1 2EE United Kingdom

In recent years, gene expression data analysis has gained growing significance in the fields of machine learning and computational biology. Typically, microarray gene datasets exhibit a scenario where the number of features exceeds the number of samples, resulting in an ill-posed and underdetermined equation system. The presence of redundant features in high-dimensional data leads to suboptimal performance and increased computational time for learning algorithms. Although feature extraction and feature selection are two approaches that can be employed to deal with this challenge, feature selection has greater interpretability ability which causes it to receive more attention. In this study, we propose an unsupervised feature selection which is based on pseudo label latent representation learning and perturbation theory. In the first step, pseudo labels are extracted and constructed using latent representation learning. In the second step, the least square problem is solved for original data matrix and perturbed data matrix. Features are clustered based on the similarity between the original data matrix and the perturbed data matrix using k-means. In the last step, features in each subcluster are ranked based on information gain criterion. To showcase the efficacy of the proposed approach, numerical experiments were carried out on six benchmark microarray datasets and two RNA-Sequencing benchmark datasets. The outcomes indicate that the proposed technique surpasses eight state-of-the-art unsupervised feature selection methods in both clustering accuracy and normalized mutual information. © 2024 Elsevier Ltd

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Vacancy-Type Defects in Thin HfO2 Layers Probed by Monoenergetic Positron Beams

Vacancy-Type Defects in Thin HfO2 Layers Probed by Monoenerg...

引用

Joint e-Manufacturing and design Collaboration Symposium (eMDC) & International Symposium on Semiconductor Manufacturing (ISSM)

作者： Akira Uedono Kazuya Kawakami Tatsunori Kuribara Ryu Hasunuma Yosuke Harashima Yasuteru Shigeta Zeyuan Ni Ruolin Yan Hideo Nakamura Akira Notake Tsuyoshi Moriya Koji Michishio Shoji Ishibashi Faculty of Pure and Applied Science University of Tsukuba Tsukuba Ibaraki Japan Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Nara Japan S-Technology Development Center Tokyo Electron Technology Solutions Ltd. Nirasaki Yamanashi Japan Development Department 1 Tokyo Electron Technology Solutions Ltd. Nirasaki Yamanashi Japan Digital Design Center Tokyo Electron Ltd. Sapporo Hokkaido Japan Software and Data Engineering Division Tokyo Electron Technology Solutions Ltd. Nirasaki Yamanashi Japan Research Institute for Measurement and Analytical Instrumentation National Institute of Advanced Industrial Science and Technology Tsukuba Ibaraki Japan Research Center for Computational Design of Advanced Functional Materials National Institute of Advanced Industrial Science and Technology Tsukuba Ibaraki Japan

ISBN: (数字)9798331510589

ISBN: (纸本)9798331510596

Behaviors of vacancies during the amorphous-to-crystalline transition of thin HfO 2 layers were studied by monoenergetic positron beams. The HfO 2 layers with 4‒30 nm thickness were fabricated on TiN/Si templates by atomic layer deposition technique. The major vacancy-type defects in the layers were identified as (i) Hf vacancies (V Hf ) coupled with oxygen vacancies (V O s) and (ii) vacancy clusters. After annealing at 500°C, the concentration of vacancy clusters increased, which was attributed to the agglomeration of intrinsic open spaces in the amorphous phase upon the phase transition from amorphous to crystalline phases. The phase transition started near the interface between the HfO 2 layer and bottom electrodes (TiN). After the crystallization, the concentration of vacancy clusters decreased as the annealing temperature increased.

关键词： Electrodes Annealing Atomic layer deposition Positrons Crystallization Tin Semiconductor device manufacture Hafnium compounds

来源：评论

学校读者我要写书评

暂无评论

Information-transfer characteristics in network motifs

引用

Physical Review Research 2023年第1期5卷 013037-013037页

作者： Fumito Mori Takashi Okada Faculty of Design Kyushu University Fukuoka 815-8540 Japan Education and Research Center for Mathematical and Data Science Kyushu University Fukuoka 819-0395 Japan Institute for Life and Medical Sciences Kyoto University Kyoto 606-8507 Japan RIKEN Interdisciplinary Theoretical and Mathematical Sciences Program (ITHEMS) Wako 351-0198 Japan Department of Physics University of California Berkeley 94720 CA United States

Information processing in biological systems is realized by the appropriate transmission of information flows over complex networks, such as gene regulatory, signal transduction, and neural networks. These information flows are affected by the input-signal characteristics and structural properties of network systems, such as the network topology, regulation rules, and intrinsic and environmental noise. Many biological networks frequently include several typical patterns called network motifs, which are considered to play important roles in biological functions. However, their information-theoretic properties, particularly the dependence of the information flows in each network on the input signal, remain poorly understood. In our previous study [Mori and Okada, Phys. Rev. Res. 2, 043432 (2020)], we developed a graphical expansion method to describe transfer entropy (TE), a measure of information flow, in Boolean networks in terms of multiple information pathways. There, the input signal was limited to a simple case, and the effect of the input-signal characteristics on TE was not clarified. In this paper, we improve our method to render it applicable to Boolean networks that receive input signals with arbitrary stochastic characteristics. Our formula expresses how TE is determined by the input-signal characteristics, the assignment of Boolean functions, and the noise magnitude. We find that, in both positive and negative feedback loops, TE hardly depends on the signal timescale. In contrast, coherent and incoherent feedforward loops show low- and high-pass filtering properties, respectively, for a time-varying signal, which is consistent with previous reports. The emergence of either low- or high-pass filtering is determined by the Fourier components of the Boolean functions on specific pathways transmitting information flows. Thus our formula reveals the mechanism of information transfer in network motifs and provides insights into the origin of information process

关键词： Network flow optimization Network structure Directed networks Gene regulatory networks Neuronal networks Stochastic dynamical systems Chaos & nonlinear dynamics Information theory Perturbative methods

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Adoption in Housing: A Bibliometric Analysis

Artificial Intelligence Adoption in Housing: A Bibliometric ...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Anthonia Oluwatosin Adediran Samuel-Soma M. Ajibade Muhammed Basheer Jasser Faizah Mohammed Bashir Yakubu Aminu Dodo Yasni Nurul Huda Mohd Yassin Bayan Issa Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University Selangor Darul Ehsan Malaysia Department of Decoration and Interior Design Engineering College of Engineering University of Hail Hail Kingdom of Saudi Arabia Architectural Engineering Department College of Engineering Najran University Najran Kingdom of Saudi Arabia Faculty of Artificial Intelligence Universiti Teknologi Malaysia Kuala Lumpur Malaysia Faculty of Informatics Engineering University of Aleppo Syria

ISBN: (数字)9798331522193

ISBN: (纸本)9798331522209

This study examines the academic field of Artificial Intelligence in Housing by examining the publications and indexed documents in Scopus and web of science (WOS) from 2000 to 2024. Consequently, we examined the publishing trends, exemplary articles, and the most engaged participants and funding institutions in the domain of AI and Housing research. A bibliometric analysis was performed to examine the network of co-authorships, keywords, and citations in the domain of AI and Housing research. The Scopus and WOS search resulted in the discovery of 246 related publications on AI and Housing. With an increase from 1 publication to 68 publications within the observed years. Additionally, trends analysis indicated a significant increase of 5,016 in publications between 2000 and 2024. Articles are the most often utilized document type, including 172 of the overall amounts. The most prolific researchers in the field of AI and Housing are Ahmad, Chatterjee, Cho, Lee, Mehmood, Shaheen, Yang, and Zhao. All having published 3 documents each. Additionally, ten institutions have produced the highest number of published documents. The output of the affiliations active in the topic is primarily attributed to the funding, specifically the National science Foundation, which is the leading funding institution based in the United States and has contributed to 8 publications. An analysis of keyword co-occurrence revealed 4 main study areas that cover the essential tools, theories, methodologies, and socioeconomic and financial aspects of artificial intelligence and Housing. Future research in the field of artificial intelligence and Housing will focus on employing sophisticated machine learning, and neural network algorithms to precisely predict Housing transactions patterns while further enhancing housing market transactions across countries.

关键词： Machine learning algorithms databases Bibliometrics Neural networks Machine learning Market research Real estate industry Prediction algorithms Internet Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

Cyber Twin-Enabled Real-Time AI Orchestration for Advanced IoT Security and Dynamic Software Optimization

Cyber Twin-Enabled Real-Time AI Orchestration for Advanced I...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Krishna Chaitanya Sunkara Pareshwar Prasad Barmola Ravi K S Vishal Shukla Umang Soni Amol Sapatnekar Oracle Cloud Engineering Data Center Design & Modeling AL/ML Expert North Carolina USA Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Mechanical Engineering Vidyavardhaka College of Engineering Mysuru India Department of Mechanical Engineering Ramdeobaba University Nagpur India Department of Electronics & Communication Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Gujarat India Faculty of Law Symbiosis Law School Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

The rapid expansion of Internet of Things (IoT) ecosystems has increased the complexity and vulnerability of software systems, making them more susceptible to security breaches and performance inefficiencies. Traditional security and optimization techniques struggle to keep up with the dynamic nature of IoT networks. This calls for the development of advanced frameworks that can adapt in real-time to evolving threats and operational requirements. This paper introduces Cyber Twins, an AI-driven framework designed for real-time security and software optimization in IoT environments. Cyber Twins leverage artificial intelligence and digital twin technology to create dynamic cyber representations of physical IoT devices and software processes. The framework integrates reinforcement learning for adaptive optimization, convolutional neural networks (CNNs) for anomaly detection, and graph neural networks (GNNs) for real-time threat analysis. By continuously synchronizing with live IoT data, Cyber Twins enable proactive threat detection and autonomous system optimization, ensuring a secure and high-performing IoT ecosystem. The proposed framework combines Federated Learning (FL) for distributed intelligence and Reinforcement Learning (RL) for adaptive decision-making. Key advancements include (1) a 35% improvement in intrusion detection accuracy compared to traditional methods, (2) a 40% reduction in false positive rates, and (3) a 25% increase in dynamic software adaptation speed. Experiments conducted on a simulated IoT environment with 1,000 devices demonstrated scalability and resilience under varying network conditions. Additionally, the framework achieved a 20% decrease in latency during AI model updates and a 30% reduction in computational overhead, ensuring efficient resource utilization.

关键词： Ecosystems Reinforcement learning Software Real-time systems Threat assessment Internet of Things Security Artificial intelligence Optimization Resilience

来源：评论

学校读者我要写书评

暂无评论

Impact of Cation Vacancies on Leakage Current on TiN/ZrO2/TiN Capacitors Studied by Positron Annihilation 29

Impact of Cation Vacancies on Leakage Current on TiN/ZrO2/Ti...

引用

29th International Symposium on Semiconductor Manufacturing, ISSM 2022

作者： Uedono, Akira Takahashi, Naomichi Hasunuma, Ryu Harashima, Yosuke Shigeta, Yasuteru Ni, Zeyuan Matsui, Hidefumi Notake, Akira Kubo, Atsushi Moriya, Tsuyoshi Michishio, Koji Oshima, Nagayasu Ishibashi, Shoji University of Tsukuba Faculty of Pure and Applied Science Ibaraki Tsukuba305-8573 Japan Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Nara630-0192 Japan Tokyo Electron Technology Solutions Ltd. S-Technology Development Center Yamanashi Nirasaki407-0192 Japan Tokyo Electron Ltd. SDC AI Development Department Hokkaido Sapporo060-0003 Japan Tokyo Electron Ltd. Advanced Data Planning Department Tokyo107-6325 Japan Research Institute for Measurement and Analytical Instrumentation National Institute of Advanced Industrial Science and Technology Ibaraki Tsukuba305-8568 Japan National Institute of Advanced Industrial Science and Technology Research Center for Computational Design of Advanced Functional Materials Ibaraki Tsukuba305-8568 Japan

ISBN: (纸本)9781665471336

TiN/ZrO2/TiN capacitors were characterized using XRD, STEM, EDX, and monoenergetic positron beams. For an as-deposited ZrO2 layer, an interlayer was formed in the layer. After post-deposition annealing at 550°C, the width of the interlayer expanded. The major vacancy-type defects in the ZrO2 layer were determined to be a Zr-vacancy coupled with oxygen vacancies by the positron annihilation technique. After annealing, the size of these vacancies increased. The presence of the cation vacancies and their complexes in the ZrO2 layer suggests that not only oxygen vacancies but also such defects play a role in the defect formation of the ZrO2 layer and affect its electrical properties. © 2022 IEEE.

关键词： Electrons

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for objective assessment of acrobatic movements: How to apply machine learning for identifying tumbling elements in cheer sports

arXiv

引用

arXiv 2025年

作者： Wesely, Sophia Hofer, Ella Curth, Robin Paryani, Shyam Mills, Nicole Ueberschär, Olaf Westermayr, Julia Leipzig University Faculty of Chemistry and Mineralogy Institute of Physical and Theoretical Chemistry Leipzig Germany Magdeburg-Stendal University of Applied Sciences Department of Engineering and Industrial Design Magdeburg Germany Center for Scalable Data Analytics and Artificial Intelligence Dresden Leipzig Germany University of North Florida Brooks College of Health JacksonvilleFL United States University of North Florida Athletics Department JacksonvilleFL United States Institute for Applied Training Science Leipzig Germany

Over the past four decades, cheerleading has evolved from a sideline activity at major sporting events into a professional, competitive sport with growing global popularity. Evaluating tumbling elements in cheerleading relies on both objective measures and subjective judgments, such as difficulty and execution quality. However, the complexity of tumbling—encompassing team synchronicity, ground interactions, choreography, and artistic expression—makes objective assessment challenging. Artificial intelligence (AI) has revolutionized various scientific fields and industries through precise data-driven analyses, yet their application in acrobatic sports remains limited despite significant potential for enhancing performance evaluation and coaching. This study investigates the feasibility of using an AI-based approach with data from a single inertial measurement unit to accurately identify and objectively assess tumbling elements in standard cheerleading routines. A sample of 16 participants (13 females, 3 males) from a Division I collegiate cheerleading team wore a single inertial measurement unit at the dorsal pelvis. Over a 4-week seasonal preparation period, 1102 tumbling elements were recorded during regular practice sessions. Using triaxial accelerations and rotational speeds, various ML algorithms were employed to classify and evaluate the execution of tumbling manoeuvres. Results indicate that certain machine learning models can effectively identify different tumbling elements despite inter-individual variability and data noise, achieving high accuracy. These findings demonstrate the significant potential for integrating AI-driven assessments into cheerleading and other acrobatic sports, providing objective metrics that complement traditional judging methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

A Method for Assisting Novices Creating Class Diagrams Based on the Instructor’s Class Layout

arXiv

引用

arXiv 2025年

作者： Saito, Yuta Kokubu, Takehiro Tanaka, Takafumi Hazeyama, Atsuo Hashiura, Hiroaki Dept. of Information Technology and Media Design Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan Dept. of Software Science Faculty of Engineering Tamagawa University Tokyo Japan Dept. of Technology and Information Science Faculty of Education Tokyo Gakugei University Tokyo Japan Dept. of Data Science Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan

Nowadays, modeling exercises on software development objects are conducted in higher education institutions for information technology. Not only are there many defects such as missing elements in the models created by learners during the exercises, but the layout of elements in the class diagrams often differs significantly from the correct answers created by the instructors. In this paper, we focus on the above problem and propose a method to provide effective support to learners during modeling exercises by automatically converting the layout of the learner’s class diagram to that of the instructor, in addition to indicating the correctness of the artifacts to the learners during the exercises. The proposed method was implemented and evaluated as a tool, and the results indicate that the automatic layout conversion was an effective feedback to the learners. Copyright © 2025, The Authors. All rights reserved.

关键词： Graphic methods

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：