检索结果-内蒙古大学图书馆

15th International Conference on parallel processing and Applied Mathematics, PPAM 2024

作者： Lawenda, Marcin Samborski, Krzesimir Khloponin, Kyrylo Szustak, Lukasz Poznan Supercomputing and Networking Center Jana Pawla II 10 Poznań61-139 Poland Czestochowa University of Technology Dąbrowskiego 69 Częstochowa42-201 Poland

ISBN: (纸本)9783031857027

This work is concerned with the evaluation of the performance of parallelization of learning and tuning processes for image classification and large language models. For machine learning model in image recognition, various parallelization methods are developed based on different hardware and software scenarios: simple data parallelism, distributed data parallelism, and distributed processing. A detailed description of presented strategies is given, highlighting the challenges and benefits of their application. Furthermore, the impact of different dataset types on the tuning process of large language models is investigated. Experiments show to what extent the task type affects the iteration time in a multi-GPU environment, offering valuable insights into the optimal data utilization strategies to improve model performance. Furthermore, this study leverages the built-in parallelization mechanisms of PyTorch that can facilitate these tasks. Furthermore, performance profiling is incorporated into the study to thoroughly evaluate the impact of memory and communication operations during the training/tuning procedure. Test scenarios are developed and tested with numerous benchmarks on the NVIDIA H100 architecture showing efficiency through selected metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Speed Up Federated Learning in Heterogeneous Environments: A Dynamic Tiering Approach

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第5期12卷 5026-5035页

作者： Mahmoud Sajjadi Mohammadabadi, Seyed Zawad, Syed Yan, Feng Yang, Lei Univ Nevada Reno Dept Comp Sci & Engn Reno NV 89557 USA IBM Res Almaden Res Dept San Jose CA 95120 USA Univ Houston Comp Sci Dept Houston TX 77004 USA Univ Houston Elect & Comp Engn Dept Houston TX 77004 USA

Federated learning (FL) enables collaborative training of a model while keeping the training data decentralized and private. However, in Internet of Things systems, inherent heterogeneity in processing power, communication bandwidth, and task size can significantly hinder the efficient training of large models. Such heterogeneity would render vast variations in the training time of clients, lengthening overall training and wasting resources of faster clients. To tackle these heterogeneity challenges, we propose dynamic tiering-based FL (DTFL), a novel system that leverages distributed optimization principles to improve the edge learning performance. Based on clients' resources, DTFL dynamically offloads part of the global model to the server, alleviating resource constraints on slower clients and speeding up training. By leveraging split learning, DTFL offloads different portions of the global model to clients in different tiers and enables each client to update the models in parallel via local-loss-based training. This helps reduce the computation and communication demand on resource-constrained devices, mitigating the straggler problem. DTFL introduces a dynamic tier scheduler that uses tier profiling to estimate the expected training time of each client based on their historical training time, communication speed, and dataset size. The dynamic tier scheduler assigns clients to suitable tiers to minimize the overall training time in each round. We theoretically prove the convergence properties of DTFL and validate its effectiveness by training large models (ResNet-56 and ResNet-110) across varying numbers of clients (from 10 to 200) using the popular image datasets (CIFAR-10, CIFAR-100, CINIC-10, and HAM10000) under both I.I.D and non-I.I.D systems. DTFL seamlessly integrates various privacy measures without sacrificing performance. Extensive experimental results show that compared with state-of-the-art FL methods, DTFL can significantly reduce the training time b

关键词： Training Computational modeling Internet of Things Servers Federated learning Accuracy Dynamic scheduling Performance evaluation Optimization Load modeling distributed optimization edge computing federated learning (FL) heterogeneous devices split learning (SL)

来源：评论

学校读者我要写书评

暂无评论

25th International Conference on parallel and distributed Computing, Applications and Technologies, PDCAT 2024

25th International Conference on Parallel and Distributed Co...

引用

25th International Conference on parallel and distributed Computing, Applications and Technologies, PDCAT 2024

ISBN: (纸本)9789819642069

The proceedings contain 55 papers. The special focus in this conference is on parallel and distributed Computing: Applications and Technologies. The topics include: A Meta-reinforcement Learning Framework for Adaptive Quadrotor UAV Attitude Control;Securing Energy Transactions for Electric Vehicles: The Blockchain Approach and Encrypted NFTs;optimizing Task Allocation in Heterogeneous Agent Manufacturing Systems;MPG: Multi-modal Personal Health Graph for Alzheimer’s Disease Diagnosis;SMAC: A Secure Multi-authority Access Control Scheme with Attribute Unification for Fog Enabled IoT in E-Health;Convolutional Neural Networks Parameter Training for SCM Algorithm Based on Hausdorff Difference;handling Non-stationarity with Distribution Shifts and Data Dependency in Time Series Forecasting;the Two-Stage Stochastic Facility Location Game;regularized Non-monotone γ-weakly Submodular Maximization;fed-MoE: Efficient Federated Learning for Mixture-of-Experts Models via Empirical Pruning;WaitIO-Hybrid: Communication for Coupling MPI Programs Among Heterogeneous Systems;the Material Delivery Route Prediction Method Based on Deep Reinforcement Learning;privacy-Preserving in Medical image Analysis: A Review of methods and Applications;research on Task Migration Problem Based on Link Uncertainty in Adversarial Scenarios;optimizing Production Component Scheduling in Multivariate Industrial Networks with Dynamic Changes in Production Costs;multi-agent Collaboration for Time-Sensitive Tasks in Multiple Networked Adversarial Scenarios;containerized Data-Flow processing for Scalable Real-Time Analytics on Edge Devices;fast Approximation for Scheduling Malleable Jobs on parallel Batch Machines with Rejection;real-Time and In-Situ Temperature Profiling for Determining Detonation of White Dwarf Mergers;accparser: A Standalone OpenACC Parser and Its Usage on Mapping OpenACC to OpenMP Directives;Out-of-Memory GPU Sorting Using Asynchronous CUDA Streams;long-Term and Periodicity-Aware Spatio

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Offloading Control for Waste Sorting Based on Deep Q-Network 24th

Dynamic Offloading Control for Waste Sorting Based on Deep...

引用

24th International Conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

作者： Wang, Jing Wang, Xiaoyang Guo, Jianxiong Tang, Zhiqing Ding, Xingjian Wang, Tian Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (纸本)9789819615278

With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to solve waste sorting in wireless bin communication networks. Due to limited computational power, bins belonging to embedded devices rely on simple classification models with varying accuracy. In this scenario, consider a network of intelligent bins, each acting as an independent agent capable of deciding to offload an image to the edge server with a more accurate but resource-intensive model when the local classification is deemed inaccurate. Thus, Our goal is to find a lightweight online offloading policy that can achieve the best possible sorting accuracy while balancing transmission traffic. The method utilizes a Deep Q-network algorithm that enables each intelligent bin to make image-processing decisions autonomously. In the experiment, we validate the effectiveness of improving the performance of waste classification compared with existing flow control methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： distributed Resource Allocation Intelligent Waste Management Waste Sorting Wireless Communication Network

来源：评论

学校读者我要写书评

暂无评论

A Counterfactual Ultrasound Anti-Interference Self-Supervised Network for B-mode Ultrasound Tongue Extraction

A Counterfactual Ultrasound Anti-Interference Self-Supervise...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jia, Yan Cheng, Yuqing Xu, Kele Dou, Yong Qiao, Peng He, Zhouyu National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (纸本)9798350368741

B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue's surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network's ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI. © 2025 IEEE.

关键词： contour extraction counterfactual inference self-supervised learning speech production ultrasound image

来源：评论

学校读者我要写书评

暂无评论

Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1237-1250页

作者： Zhang, Jie Cao, Ke Yan, Keyu Lin, Yunlong He, Xuanhua Wang, Yingying Li, Rui Xie, Chengjun Zhang, Jun Zhou, Man Chinese Acad Sci Inst Intelligent Machines Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Grad Sch Sci Isl Branch Hefei 230026 Peoples R China Chinese Acad Sci Inst Intelligent Machines Hefei Inst Phys Sci Hefei 230031 Peoples R China Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Univ Key Lab Multimedia Trusted Percept & Efficient Com Minist Educ China Xiamen 361005 Peoples R China Chinese Acad Sci High Magnet Field Lab Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230026 Peoples R China

Pan-sharpening aims to generate high-detail multi-spectral images (HRMS) through the fusion of panchromatic (PAN) and multi-spectral (MS) images. However, existing pan-sharpening methods often suffer from significant performance degradation when dealing with out-of-distribution data, as they assume the training and test datasets are independent and identically distributed. To overcome this challenge, we propose a novel frequency domain-irrelevant feature learning framework that exhibits exceptional generalization capabilities. Our approach involves parallel extraction and processing of domain-irrelevant information from the amplitude and phase components of the input images. Specifically, we design a frequency information separation module to extract the amplitude and phase components of the paired images. The learnable high-pass filter is then employed to eliminate domain-specific information from the amplitude spectrums. After that, we devised two specialized sub-networks (AFL-Net and PFL-Net) to perform targeted learning of the frequency domain-irrelevant information. This allows our method to effectively capture the complementary domain-irrelevant information contained in the amplitude and phase spectra of the images. Finally, the information fusion and restoration module dynamically adjusts the feature channel weights, enabling the network to output high-quality HRMS images. Through this frequency domain-irrelevant feature learning framework, our method balances generalization capability and network performance on the distribution of training dataset. Extensive experiments conducted on various satellite datasets demonstrate the effectiveness of our method for generalized pan-sharpening. Our proposed network outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality, showcasing its superior ability to handle diverse, out-of-distribution data.

关键词： Representation learning Frequency-domain analysis Feature extraction Data mining Training Spatial resolution Circuits and systems image restoration Fourier transforms Distortion Frequency domain-irrelevant pan-sharpening learnable filter amplitude spectrums

来源：评论

学校读者我要写书评

暂无评论

A Noise-Based Approach Augmented with Neural Cleanse and JPEG Compression to Counter Adversarial Attacks on image Classification Systems

A Noise-Based Approach Augmented with Neural Cleanse and JPE...

引用

Euromicro Conference on parallel, distributed and Network-Based processing

作者： Igor Kotenko Igor Saenko Oleg Lauta Nikita Vasiliev Vladimir Sadovnikov Laboratory of Computer Security Problems St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS) Saint-Petersburg Russia Department of Telecommunications and Information Security Admiral Makarov State University of Maritime and Inland Shipping Saint-Petersburg Russia

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

Adversarial attacks are now becoming quite a dangerous means of disrupting image processing systems that use machine learning methods for decision making. Therefore, developing effective countermeasures against adversarial attacks is becoming quite an important area of cybersecurity. The paper proposes a noise-based approach to countering adversarial attacks that is augmented with neural-cleanse and jpeg-compression technologies. The idea of the proposed approach is that adding noise distorts the effect of an adversarial attack, and neural cleaning and jpeg compression eliminate the consequences of such an effect. The paper examines the three most well-known types of adversarial attacks: Fast Gradient Sign Method, Zeroth Order Optimization and One Pixel Attack. These attacks manipulate input data, resulting in misclassification or incorrect predictions by exploiting high-frequency components that are undetectable to humans. The research was carried out on two datasets: MNIST-JPG and PC Parts images. Two types of noise were used: Gaussian and Poisson. During the experiments, optimal parameters for these types of noise were found, ensuring maximum accuracy of image recognition after exposure to adversarial attacks.

关键词： Resistance image recognition image coding image resolution Noise Transform coding Machine learning Distortion Optimization image classification

来源：评论

学校读者我要写书评

暂无评论

MiDedup: A Restore-Friendly Deduplication Method on Docker image Storage Systems 20th

MiDedup: A Restore-Friendly Deduplication Method on Docker ...

引用

20th IFIP WG 10.3 International Conference on Network and parallel Computing, NPC 2024

作者： Qin, Lisha Tan, Haoliang Zou, Xiangyu Ou, Wenhao Wei, Yan Huang, Rubing Xia, Wen Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory Shenzhen China Zhongruan International Technology Service Co. Ltd. Shenzhen China Macau University of Science and Technology Macao China

ISBN: (纸本)9789819628292

Docker image storage systems, like Docker registry, often employ deduplication to reduce storage overhead. Existing deduplication methods for these systems detect redundancy at either layer or file level, each with its own advantages and limitations. Layer-level deduplication offers much faster restoration but lower deduplication ratio, as it eliminates duplicate layers while ignoring duplicate files across layers. Conversely, file-level deduplication offers a higher deduplication ratio but slower restoration, as removing duplicate files scatters the files of a layer, leading to multiple disk read I/O during restoration. Our analysis reveals that the slow restoration in file-level deduplication partly stems from ignoring file-layer relationships. In this paper, we propose MiDedup, a new Docker deduplication method. MiDedup detects redundancy at file-level and organizes files into a restore-friendly layout by considering file-layer relationships to enhance restore speed. Our studies also show that duplicated files of one layer are not uniformly distributed across different layers. MiDedup uses this insight to skip deduplicating scattered files to further optimize the file layout for faster restoration. Evaluations indicate that MiDedup achieves restore speeds that are 8–19× faster than file-level deduplication (slightly slower than layer-level one), while maintaining 9–47% higher deduplication ratios than layer-level deduplication. © IFIP International Federation for Information processing 2025.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Frequency-Domain Guided Multiple parallel Kernels Network for Low-Light Remote Sensing image Enhancement

Frequency-Domain Guided Multiple Parallel Kernels Network fo...

引用

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

作者： Jingxuan Zhou Hao Li Jinlong Wang Xiongxin Tang Fanjiang Xu Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Due to dark environments, optical aberrations, etc, the remote sensing images are often submerged under low contrast degradation, which greatly hinders their practical applications for agricultural management and other related tasks. The surface features of remote sensing images are often continuously distributed in space, thus, the sizes of the network’s receptive fields and its ability to learn long-range dependencies are crucial for restoring low-light remote sensing images. Existing methods based on CNN provide limited receptive fields, while Transformer-based methods are constrained by their quadratic computational complexity. To cope with these issues, we propose a novel low-light remote sensing image enhancement network that combines multi-scale receptive fields with frequency-domain attention. Specifically, this network employs multiple parallel kernels of varying sizes to learn multi-scale local features in the spatial domain and complements frequency-domain information to learn global long-range correlations, which achieves local-global feature extraction and further facilitates subsequent degraded images enhancement. We have conducted extensive experiments to demonstrate that our network outperforms existing methods quantitatively and achieves exceptional visual performance, which fully highlights the effectiveness and superiority of our method in enhancing low-light remote sensing images.

关键词： Visualization Frequency-domain analysis Transforms Speech enhancement Feature extraction Transformers image restoration Kernel Remote sensing image enhancement

来源：评论

学校读者我要写书评

暂无评论

Review of parallel processing methods for Big image Data Applications

Review of Parallel Processing Methods for Big Image Data App...

引用

International Conference on Communication, Computing and Electronics Systems, ICCCES 2019

作者： Vigneshwari, K. Kalaiselvi, K. Department of Computer Science VELS Institute of Science Technology and Advanced Studies Chennai600117 India Formerly Vels University Chennai600117 India

ISBN: (纸本)9789811526114

The coexistence of technologies, like big data application, cloud computing, and the numerous images in the Web has paved the need for new image processing algorithms that exploit the processed image for diverse applications. There arises a need for new image processing algorithms to utilize the processed image for diverse applications though many techniques with variations exist. Ultimately, the enduring issue is to enhance the effectiveness of huge image processing and to maintain the combination of the same with recent works. This paper presents a review of the newest progress in researches on parallel processing methods for the processing of big data. Initially, the reviews about the parallel processing methods were carried out by highlighting some promising parallel processing methods in recent studies, such as the representation of MapReduce (MR) framework, distributed, parallel methods, and Hadoop framework. Subsequently, focus on analysis and deliberations about the challenges and promising solutions of parallel computing methods on big data in various applications and on image processing applications were made and concluded with a summary of number of open problems and research areas. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Big data

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：