检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Izankar, Sakshi V. Puri, Chetan Burle, Rushikesh Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798331523923

Esophageal, gastric, and colorectal cancers (CRC) are some of the gastrointestinal (GI) cancers threatening global health with CRC being particularly concerning due to its high fatality rate. While early diagnosis is crucial in improving treatment efficiency, barriers such as image noise and visual subjective assessments during diagnostics such as colonoscopies often render it inconceivable. For better diagnostic accuracy in detecting gastrointestinal disease via endoscopic images, the research explores whether highly advanced artificial intelligence (AI) models such as Vision Transformers (ViTs) and pre-trained DenseNet201 can be effective. We compare these models to popular deep learning techniques such as Support Vector Machines (SVM), ResNet50, VGG19, and GoogleNet. At a training accuracy of 99.9% and a validation accuracy of 98.8%, experiments on the KVASIR dataset indicate that Vision Transformer is superior to other models since it can learn long-range dependencies. The robustness of deep learning models for identifying GI disease is exemplified by the superior performance of DenseNet201, ResNet50, and InceptionV3, all of which possess high accuracy, precision, and recall values. The paper illustrates the potential of Vision Transformers, when combined with transfer learning and pre-trained CNN models, to revolutionize endoscopic diagnoses and provide a valuable resource to help physicians manage gastrointestinal conditions more effectively. © 2025 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

SP-ADMM: a distributed optimization method of SFC placement for 5G-MEC networks 3

SP-ADMM: a distributed optimization method of SFC placement ...

引用

3rd International Conference on Algorithms, Microchips, and Network Applications, AMNA 2024

作者： Zhang, Zhibo Wang, Huiqiang Niu, Shuangyue Lv, Hongwu College of Computer Science and Technology Harbin Engineering University Harbin China AVIC Chengdu Aircraft Design and Research Institute Chengdu China

ISBN: (纸本)9781510680098

Recently, the combination of a service function chain (SFC) with network function virtualization (NFV) and software-defined networking (SDN) has provided customers with flexible and efficient services. The emergence of multi-access edge computing (MEC) further enhances the level of service customization. However, achieving joint optimization of virtual network function (VNF) deployment and flow allocation in resource-constrained scenarios while meeting the diverse requirements of 5G verticals is challenging. Current research rarely addresses dedicated service provisioning for edge servers and considers the additional instantiation overhead introduced by adjusting cloud server parameters. In fact, this is a non-negligible issue during SFC deployment in 5G-MEC scenarios. Based on the above considerations, this paper constructs a joint SFC deployment problem for edge-cloud networks with the goal of maximizing network utility. We first propose a univariate modeling method based on meta-links that effectively avoids the variable coupling problem in traditional multivariate modeling approaches and reduce the problem size by at least half. Subsequently, to solve the NP-hard integer nonlinear problem (INLP), we propose a distributed computing architecture named SP-ADMM, which improves the speed and quality of SFC deployment in large-scale scenarios via convex combinatorial formulations and a Viterbi-based heuristic algorithm (PAC-GREP). Finally, we experimentally verify the convergence and approximation of the algorithms. Our solution demonstrates advantages in terms of network utility and convergence speed under the same network resources, increasing service capacity by at least 39%. © 2024 SPIE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Systematic Review of GAN for Enhancing Efficiency in AI in Gaming

Systematic Review of GAN for Enhancing Efficiency in AI in G...

引用

2024 International Conference on Advances in Computing research on science engineering and technology, ACROSET 2024

作者： Singh, Jasdeep Islam, Sardar M. N. Tewatia, Manav Garg, Deepanshu Fatima, Neda School of Computer Applications Manav Rachna International Institute of Research and Studies Faridabad India Victoria University Department of Computer Science and Engineering Melbourne Australia School of Engineering and Technology Manav Rachna International Institute of Research and Studies Faridabad India

ISBN: (纸本)9798350388800

A thorough analysis of Generative Adversarial Networks (GANs) and how they might be used to improve AI gaming efficiency is presented in this research. Game developers now have never-before-seen possibilities for innovation, immersion, and personalization thanks to GANs, which have become a potent tool for producing realistic data samples across a variety of fields. This review investigates the architecture, training methods, applications, difficulties, and potential future directions of GANs in AI gaming through a thorough analysis of the body of research and publications. The review demonstrates how GANs can transform the game industry by highlighting their many uses in procedural content generation, texture synthesis, character animation, environment design, and content customization. Nevertheless, there are certain difficulties in integrating GANs into AI games, such as computational resources, mode collapse, training instability, and assessment *** well as legal matters. To tackle these obstacles, multidisciplinary research endeavors and cooperation across academic institutions, corporate entities, and regulatory agencies are necessary. Going forward, new avenues for study and developments in GAN technology hold great potential for getting over these roadblocks and opening up fresh possibilities in AI gaming. We can create a future where AI powered gaming experiences change the parameters of interactive entertainment and provide players globally with more engaging, varied, and personalized gaming experiences by utilizing the possibilities of GANs and addressing the related obstacles. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Multipath Routing Approach for Mobile Ad Hoc Networks with Network Coding 15

A Multipath Routing Approach for Mobile Ad Hoc Networks with...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sujai, S. Tiwaskar, S.A. Thangarasu, N. Jain, Romil Preetha, M. Goyal, Shubhi School of Engineering and Technology Mechaical Engineering Karnataka Bangalore India Computer Engg Vishwakarma Institute of Technology Pune India Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research for Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Quantum University Research Center Quantum University India

ISBN: (纸本)9798350370249

Mobile advert hoc networks (MANETs) are self-organizing, infrastructure-less networks together with cellular nodes that talk with each other without delay over wireless links. In spite of the numerous benefits they offer, MANETs need more bandwidth and strength assets and numerous inherent obstacles such as route preservation price and transmission reliability. To address those issues, this paper gift a routing method based on multipath routing and community coding for MANETs. Multipath routing is based on packet-degree duplication to stabilize the traffic load among multiple paths to be had in the network. In contrast, network coding combines more than one packet at community interface nodes, which will increase throughput and reduce manipulation overhead when packets traverse intermediate nodes. The proposed routing method combines each of these techniques, which ends up in efficient and dependable information transmission, even as concurrently decreasing the stress on the network sources. The proposed approach changed into simulating the usage of an OMNeT++ simulator and evaluated in terms of shipping ratio and common stop-to-give-up postponement. The simulation outcomes confirmed that the proposed technique outperforms multipath routing without network coding and single-direction routing in phrases of delivery ratio and average end-to-give-up delay. © 2024 IEEE.

关键词： Infrastructure Manipulation Multipath Numerous Preservation Strength Technique

来源：评论

学校读者我要写书评

暂无评论

Cost/Benefit Analysis of AIoT Image Sensing for Construction Safety Monitoring

引用

Journal of engineering, Project, and Production Management 2024年第3期14卷 1-13页

作者： Wang, Rong-Jing Yu, Wen-Der Liao, Hsien-Chou Chang, Hsien-Kuan Lim, Zi-Yi Architecture and Building Research Institute Ministry of Interior New Taipei23143 Taiwan Department of Construction Engineering Chaoyang University of Technology Taichung413310 Taiwan Department of Computer Science and Information Technology Chaoyang University of Technology Taichung413310 Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung413310 Taiwan

Rapid advances in deep learning and computer vision enable traditional cloud-based decision-making through edge computing with the Artificial Intelligent Internet of Things (AIoT) image sensors (AIoT-IS), thus improving the timeliness and security of image recognition. This study is indented to investigate the potential costs and benefits of AIoT-IS applications. This study summarizes AIoT-IS application scenarios for construction safety monitoring and proposes a cost/benefit analysis method for AIoT-IS implementation projects. According to the case study results, AIoT-IS achieves significant benefits, with a Net Present Value Index (NPVI) of 19.17% and a Benefit/Cost Ratio (BCR) of 4.65 as applied to construction site safety monitoring. Interviews with domain experts also provided qualitative feedback, pointing to the directions for future research. The proposed method is applicable for the decision-making of AIoT-IS adoption and the feasibility assessment of other innovative construction technologies. Copyright © Journal of engineering, Project, and Production Management (EPPM-Journal).

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-Aware Federated Learning with Adaptive Client Selection and Gradient Compression 42

Heterogeneity-Aware Federated Learning with Adaptive Client ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Jiang, Zhida Xu, Yang Xu, Hongli Wang, Zhiyuan Qian, Chen University of Science and Technology of China School of Computer Science and Technology China University of Science and Technology of China Suzhou Institute for Advanced Research China University of California Jack Baskin School of Engineering Department of Computer Science and Engineering United States

ISBN: (纸本)9798350334142

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and heterogeneous client properties, which slow down the convergence of FL. To tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, the parameter server (PS) selects a representative client subset considering statistical heterogeneity and sends the global model to them. After local training, these selected clients upload compressed model updates matching their capabilities to the PS for aggregation, which significantly alleviates the communication load and mitigates the straggler effect. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the derived convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. Extensive experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3× speedup compared to other methods. © 2023 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

引用

computers, Materials & Continua 2023年第4期75卷 1-17页

作者： Xiaorui Zhang Rui Jiang Wei Sun Aiguo Song Xindong Wei Ruohan Meng Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Instrument Science and Engineering Southeast UniversityNanjing211189China School of Teacher Education Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

Robust watermarking requires finding invariant features under multiple attacks to ensure correct *** learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread *** existing methods use 3×3 small kernel convolution to extract image features and embed the ***,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the *** address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss *** uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel ***,the modification of the embedded watermarking on the cover image is extended to more *** the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight ***,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image *** experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise.

关键词： Robust watermarking large kernel convolution adaptive loss weights high-frequency wavelet loss deep learning

来源：评论

学校读者我要写书评

暂无评论

Periodic poling of single crystal thin film barium titanate-on-insulator

Periodic poling of single crystal thin film barium titanate-...

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Aashna, Pragati Lin, Hong-Lin Cao, Yu Gao, Yuan Mohanraj, Sakthi Sanjeev Zhu, Di Danner, Aaron Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore Department of Material Science and Engineering National University of Singapore 117575 Singapore Institute of Materials Research and Engineering Agency for Science Technology and Research 138634 Singapore

We report, for the first time, electric field periodic poling of single-crystal thin film barium titanate grown using pulsed-laser-deposition on dysprosium scandate substrate. Uniform domains with periods 5-7 μm are ... 详细信息

关键词： Single crystals

来源：评论

学校读者我要写书评

暂无评论

An Anatomization for Classification Skin Lesion Using Custom CNN Framework 1

An Anatomization for Classification Skin Lesion Using Custom...

引用

1st International Conference on Industrial Electronics research and Applications, ICIERA 2021

作者： Gupta, Shubham Acropolis Institute of Technology and Research Department of Computer Science Indore India

ISBN: (纸本)9781665435420

A skin lesion is a growth or appearance anomaly in the dermis that is different from the rest of the body. A tiny scratch or something more serious like skin cancer might be completely unnoticeable. The use of deep learning (DL) architectures for image categorization in several fields, including dermatology, has shown impressive results. The expectations produced by DL for applications like image-based diagnostics have necessitated that non-experts become acquainted with algorithms' working principles. Obtaining hands-on experience using these tools through a simplified however realistic method, in our opinion, may significantly aid in their intuitive comprehension. Even students without a strong mathematical background may understand concepts like convolution by seeing the outcomes of DL algorithms' operations on dermatological images. Furthermore, the ability to fine-Tune hyperparameters even computer code expands the reach of basic intuitive understanding of these methods without having complex computational theoretical skills. It is now feasible because of recent technology advancements that have lowered technical technological obstacles associated with usage of these tools, creation them available to a larger population. So, we present a custom CNN for training a CNN on a dataset that contains skin lesions images linked by distinct skin cancer groups. Activity is open-source doesn't need any additional software to be installed to use it. Additionally, we describe the algorithm and its functions in detail, starting with the creation of the basic computer code building blocks and leading the reader through the execution of real-world examples, comprising visualization assessment of results. We get a training accuracy of 100 percent a validation accuracy of 98.32 percent using this method. © 2021 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Achieving high strength-ductility synergy in a Mg_(97)Y_(1)Zn_(1)Ho_(1) alloy via a nano-spaced long-period stacking-ordered phase

引用

Journal of Magnesium and Alloys 2023年第4期11卷 1321-1331页

作者： Mingyu Fan Ye Cui Yang Zhang Xinghao Wei Xue Cao Peter K.Liaw Yuansheng Yang Zhongwu Zhang Key Laboratory of Superlight Materials and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityHarbin 150001PR China College of Computer Science and Technology Harbin Engineering UniversityHarbin 150001PR China Department of Materials Science and Engineering The University of TennesseeKnoxvilleTN 37996-2100USA Institute of Metal Research Chinese Academy of SciencesShenyang 110016PR China

Achieving high strength in Mg alloys is usually accompanied by ductility ***,a novel Mg97Y1Zn1Ho1 at.%alloy with a yield strength of 403 MPa and an elongation of 10%is *** strength-ductility synergy is obtained by a comprehensive strategy,including a lamella bimodal microstructure design and the introduction of nano-spaced solute-segregated 14H long-period stacking-ordered phase(14H LPSO phase)through rare-earth Ho *** lamella bimodal microstructure consists of elongated un-recrystallized(un-DRXed)coarse grains and fine dynamically-recrystallized grains(DRXed regions).The nano-spaced solute-segregated 14H LPSO phase is distributed in DRXed *** outstanding yield strength is mainly contributed by grain-boundary strengthening,18R LPSO strengthening,and fiberlike reinforcement strengthening from the nano-spaced 14H LPSO *** high elongation is due primarily to the combined effects of the bimodal and lamellar microstructures through enhancing the work-hardening capability.

关键词： Mg wrought alloy Mechanical properties Long-period stacking-ordered(LPSO)phase Age-strengthening behavior Strengthening mechanism

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：