检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gao, Fei Hu, Ming Xie, Zhiyu Shi, Peichang Xie, Xiaofei Yi, Guodong Wang, Huaimin National Key Lab. of Parallel and Distributed Processing National University of Defense Technology Changsha China School of Computing and Information Systems Singapore Management University Singapore Xiangjiang Lab Changsha China

With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud Computing (JCC) is promising to break through the resource constraints caused by heterogeneous edge devices in the traditional Federated Learning (FL) paradigm. Specifically, with the protection from TEE, data owners can achieve efficient model training with high-performance AI services in the cloud. By providing additional FL services, cloud service providers can achieve collaborative learning among data owners. However, FLaaS still faces three challenges, i.e., i) low training performance caused by heterogeneous data among data owners, ii) high communication overhead among different clouds (i.e., data centers), and iii) lack of efficient resource scheduling strategies to balance training time and cost. To address these challenges, this paper presents a novel asynchronous FL approach named NebulaFL for collaborative model training among multiple clouds. To address data heterogeneity issues, NebulaFL adopts a version control-based asynchronous FL training scheme in each data center to balance training time among data owners. To reduce communication overhead, NebulaFL adopts a decentralized model rotation mechanism to achieve effective knowledge sharing among data centers. To balance training time and cost, NebulaFL integrates a reward-guided strategy for data owners selection and resource scheduling. The experimental results demonstrate that, compared to the state-of-the-art FL methods, NebulaFL can achieve up to 5.71% accuracy improvement. In addition, NebulaFL can reduce up to 50% communication overhead and 61.94% costs under a target accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Customizing Super-Resolution Framework According to image Features 18

Customizing Super-Resolution Framework According to Image Fe...

引用

18th IEEE Int Symp on parallel and distributed Proc with Applicat (ISPA) / 10th IEEE Int Conf on Big Data and Cloud Comp (BDCloud) / IEEE Int Symp on Social Comp and Networking (SocialCom) / IEEE Int Conf on Sustainable Comp and Commun (SustainCom)

作者： Yuan, Ninghui Liu, Jingyu Wang, Qiong Shen, Li Natl Univ Def Technol Sch Comp Changsha Peoples R China

ISBN: (纸本)9781665414852

As a popular research field of computer vision, super resolution(SR) has received more and more attention in recent years. Although the deep learning methods have achieved good results in SR, there are still some problems. For example, the previous models are often based on single depth mechanism. This means that the SR reconstruction problem of all images is regarded as of equal complexity. And we found that some images have more details and are suitable for recovering in complex models, while other images have less texture information and are suitable for recovering in simple models. At the same time, the size of the training set is too large, which creats a lot of resource overhead. To solve these problems, this paper proposes a new SR framework can be customized according to image features. We choose 3 representative models for testing and in test our framework can reduce the size of the training set by 41.9%. For MSRResNet, we can reduce the training time from 2517 minutes to 2449 minutes. The reconstruction quality of 61% test images has been improved and the average perceptual index has dropped from 5.1912 to 5.155833, at the same time the reconstruction time has been optimized from 85 seconds to 59 seconds. For SRGAN, the training time can be reduced from 1920 minutes to 1812 minutes. The reconstruction quality of 58% test images have been improved and the average perceptual index has dropped from 2.0869 to 2.0509, while the reconstruction time has been optimized from 82 seconds to 46 seconds. For ESRGAN, the training time can be reduced from 4368 minutes to 4249 minutes. The reconstruction quality of 78% test images has been improved and the average perceptual index has dropped from 2.2041 to 2.0535. The reconstruction time has been optimized from 138 seconds to 95 seconds. Our framework can improve the effect of super-resolution models while reducing the resource overhead.

关键词： super-resolution framework random forest

来源：评论

学校读者我要写书评

暂无评论

A novel experimental based statistical study for water management in proton exchange membrane fuel cells

引用

APPLIED ENERGY 2020年第0期264卷 114713-000页

作者： Hasheminasab, M. Kermani, M. J. Nourazar, S. S. Khodsiani, M. H. Amirkabir Univ Technol Dept Mech Engn 424 Hafez Ave Tehran 158754413 Iran Ctr Solar Energy & Hydrogen Res ZSW Helmholtz Str 8 D-89081 Ulm Germany

Water management is a key issue in low-temperature PEMFCs. For proper water management, processes leading to dehydration or flooding of cells should be clearly understood, hence prevented. Here, the effects of Anode Stoichiometry (AST), Cathode Stoichiometry (CST) and inlet gas temperature (T*) on the cell performance and water management in PEMFC are experimentally studied. Two methods, namely (i) direct- and (ii) indirect-method are employed to monitor water accumulation in cathode flow channels of a multi-path-parallel-serpentine PEMFC. Flow visualization served as direct method (item (i)), in which recorded videos of transparent channels were analyzed via an image-processing algorithm to monitor water coverage ratio (WCR). Simultaneously an inlet-to-exit pressure drop coefficient (Phi) was defined for indirect-method (item (ii)). AST, CST and T* were taken as input to provide three experimental based correlations for generated electrical power, WCR and Phi as a response. According to the results, an increase in AST reduces water-content in cathode channels;decreases performance also raises the sensitivity of generated power to variations in other operating-parameters. However, an increase in CST and T* reduces water contents in cathode channels also increases the cell power and lowers sensitivity of the power to the variation of other operating-parameters. It is observed that strong connectivity exists between WCR and Phi. This is verified by obtaining a high Pearson correlation coefficient of 0.887 between WCR and Phi. It is demonstrated that dehydration and flooding could be prevented when 3 <= WCR <= 4, from which appropriate operating-parameters AST, CST and T* could be retrieved.

关键词： Performance enhancement of PEMFC Water management Two-phase flow Design of Experiment (DOE) Direct optical visualization Digital image processing

来源：评论

学校读者我要写书评

暂无评论

WBA: A Warping-based Approach to Generating Imperceptible Adversarial Examples

WBA: A Warping-based Approach to Generating Imperceptible Ad...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Chengyao Hua Shigeng Zhang Weiping Wang Zhankai Li Jian Zhang School of Computer Science and Engineering Central South University Changsha China Science and Technology on Parallel and Distributed Processing Laboratory (PDL)

The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and imageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.

关键词： Measurement Deep learning Privacy image recognition Perturbation methods Neural networks Robustness

来源：评论

学校读者我要写书评

暂无评论

Maximum Mean and Covariance Discrepancy for Unsupervised Domain Adaptation

引用

NEURAL processing LETTERS 2020年第1期51卷 347-366页

作者： Zhang, Wenju Zhang, Xiang Lan, Long Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha 410073 Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Peoples R China

A fundamental research topic in domain adaptation is how best to evaluate the distribution discrepancy across domains. The maximum mean discrepancy (MMD) is one of the most commonly used statistical distances in this field. However, information about distributions could be lost when adopting non-characteristic kernels by MMD. To address this issue, we devise a new distribution metric named maximum mean and covariance discrepancy (MMCD) by combining MMD and the proposed maximum covariance discrepancy (MCD). MCD probes the second-order statistics in reproducing kernel Hilbert space, which equips MMCD to capture more information compared to MMD alone. To verify the efficacy of MMCD, an unsupervised learning model based on MMCD abbreviated as McDA was proposed and efficiently optimized to resolve the domain adaptation problem. Experiments on image classification conducted on two benchmark datasets show that McDA outperforms other representative domain adaptation methods, which implies the effectiveness of MMCD in domain adaptation.

关键词： Domain adaptation image classification Dimensionality reduction Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A parallel Drone image Mosaic Method Based on Apache Spark 1

引用

9th EAI International Conference on Cloud Computing, CloudComp 2019 and the 4th EAI International Conference on Smart Grid and Innovative Frontiers in Telecommunications, SmartGIFT 2019

作者： Wu, Yirui Ge, Lanbo Luo, Yuchi Teng, Deqiang Feng, Jun College of Computer and Information Hohai University Nanjing China

ISBN: (数字)9783030485139

ISBN: (纸本)9783030485122

MapReduce has been widely used to process large-scale data in the past decade. Among the quantity of such cloud computing applications, we pay special attention to distributed mosaic methods based on numerous drone images, which suffers from costly processing time. In this paper, a novel computing framework called Apache Spark is introduced to pursue instant responses for the quantity of drone image mosaic requests. To assure high performance of Spark-based algorithms in a complex cloud computing environment, we specially design a distributed and parallel drone image mosaic method. By modifying to be fit for fast and parallel running, all steps of the proposed mosaic method can be executed in an efficient and parallel manner. We implement the proposed method on Apache Spark platform and apply it to a few self-collected datasets. Experiments indicate that our Spark-based parallel algorithm is of great efficiency and is robust to process low-quality drone aerial images. © 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Poetic Expression Through Scenery: Sentimental Chinese Classical Poetry Generation from images 26th

Poetic Expression Through Scenery: Sentimental Chinese Class...

引用

26th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Li, Haotian Zhu, Jiatao Cao, Sichen Li, Xiangyu Zeng, Jiajun Wang, Peng Southeast Univ Sch Artificial Intelligence Nanjing Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China Southeast Univ Sch Cyber Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9783030731960;9783030731977

Most Chinese poetry generation methods only accept texts or user-specified words as input, which contradicts with the fact that ancient Chinese wrote poems inspired by visions, hearings and feelings. This paper proposes a method to generate sentimental Chinese classical poetry automatically from images based on convolutional neural networks and the language model. First, our method extracts visual information from the image and maps it to initial keywords by two parallel image classification models, then filters and extends these keywords to form a keywords set which is finally input into the poetry generation model to generate poems of different genres. A bi-directional generation algorithm and two fluency checkers are proposed to ensure the diversity and quality of generated poems, respectively. Besides, we constrain the range of optional keywords and define three sentiment-related keywords dictionary to avoid modern words that lead to incoherent content as well as ensure the emotional consistency with given images. Both human and automatic evaluation results demonstrate that our method can reach a better performance on quality and diversity of generated poems.

关键词： Information extraction and summarization Poetry generation Vision-driven modelling Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Unified Density-Aware image Dehazing and Object Detection in Real-World Hazy Scenes 15th

Unified Density-Aware Image Dehazing and Object Detection in...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High -Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of an HPC-based Expert System to speed-up Retail Data Analysis using Residual Networks Combined with parallel Association Rule Mining and Scalable Recommenders 44

Design and Evaluation of an HPC-based Expert System to speed...

引用

44th International Convention on Information, Communication and Electronic Technology, MIPRO 2021

作者： Barakat, C. Riedel, M. Brynjolfsson, S. Cavallaro, G. Busch, J. Sedona, R. School of Engineering and Natural Sciences University of Iceland Iceland Jülich Supercomputing Centre Forschungszentrum Jülich Germany

ISBN: (纸本)9789532331011

Given the Covid-19 pandemic, the retail industry shifts many business models to enable more online purchases that produce large transaction data quantities (i.e., big data). Data science methods infer seasonal trends about products from this data and spikes in purchases, the effectiveness of advertising campaigns, or brand loyalty but require extensive processing power leveraging High-Performance Computing to deal with large transaction datasets. This paper proposes an High-Performance Computing-based expert system architectural design tailored for 'big data analysis' in the retail industry, providing data science methods and tools to speed up the data analysis with conceptual interoperability to commercial cloud-based services. Our expert system leverages an innovative Modular Supercomputer Architecture to enable the fast analysis by using parallel and distributed algorithms such as association rule mining (i.e., FP-Growth) and recommender methods (i.e., collaborative filtering). It enables the seamless use of accelerators of supercomputers or cloud-based systems to perform automated product tagging (i.e., residual deep learning networks for product image analysis) to obtain colour, shapes automatically, and other product features. We validate our expert system and its enhanced knowledge representation with commercial datasets obtained from our ON4OFF research project in a retail case study in the beauty sector. © 2021 Croatian Society MIPRO.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Towards distributed node similarity search on graphs

引用

WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS 2020年第6期23卷 3025-3053页

作者： Zhang, Tianming Gao, Yunjun Zheng, Baihua Chen, Lu Wen, Shiting Guo, Wei Zhejiang Univ Technol Coll Comp Sci & Software Engn Hangzhou Peoples R China Singapore Management Univ Sch Informat Syst Singapore Singapore Aalborg Univ Dept Comp Sci Aalborg Denmark Zhejiang Univ Ningbo Inst Technol Ningbo Peoples R China

Node similarity search on graphs has wide applications in recommendation, link prediction, to name just a few. However, existing studies are insufficient due to two reasons: (i) the scale of the real-world graph is growing rapidly, and (ii) vertices are always associated with complex attributes. In this paper, we propose an efficiently distributed framework to support node similarity search on massive graphs, which considers both graph structure correlation and node attribute similarity in metric spaces. The framework consists of preprocessing stage and query stage. In the preprocessing stage, a parallel KD-tree construction (KDC) algorithm is developed to form a newly defined graph so-calledhybrid graph, in order to integrate node attribute similarity into the original graph. To equally divide graph vertices into subsets, KDC adopts the KD-tree partitioning after the pivot mapping. In addition, two metric pruning rules and an optimized allocation strategy are presented to reduce communication and computation costs. In the query stage, based on the formed hybrid graph, we develop similarity search methods using random walk with restart (RWR) to measure node similarity. To boost efficiency, we derive tight bounds to rapidly shrink the search region. Extensive experiments with three real massive graphs are conducted to verify the effectiveness, efficiency, and scalability of our proposed techniques.

关键词： Graph Node similarity search distributed processing Algorithm

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：