检索结果-内蒙古大学图书馆

An Efficient Algorithm for Hamiltonian Path Embedding of k-Ary n-Cubes Under the Partitioned Edge Fault Model

IEEE Transactions on Parallel and Distributed Systems 2023年第6期34卷 1802-1815页

作者： Zhuang, Hongbin Li, Xiao-Yan Chang, Jou-Ming Wang, Dajin Fuzhou University College of Computer and Data Science Fuzhou350108 China National Taipei University of Business Institute of Information and Decision Sciences Taipei10051 Taiwan Montclair State University Department of Computer Science MontclairNJ07043 United States

The k-ary n-cube Qnk is one of the most important interconnection networks for building network-on-chips, data center networks, and parallel computing systems owing to its desirable properties. Since edge faults grow rapidly and the path structure plays a vital role in large-scale networks for parallel computing, fault-tolerant path embedding and its related problems have attracted extensive attention in the literature. However, the existing path embedding approaches usually only focus on the theoretical proofs and produce an n-related linear fault tolerance since they are based on the traditional fault model, which allows all faults to be adjacent to the same node. In this paper, we design an efficient fault-tolerant Hamiltonian path embedding algorithm for enhancing the fault-tolerant capacity of k-ary n-cubes. To facilitate the algorithm, we first introduce a new conditional fault model, named Partitioned Edge Fault model (PEF model). Based on this model, for the k-ary n-cube Qnk with n ≥ 2 and odd k ≥ 3, we explore the existence of a Hamiltonian path in Qnk with large-scale edge faults. Then we give an O(N) algorithm, named HP-PEF, to embed the Hamiltonian path into Qnk under the PEF model, where N is the number of nodes in Qnk. The performance analysis of HP-PEF shows the average path length of adjacent node pairs in the Hamiltonian path constructed by HP-PEF. We also make comparisons to show that our result of edge fault tolerance has exponentially improved other known results. We further experimentally show that HP-PEF can support the dynamic degradation of average success rate of constructing Hamiltonian paths when increasing faulty edges exceed the fault tolerance. © 1990-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

UNDERSTANDING THE GENERALIZATION OF ADAM IN LEARNING NEURAL NETWORKS WITH PROPER REGULARIZATION 11

UNDERSTANDING THE GENERALIZATION OF ADAM IN LEARNING NEURAL ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zou, Difan Cao, Yuan Li, Yuanzhi Gu, Quanquan Department of Computer Science Institute of Data Science The University of Hong Kong Hong Kong Department of Statistics & Actuarial Science The University of Hong Kong Hong Kong Machine Learning Department Carnegie Mellon University United States Department of Computer Science University of California Los Angeles United States

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed in many deep learning applications such as image classification, Adam can converge to a different solution with a worse test error compared to (stochastic) gradient descent, even with a fine-tuned regularization. In this paper, we provide a theoretical explanation for this phenomenon: we show that in the nonconvex setting of learning over-parameterized two-layer convolutional neural networks starting from the same random initialization, for a class of data distributions (inspired from image data), Adam and gradient descent (GD) can converge to different global solutions of the training objective with provably different generalization errors, even with weight decay regularization. In contrast, we show that if the training objective is convex, and the weight decay regularization is employed, any optimization algorithms including Adam and GD will converge to the same solution if the training is successful. This suggests that the generalization gap between Adam and SGD in the presence of weight decay regularization is closely tied to the nonconvex landscape of deep learning optimization, which cannot be covered by the recent neural tangent kernel (NTK) based analysis. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Security and Energy Efficiency Enhancement for the Internet of Things: Challenges, Architecture and Future Research

Security and Energy Efficiency Enhancement for the Internet ...

引用

International Conference on data science and Network Engineering, ICDSNE 2023

作者： Dewan, Ritu Nagpal, Tapsi Ahmad, Sharik Rana, Arun Kumar Islam, Sardar M. N. Department of Computer Science and Engineering Lingayas Vidyapeeth Faridabad India Department of Computer Science and Engineering Galgotias College of Engineering & Technology Gr. Noida India SILC Decision Sciences and Modelling Program Victoria University Victoria Australia

ISBN: (纸本)9789819967544

Thanks to constantly advancing technology, the world is changing rapidly. One such idea that has contributed to the reality of automation is the Internet of Things (IoT). IoT links various non-living objects to the internet and enables them to communicate with their local network to automate processes and simplify people’s lives. The IoT’s potential needs to be completely realised despite the enormous efforts of standards, organisations, coalitions, businesses, academics and others. A number of problems remain. The enabling technology, applications and business models, as well as the social and environmental repercussions, should all be taken into consideration while analysing these difficulties. This article’s emphasis is on unresolved issues and challenges from a technological perspective. The main objective is to provide a thorough evaluation of IoT in terms of energy and security, as well as unresolved problems and obstacles that need further study. We provide some perspectives on some new concepts to help future research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Suitability of Latest Version of YOLOv11 in Drone Development Studies 7

Suitability of Latest Version of YOLOv11 in Drone Developmen...

引用

7th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2024

作者： Riftiarrasyid, Mohammad Faisal Gaol, Ford Lumban Soeparno, Haryono Arifin, Yulyani Nunsantara University Binus Graduate Program Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331519643

Although drones have become increasingly advanced and sophisticated, they still face challenges such as limited computing power and high-power consumption. Optimizing their features is a key strategy to address these limitations. One critical feature that can be further improved is the algorithm for specialized tasks like obstacle detection. Recent studies have primarily relied on earlier versions of YOLO for this purpose. However, with the release of the latest YOLO versions, YOLOv10 and YOLOv11, there is an opportunity to assess their suitability for drone applications. In this study, we trained YOLOv10-nano and YOLOv11-nano using a drone-specific dataset and compared their performance with similar studies. The results indicate that YOLOv11-nano outperforms YOLOv10-nano in bounding-box prediction, achieving a higher mAP of 0.957 with a 0.22 difference, as well as faster inference times with a 74.1 ms improvement, resulting in a frame rate gain of 0.0421 FPS. However, when compared to earlier studies, YOLOv11-nano demonstrates superior precision but lags in real-time processing speed. These findings highlight the trade-off between accuracy and inference time, highlighting the suitability of YOLOv11-nano for applications in drone development where accuracy takes precedence over processing speed. © 2024 IEEE.

关键词： Autonomous Drone Algorithm Drone Object Detection YOLO YOLOv11

来源：评论

学校读者我要写书评

暂无评论

Recommendation System and Its Techniques in Machine Learning: A Survey 1

引用

8th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Banwala, Neeru Singh, Gurpreet Singh, Jaspreet Goswami, Vishwajeet Shankar Bagnia, Aashima Data Science Department of Mathematics Chandigarh University Mohali India Department of Computer Science and Engineering Chandigarh University Mohali India Department of Mathematics Chandigarh University Mohali India

ISBN: (数字)9789811998584

ISBN: (纸本)9789811998577

Machine learning-based recommendation systems are formidable tools that target specific customers with tailored product and content recommendations based on their user data and behavioural patterns. Due to the abundance of information available today, it is now challenging to separate out and provide the user with the most pertinent information. Therefore, using recommendation systems to reduce time and costs for both the business and the user is now necessary to address the issue of information overload. Based on a user’s interest and past preferences, these systems might suggest suitable products to them, thus increasing revenue. This paper seeks to clarify the idea of the recommendation systems built upon, the many methods used to create these systems and the necessity of using these systems in the current and future environments. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Optimation Cavacity Vehicle Routing Problem with K-Nearest Neighbor in Classification of Goods Ditribution Route 7

Optimation Cavacity Vehicle Routing Problem with K-Nearest N...

引用

7th IEEE International Conference of computer science and Information Technology, ICOSNIKOM 2023

作者： Novelan, Muhammad Syahputra Efendi, Syahril Sihombing, Poltak Mawengkang, Herman Universitas Sumatera Utara Doctoral Program of Computer Science Faculty of Computer Science and Information Technology Medan Indonesia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Department of Computer Science Medan Indonesia Universitas Sumatera Utara Faculty of Mathematics and Natural Sciences Department of Mathematics Medan Indonesia

ISBN: (纸本)9798350360752

Industrial and distribution service problems that belong to combinatorial optimization include vehicle routing with Vehicle Routing Problem. This research builds a framework and implements it in a multi-class optimization model to reduce overfitting and misclassification results caused by unbalanced multiclassification in the influence of the number of 'nodes' on vehicle routes with machine learning. The problem of imbalance in vehicle route classification has been a challenge in the classification process and attracted the attention of a number of researchers. The purpose of the model in general is to gain an understanding of the mechanism in the problem so as to classify the imbalanced vehicle route data based on JNE delivery routes. The solution method that will be used by applying k-nearest neighbor to determine the amount of carrying capacity of the goods will then determine the delivery location point with the vehicle routing problem. So that this model can be a model in determining vehicle routes based on the capacity limit of the number of shipments of goods. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Load Balancer in Storage Level Service Offering Applications 5th

Performance Evaluation of Load Balancer in Storage Level Ser...

引用

5th International Conference on Recent Developments in Control, Automation and Power Engineering, RDCAPE 2023

作者： Vianny, Maria Manuel Bhardwaj, Rajat Bhardwaj, Vivek Sharma, Vikrant Virender Manikandan, S. Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamilnadu Chennai India Department of Computer Science and Engineering ASET Amity University Karnataka Bengaluru India School of Computer Science and Engineering Manipal University Jaipur Jaipur India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India Chandigarh University Punjab Mohali India Department of Information Technology E.G.S. Pillay Engineering College Tamil Nadu Nagapattinam India

ISBN: (纸本)9789819600465

Cloud computing is a world view appropriately characterized for IT contributions where data and resources are aggregated by web-based cloud administration organizations using planned hardware and packages, primarily based on the web. People could use at a reasonable cost. Combining resources may affect the ease with which those resources are accessed, which might result in an issue. Load control is the process of distributing network traffic among several servers. No server will be overburdened as a result of this. In order to increase user responsiveness, load regulation equitably distributes the tasks. Additionally, it improves client accessibility to projects and websites. This archive is being kept in order to better understand charge control. It is connected to other structures via correspondence bodies like the Internet. Load balancing is an important distributed computing space to stay away from work beyond the workload and provide equally important support. Different calculations are used to determine the complexity of the system. Our suggested technique selects 100 virtual computers and, with 92% accuracy, determines where an ideal storage facility is for use in real time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

A New Federated Learning Framework Against Gradient Inversion Attacks 39

A New Federated Learning Framework Against Gradient Inversio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Pengxin Zeng, Shuang Chen, Wenhao Zhang, Xiaodan Ren, Weihong Zhou, Yuyin Qu, Liangqiong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Beijing University of Technology China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering UC Santa Cruz United States

ISBN: (纸本)157735897X

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively "breaks the direct connection" between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Subspace Clustering in High-Dimensional data Streams:A Systematic Literature Review

引用

computers, Materials & Continua 2023年第5期75卷 4649-4668页

作者： Nur Laila Ab Ghani Izzatdin Abdul Aziz Said Jadid AbdulKadir Department of Computer and Information Sciences Universiti Teknologi PETRONASSeri Iskandar32610PerakMalaysia Centre for Research in Data Science(CeRDAS) Universiti Teknologi PETRONASSeri Iskandar32610PerakMalaysia

Clustering high dimensional data is challenging as data dimensionality increases the distance between data points,resulting in sparse regions that degrade clustering *** clustering is a common approach for processing high-dimensional data by finding relevant features for each cluster in the data *** clustering methods extend traditional clustering to account for the constraints imposed by data *** streams are not only high-dimensional,but also unbounded and *** necessitates the development of subspace clustering algorithms that can handle high dimensionality and adapt to the unique characteristics of data *** many articles have contributed to the literature review on data stream clustering,there is currently no specific review on subspace clustering algorithms in high-dimensional data ***,this article aims to systematically review the existing literature on subspace clustering of data streams in high-dimensional streaming *** review follows a systematic methodological approach and includes 18 articles for the final *** analysis focused on two research questions related to the general clustering process and dealing with the unbounded and evolving characteristics of data *** main findings relate to six elements:clustering process,cluster search,subspace search,synopsis structure,cluster maintenance,and evaluation *** algorithms use a two-phase clustering approach consisting of an initialization stage,a refinement stage,a cluster maintenance stage,and a final clustering *** density-based top-down subspace clustering approach is more widely used than the others because it is able to distinguish true clusters and outliers using projected *** algorithms implicitly adapt to the evolving nature of the data stream by using a time fading function that is sensitive to *** work can focus on the clustering framework,parameter optimiza

关键词： Clustering subspace clustering projected clustering data stream stream clustering high dimensionality evolving data stream concept drift

来源：评论

学校读者我要写书评

暂无评论

Wheat Disease Recognition Based on a Fusion Model with Improved Spatial and Channel Reconstruction Convolution Combined with Contextual Transformer 5

Wheat Disease Recognition Based on a Fusion Model with Impro...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Yang, Zicong Jin, Aitong Wang, Junxi Xie, Haifan Zhan, Xin Li, Qiaolin Zhuhai College of Science and Technology Department of Computer Zhuhai China Zhuhai College of Science and Technology Department of Statistics and Data Science Zhuhai China Zhuhai College of Science and Technology Department of Mechanical Engineering Zhuhai China Fujian University of Traditional Chinese Medicine School of Traditional Chinese Medicine Fuzhou China

ISBN: (纸本)9798350373820

Crop diseases cause loss of agricultural products and have a critical impact on society, the economy, and the environment, so it is crucial for early defending the wheat disease. However, seeking an expert diagnosis can contribute to delays and higher costs. Therefore, this paper proposes a deep learning neural network with improved spatial and channel reconstruction convolution combined with CoT Attention module, named SCCoT-WheatNet. This innovated neural network can recognize wheat disease. The experimental dataset was obtained from the Internet and some publicly available datasets using web crawler was technology. This modification is based on the VGG13 model. In the final two sections of the VGG13 model, feature extraction replaces conventional convolutional layers with Contextual Transformer module and spatial and channel reconstruction convolution block. The experiment adopts a cross-fold approach. In the first fold test, the results show that the average recognition accuracy of the SCCoT-WheatNet network is 9 6. 9 4%, which is higher than the classical VGG network and the Vision Transformer models of the last two years. © 2024 IEEE.

关键词： Convolution

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：