检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

作者： Mobaraki, Mobina Ahani, Soodeh Yi, Kwang Moo Asadi, Mahyar Van Heusden, Klaske Dumont, Guy A. University of British Columbia Electrical and Computer Engineering Vancouver Canada University of British Columbia Computer Science Vancouver Canada Novarc Technologies Co. Vancouver Canada School of Mechanical Engineering Kelowna Canada

ISBN: (纸本)9798350359855

We propose an efficient method to label the frames of a video consistently and quickly. Our method is motivated by welding videos, where molten metal moves continuously, and some frames may be noisy due to the high intensity of arc and spatters that can obscure the desired point to be annotated. The traditional annotation methods which pause the videos and annotate each frame individually are time-consuming and may result in inconsistent labeling between different annotators for noisy frames of a video. Our new proposed method benefits from the fact that video sequences are contiguous. We track the location of the cursor while the video is being played, with the user controlling the playback speed, including the playback direction. We process the recorded cursor locations to convert them to the final annotation. Compared to frame-to-frame annotation methods, we show that our proposed interface speeds up the annotating process by 21 times while maintaining consistency of the labels. © 2023 IEEE.

关键词： Liquid metals

来源：评论

学校读者我要写书评

暂无评论

ViT-Reg: Regression-Focused Hardware-Aware Fine-Tuning for ViT on tinyML Platforms

IEEE Design and Test

引用

IEEE Design and Test 2024年

作者： Shaharear, Md Ragib Mazumder, Arnab Neelim Mohsenin, Tinoosh Johns Hopkins University Department of Electrical & Computer Engineering United States University of Maryland Department of Computer Science & Electrical Engineering Baltimore County United States

Vision Transformers (ViTs) have demonstrated significant improvements in image classification tasks. However, deploying them on resource-constrained tinyML platforms presents considerable challenges due to their high computational demands and dynamic power consumption. Current methods rely heavily on computationally intensive architecture search techniques to identify optimal configurations, which are not well-suited for tinyML devices. This paper introduces ViT-Reg, a regression-based hardware-aware fine-tuning approach that identifies suitable ViT architectures for tinyML platforms. The proposed method enables efficient exploration of the configuration space, drastically reducing the computational overhead typically associated with architecture searches. ViT-Reg is hardware-aware, utilizing polynomial regression to narrow the search space while treating accuracy as a constraint. In experiments conducted on the CIFAR-10 and Tiny-ImageNet datasets, ViT-Reg deployed on Nvidia Jetson Nano achieved a 55.6% and 37.4% reduction in dynamic power consumption, along with a 65% and 60% improvement in energy efficiency compared to baseline ViT models. Finally, ViT-Reg provides an 8× improvement in energy efficiency relative to recent hardware implementations of the VGG model. © 2024 IEEE.

关键词： real-time and energy efficient deployment Regression tinyML Hardware Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Data Processing with Amortized Analysis and Splay Trees for Cyber Threat Intelligence 2023

Enhancing Cloud Data Processing with Amortized Analysis and ...

引用

15th International Conference on Contemporary Computing, IC3 2023

作者： Westmoreland, Deven Hossain, Gahangir Electrical Engineering and Computer Science Texas A&M University-Kingsville United States Information Science University of North Texas United States

ISBN: (纸本)9798400700224

This paper focuses on using amortized analysis with splay trees to calculate the time complexity in cyber threats on the cloud network. The paper explains little bit detail on how each of these analysis and modeling methods work, and then shows how to use the amortized algorithm for cyber intelligence - calculating attack vectors efficiently so that it reaches a time complexity of O(log n) for the splay operations. Amortized analysis is good for determining a better time complexity than when worst-case is used in a way that is too pessimistic and may not even be possible to happen, hence proposed an effective method in robust cyber incidence identification. The distributed network on the clouds forms a tree, hence the splay trees are proposed as a good alternative to other binary search trees, in improving amortized calculation. Finally, the combined approach helps speed up computation efficiency. © 2023 ACM.

关键词： Binary trees

来源：评论

学校读者我要写书评

暂无评论

Second Order Rate Regions of Gaussian Broadcast Channels under Heterogeneous Blocklength Constraints

引用

IEEE Transactions on Communications 2024年第2期72卷 801-814页

作者： Lin, Pin-Hsun Lin, Shih-Chun Chen, Peng-Wei Mross, Marcel A. Jorswieck, Eduard A. Technische Universitaät Braunschweig Institute for Communications Technology Braunschweig38106 Germany National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan Hsinchu300031 Taiwan

Future wireless access networks aim to simultaneously support a large number of devices with heterogeneous service requirements, including data rates, error rates, and latencies. While achievable rate and capacity results exist for Gaussian broadcast channels in the asymptotic blocklength regime, the characterization of second-order achievable rate regions for heterogeneous blocklength constraints is not available. Therefore, we investigate a two-user Gaussian broadcast channel (GBC) with heterogeneous blocklength constraints, specified according to users' channel output signal-To-noise ratios (SNRs). We assume that the user with higher output SNR has a shorter blocklength constraint. We show that with sufficiently large output SNR, the stronger user can perform the early decoding (ED) technique to decode and subtract the interference via successive interference cancellation (SIC). To achieve this goal, we derive an explicit lower bound on the necessary number of received symbols for a successful ED, using an independent and identically distributed Gaussian input. The second-order rate region is also derived. Numerical results show that ED can outperform the hybrid non-orthogonal multiple access scheme when the stronger channel is sufficiently better than the weaker one. Under the considered setting, about 7-dB SNR gain can be achieved compared to treating interference as noise. These results show that ED with SIC is a promising technique for future wireless networks. © 1972-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A WSN Node Fault Diagnosis Model Based on BRB with Self-Adaptive Quality Factor

引用

computers, Materials & Continua 2023年第4期75卷 1157-1177页

作者： Guo-Wen Sun Gang Xiang Wei He Kai Tang Zi-Yi Wang Hai-Long Zhu School of Computer Science and Information Engineering Harbin Normal UniversitySongbei DistrictHarbin150025China Beihang University School of Automation Science and Electrical Engineering Beijing100191China Beijing Aerospace Automatic Control Institute Beijing100074China Rocket Force University of Engineering Xi’anShaanxi Province710025China

Wireless sensor networks (WSNs) operate in complex and harshenvironments;thus, node faults are inevitable. Therefore, fault diagnosis ofthe WSNs node is essential. Affected by the harsh working environment ofWSNs and wireless data transmission, the data collected by WSNs containnoisy data, leading to unreliable data among the data features extracted duringfault diagnosis. To reduce the influence of unreliable data features on faultdiagnosis accuracy, this paper proposes a belief rule base (BRB) with a selfadaptivequality factor (BRB-SAQF) fault diagnosis model. First, the datafeatures required for WSN node fault diagnosis are extracted. Second, thequality factors of input attributes are introduced and calculated. Third, themodel inference process with an attribute quality factor is designed. Fourth,the projection covariance matrix adaptation evolution strategy (P-CMA-ES)algorithm is used to optimize the model’s initial parameters. Finally, the effectivenessof the proposed model is verified by comparing the commonly usedfault diagnosis methods for WSN nodes with the BRB method consideringstatic attribute reliability (BRB-Sr). The experimental results show that BRBSAQFcan reduce the influence of unreliable data features. The self-adaptivequality factor calculation method is more reasonable and accurate than thestatic attribute reliability method.

关键词： Self-adaptive quality factor belief rule base wireless sensor networks fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Evaluating collaborative rationality-based decisions: A literature review

Evaluating collaborative rationality-based decisions: A lite...

引用

2022 International Conference on ENTERprise Information Systems, CENTERIS 2022 - International Conference on Project MANagement, ProjMAN 2022 and International Conference on Health and Social Care Information Systems and Technologies, HCist 2022

作者： Elgendy, Nada Elragal, Ahmed Päivärinta, Tero M3S Faculty of Information Technology and Electrical Engineering University of Oulu Finland Department of Computer Science Electrical and Space Engineering Lulea University of Technology Sweden

Decision making has evolved throughout the years, nowadays harnessing massive amounts and types of data through the unprecedented capabilities of data science, analytics, machine learning, and artificial intelligence. This has potentially led to higher quality and more informed decisions based on the collaborative rationality between humans and machines, no longer bounded by the cognitive capacity and limited rationality of each on their own. However, the multiplicity of modes of collaboration and interaction between humans and machines has also increased the complexity of decision making, consequentially complicating ex-Ante and ex-post decision evaluation. Nevertheless, evaluation remains crucial to enable human and machine learning, rationalization, and sensemaking. This paper addresses the need for more research on why and how to evaluate collaborative rationality-based decisions, setting the stage for future studies in developing holistic evaluation solutions. By analyzing four relevant streams of literature: 1) classical decision theory and organizational management, 2) cognitive and neuroscience, 3) AI and ML, and 4) data-driven decision making, we highlight the limitations of current literature in considering a holistic evaluation perspective. Finally, we elaborate the theoretical underpinnings from the knowledge base on how humans and machines evaluate decisions, and the considerations for evaluating collaborative rationality-based decisions. © 2023 Elsevier B.V.. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A hybrid optimization approach for securing cloud-based e-health systems

引用

Multimedia Tools and Applications 2024年第16期84卷 1-36页

作者： Altherwi, Abdulhadi Ahmad, Mohammad Tauheed Alam, Md. Moddassir Mirza, Hidayath Sultana, Nazia Pasha, Amjad Ali Sultana, Nishat Khan, Asif Irshad Alam, Md Mottahir Azim, Rezaul Department of Industrial Engineering College of Engineering and Computer Science Jazan University PO Box. 706 Jazan45142 Saudi Arabia College of Medicine King Khalid University Abha Saudi Arabia Department of Health Information Management and Technology College of Applied Medical Sciences University of Hafr Al-Batin Hafr Al-Batin Saudi Arabia Department of Electrical and Electronic Engineering College of Engineering and Computer Science Jazan University Jazan45142 Saudi Arabia Government Medical College Siddipet Ensanpalli Siddipet District Telangana502114 India Aerospace Engineering Department King Abdulaziz University Jeddah21589 Saudi Arabia Department of Business Administration Applied College Jazan University P. O. Box 706 Jazan45142 Saudi Arabia Department of Computer Science Aligarh Muslim University Uttar Pradesh Aligarh202002 India Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz Jeddah21589 Saudi Arabia Department of Physics University of Chittagong Chattogram4331 Bangladesh

In modern healthcare, cloud-based e-health technology offers substantial benefits but faces significant security challenges. Sensitive patient data is vulnerable to cyber threats during transmission and storage, potentially enabling unethical collaboration between healthcare professionals and cloud storage providers. This paper aims to develop a robust security framework that safeguards patient privacy and prevents unauthorized access to sensitive medical information in remote patient health monitoring systems. The study presents an Artificial Hybrid Optimization with an Attribute-Based Encryption (AHO-ABE) model. The model leverages cryptographic techniques and hybrid optimization to enhance data security. Specifically, whale optimization (WO) is used for efficient key generation, while sheep flock optimization (SFO) is employed for continuous network surveillance. Experimental results demonstrate that the AHO-ABE model significantly enhances data security, outperforming existing RPM-MEC, AID, AI-HCS, and IoT-HMS approaches. The model exhibits superior resilience against unauthorized access and data breaches, achieving a 5 ms execution time, 850 kbps throughput, 0.121 mJ energy usage, and 4 s latency. Combining cryptographic techniques with hybrid optimization algorithms, the AHO-ABE model provides a robust framework for safeguarding sensitive medical information. This approach ensures the integrity and confidentiality of patient data in remote healthcare settings, offering an effective solution against high-performance cyber attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Regional Style and Color Transfer 5

Regional Style and Color Transfer

引用

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

作者： Ding, Zhicheng Li, Panfeng Yang, Qikai Li, Siyang Gong, Qingtian Columbia University Fu Foundation School of Engineering and Applied Science New York United States University of Michigan Electrical Engineering and Computer Science Ann Arbor United States University of Illinois Urbana-Champaign Department of Computer Science Urbana United States Pace University Lubin School of Business New York United States

ISBN: (纸本)9798350373820

This paper presents a novel contribution to the field of regional style transfer. Existing methods often suffer from the drawback of applying style homogeneously across the entire image, leading to stylistic inconsistencies or foreground object twisted when applied to images with foreground elements such as person figures. To address this limitation, we propose a new approach that leverages a segmentation network to precisely isolate foreground objects within the input image. Subsequently, style transfer is applied exclusively to the background region. The isolated foreground objects are then carefully reintegrated into the style-transferred background. To enhance the visual coherence between foreground and background, a color transfer step is employed on the foreground elements prior to their reincorporation. Finally, we utilize feathering techniques to achieve a seamless amalgamation of foreground and background, resulting in a visually unified and aesthetically pleasing final composition. Extensive evaluations demonstrate that our proposed approach yields significantly more natural stylistic transformations compared to conventional methods. © 2024 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System

Smart-Infinity: Fast Large Language Model Training using Nea...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Hongsun Jang Jaeyong Song Jaewon Jung Jaeyoung Park Youngsok Kim Jinho Lee Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering University of Texas at Austin Department of Computer Science Yonsei University

The recent huge advance of Large Language Models (LLMs) is mainly driven by the increase in the number of parameters. This has led to substantial memory capacity requirements, necessitating the use of dozens of GPUs just to meet the capacity. One popular solution to this is storage-offloaded training, which uses host memory and storage as an extended memory hierarchy. However, this obviously comes at the cost of storage bandwidth bottleneck because storage devices have orders of magnitude lower bandwidth compared to that of GPU device memories. Our work, Smart-Infinity, addresses the storage bandwidth bottleneck of storage-offloaded LLM training using near-storage processing devices on a real system. The main component of Smart-Infinity is SmartUpdate, which performs parameter updates on custom near-storage accelerators. We identify that moving parameter updates to the storage side removes most of the storage traffic. In addition, we propose an efficient data transfer handler structure to address the system integration issues for Smart-Infinity. The handler allows overlapping data transfers with fixed memory consumption by reusing the device buffer. Lastly, we propose accelerator-assisted gradient compression/decompression to enhance the scalability of Smart-Infinity. When scaling to multiple near-storage processing devices, the write traffic on the shared channel becomes the bottleneck. To alleviate this, we compress the gradients on the GPU and decompress them on the accelerators. It provides further acceleration from reduced traffic. As a result, Smart-Infinity achieves a significant speedup compared to the baseline. Notably, SmartInfinity is a ready-to-use approach that is fully integrated into PyTorch on a real system. The implementation of Smart-Infinity is available at https://***/AIS-SNU/smart-infinity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Quantifying the Aggregate Flexibility of Plug-In Electric Vehicle Populations

引用

IEEE Transactions on Smart Grid 2024年 1-1页

作者： Taha, Feras Al Vincent, Tyrone Bitar, Eilyan School of Electrical and Computer Engineering Cornell University Ithaca NY USA Department of Electrical Engineering and Computer Science Colorado School of Mines Golden CO USA

Plug-in electric vehicles (EVs) are widely recognized as being highly flexible electric loads that can be pooled and controlled via aggregators to provide low-cost energy and ancillary services to wholesale electricity markets. To participate in these markets, an aggregator must encode the aggregate flexibility of the population of EVs under their command as a single polytope that is compliant with existing market rules. To this end, we investigate the problem of characterizing the aggregate flexibility set of a heterogeneous population of EVs whose individual flexibility sets are given as convex polytopes in half-space representation. As the exact computation of the aggregate flexibility set—the Minkowski sum of the individual flexibility sets—is known to be intractable, we study the problem of computing maximum-volume inner approximations to the aggregate flexibility set by optimizing over affine transformations of a given convex polytope in half-space representation. We show how to conservatively approximate these set containment problems as linear programs that scale polynomially with the number and dimension of the individual flexibility sets. The inner approximation methods provided in this paper generalize and improve upon existing methods from the literature. We illustrate the improvement in approximation accuracy and performance achievable by our methods with numerical experiments. IEEE

关键词： Aggregates

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：