检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2021年第2期6卷 365-379页

作者： Zheng, Wenbin Zhou, Ye Zhang, Tiancong Zhang, Chunyu Zou, Fumin Shi, Yunqing School of Electronic Electrical Engineering and Physics Fujian University of Technology Fuzhou350118 China School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China College of information engineering Xizang Minzu university Xianyang712082 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology 350118 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07103 United States

The advantage of the improved pixel value ordering (IPVO) lies in introduc-ing the positions of two pixels to calculate the difference value between these two pixels, so that each prediction error valued 0 or 1 can be embedded with one bit of data. How-ever, in IPVO, each prediction error at-1 provides no capacity but merely degrade the visual quality. To increase the number of prediction errors valued 1 while decreasing the number of prediction errors valued-1, 16 different block scanning ways are designed to obtain the optimal scanning way generating the large inverse number for each block. Besides, the single-layer embedding strategy of Weng et al.’s method is employed in the proposed method to adaptively select pixels of a block for carrying data. By combining 16 different block scanning ways with the single-layer embedding strategy, the proposed method not only improves the rate-distortion performance but also reduces the computational complexity. Extensive experiments have proved that the performance of our scheme is superior to those of several related schemes. © 2021, Taiwan Ubiquitous Information. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Controlled Out-band Device to Device Communication in Cellular Networks Using Backup Channel in Television White Space

Controlled Out-band Device to Device Communication in Cellul...

引用

International Conference on Emerging Technologies, ICET

作者： Saifur Rahman Syed Luqman Shah Salim Nasar Faraj Mursal Ziaul Haq Abbas Muhammad Usman Muhammad Irfan Fazal Muhammad Electrical Engineering Department College of Engineering Nairan University Nairan Saudi Arabia TeleCoN Research Lab GIK Institute of Engineering Sciences and Technology Topi Pakistan Faculty of Electrical Engineering GIK Institute of Engineering Sciences and Technology Toni Pakistan Department of Electrical Engineering University of Engineering and Technology Mardan Pakistan Department of Computer Science University of Engineering and Technology Mardan Pakistan

In this article, we address the problem of spectrum scarcity in cellular networks (CNs). We propose a backup channel (BuC) for cellular users (CUs) who are in the same macro-cell under the control of a single macro base station (eNB). This BuC operates in the television white space and is detected by the CUs through a cognitive radio energy detection channel sensing technique with a certain probability of success. When the regular channels with the cellular eNB are all occupied, the CUs within the same coverage area of the macro eNB can utilize the sensed BuC to establish a controlled out-band device-to-device link for communication. The BuC bypasses the eNB and reduces the burden on the core of the CN. This leads to improvements in the capacity of the cellular eNB. In the proposed system model, each CU and eNB is equipped with two antennas for communication in two separate bands, i.e., cellular and TV bands. Through simulations, we have observed significant reductions in the blocking probability and probability of call delays.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks

On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural ...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Zhican Zhou Yuetong Fang Xiangpeng Ou William He Xuhao Wu Renjing Xu David Z. Pan Yating Wan Integrated Photonics lab King Abdullah University of Science and Technology Thuwal Makkah Saudi Arabia Function Hub The Hong Kong University of Science and Technology (Guangzhou) China Department of Electrical and Computer Engineering The University of Texas at Austin United States

We present an optical neural network architecture driven by on-chip quantum dot lasers, achieving 3.5 TOPS/mm 2 theoretical computational density. With an optimized model (reducing programming operations by over 75%)... 详细信息

ISBN: (纸本)9798350369311

关键词： Laser theory Quantum dot lasers Neural networks computer architecture Optical computing Programming Optical fiber networks Laser modes System-on-chip High-speed optical techniques

来源：评论

学校读者我要写书评

暂无评论

A Mixed Method Study of Devops Challenges

SSRN

引用

SSRN 2022年

作者： Tanzil, Minaoar Hossain Sarker, Masud Uddin, Gias Iqbal, Anindya Department of Electrical and Software Engineering DISA Lab University of Calgary Canada Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Bangladesh

DevOps practices combine software development and IT (Information Technology) operations. Our continuous needs for rapid but quality software development necessitates the adoption of high-quality DevOps tools. Therefore, it is important to learn the challenges developers face while using the currently available DevOps tools and techniques. We observed a growing number of DevOps related posts in popular online developer forum Stack Overflow (SO). While previous research analyzed SO posts related to build/release engineering, we are aware of no research that specifically focused on DevOps related discussions. In this paper, we first conduct an empirical study by applying topic modeling on 174K SO posts that contain DevOps discussions. We then validate and extend the empirical study findings with a survey of 21 professional DevOps practitioners. We find that: There are 23 DevOps topics grouped into four categories:cloud & CI/CD Tools, Infrastructure as Code, Container & Orchestration, and Quality Assurance. In the followup survey, DevOps developers agree with our findings and mention that it requires hands-on experience before current DevOps tools can be considered easy. The survey participants raised the needs for better documentation and learning resources to learn the rapidly changing DevOps tools and techniques. © 2022, The Authors. All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

OSM2Net: A Robust Road Network Extraction Framework from Noisy Indoor Parking OpenStreetMap

引用

IEEE Internet of Things Journal 2025年

作者： Cao, Yu Guo, Xiansheng Boateng, Gordon Owusu Ansari, Nirwan Si, Haonan Qian, Bocheng Liu, Xinhao Xia, Huang Liu, Yinong University of Electronic Science and Technology of China Department of Electronic Engineering Chengdu611731 China Xi'an Jiaotong-Liverpool University Department of Communications and Networking Suzhou215123 China New Jersey Institute of Technology Advanced Networking Lab Department of Electrical and Computer Engineering NewarkNJ07102 United States

Intelligent Transportation Systems (ITS) rely on high-precision road networks, which are particularly scarce in indoor parking. Existing methods depend on expensive hardware (e.g., LiDAR) or manual mapping, both of which are costly and inefficient. The rise of the Internet of Things (IoT) has enabled large-scale data collection and connectivity, offering new opportunities for automated road network extraction. OpenStreetMap (OSM), as a crowdsourced IoT-driven platform, provides multi-layer geospatial data, including the Road Network Layer (RNL), Lane Boundary Layer (LBL), and Turn Sign Layer (TSL). However, OSM data often suffers from incompleteness and noisy connectivity, affecting the continuity and accuracy of road networks. This paper introduces OSM2Net, a novel framework designed to extract road networks from individual layers and leverage multi-layer data to construct directed road networks. Specifically, OSM2Net rasterizes noisy OSM data into bitmaps for image processing and multi-layer fusion. By leveraging the topology relationship between lane boundaries and road networks, a Lane-Road Map Generator (LRMG) creates a simulated dataset for training. Then, utilizing the simulated dataset, a Lane2Net model is designed to extract road networks from sparse lane boundary images. The framework then vectorizes bitmaps into a lightweight, undirected road network and refines it into a directed network by extracting and matching turn sign information. Experimental results show that Lane2Net achieves Intersection over Union (IoU) of 93% and 92% using simulated and real-world datasets, respectively. Extensive experiments on real-world datasets confirm that OSM2Net delivers robust completeness and high-quality road network extraction. © 2014 IEEE.

关键词： Advanced public transportation systems

来源：评论

学校读者我要写书评

暂无评论

What improves the generalization of graph transformers? a theoretical dive into the self-attention and positional encoding 24

What improves the generalization of graph transformers? a th...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hongkang Li Meng Wang Tengfei Ma Sijia Liu Zaixi Zhang Pin-Yu Chen Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute Troy NY Department of Biomedical Informatics Stony Brook University Stony Brook NY Department of Computer Science and Engineering Michigan State University East Lansing MI and MIT-IBM Watson AI Lab IBM Research MA Department of Computer Science and Engineering University of Science and Technology of China Hefei Anhui China IBM Thomas J. Watson Research Center Yorktown Heights NY

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Byzantine Robust Aggregation in Federated Distillation with Adversaries

Byzantine Robust Aggregation in Federated Distillation with ...

引用

International Conference on Distributed Computing Systems

作者： Wenrui Li Hanlin Gu Sheng Wan Zhirong Luan Wei Xi Lixin Fan Qiang Yang Badong Chen Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China WeBank AI Lab Shenzhen China Department of Computer Science Hong Kong University of Science and Technology Hong Kong China School of Electrical Engineering Xi'an University of Technology Xi'an China Department of Computer Science Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Federated learning empowers privacy-preserving, multi-party secure model training without the necessity of sharing raw data. In recent years, knowledge distillation has emerged as a promising solution to address the significant challenge of model heterogeneity within federated learning. However, current research often overlooks the potential threats posed by Byzantine attacks, which can significantly compromise the security of federated distillation. Previous work on Byzantine attacks has been primarily focused on manipulating local gradients to compromise global model, lacking attacks on logits in knowledge distillation scenarios. In this paper, we introduce two innovative attacks, shedding light on the inherent risks in federated distillation. The proposed attacks include a top-k attack, which perturbs the top k values of logits in each column, and an impersonation attack, which emulates knowledge significantly deviating from the norm. To counter such attacks, we propose a robust aggregation strategy-FedTGD (Federated Top Guard Distillation), designed to ensure robust distillation with heterogeneous models. Specifically, FedTGD incorporates Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and maximum cosine similarity on top-k values of logits to select benign knowledge. Experimental evaluations conducted on FEMNIST and CIFAR100 datasets, considering scenarios for both IID and Non-IID, reveal that top-k attack results in a substantial 27.16% accuracy reduction for FedMD. In contrast, our aggregation method shows a marginal 0.7% accuracy decrease under top-k attacks, outperforming state-of-the-art baselines.

关键词： Training Accuracy Federated learning Computational modeling Noise Impersonation attacks Data models

来源：评论

学校读者我要写书评

暂无评论

Learning Hand Gestures using Synergies in a Humanoid Robot

Learning Hand Gestures using Synergies in a Humanoid Robot

引用

IEEE International Conference on Robotics and Biomimetics

作者： Parthan Olikkal Dingyi Pei Bharat Kashyap Karri Ashwin Satyanarayana Nayan M. Kakoty Ramana Vinjamuri Vinjamuri Lab in the Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD USA City Tech at CUNY Tezpur University Assam India

Hand gestures are a natural way of communication and integrating them into robots could allow for more efficient human-robot collaboration. In recent years, researchers and roboticists have attempted to replicate human hand motor control using the concept of synergies. In this paper, we present a new approach to obtaining kinematic synergies from hand gestures using a single RGB camera. We capture real-time hand gestures using the MediaPipe framework and convert them to joint angular velocities. We then use dimensionality reduction to obtain kinematic synergies from the joint angular velocities. These synergies can be used to reconstruct new hand gestures. We translate these reconstructed hand movement patterns into a humanoid robot, Mitra. Our results show that it is possible to control most of the joints of the robot for performing hand gestures using only a few synergies. This is more efficient than other contemporary methods. Furthermore, robots and prosthetics that use synergy models could enable near-natural human-robot collaboration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large sequence models for sequential decision-making:a survey

引用

Frontiers of computer science 2023年第6期17卷 25-42页

作者： Muning WEN Runji LIN Hanjing WANG Yaodong YANG Ying WEN Luo MAI Jun WANG Haifeng ZHANG Weinan ZHANG School of Electronics Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200241China Digital Brain Lab Shanghai 201306China Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Institute for Artificial Intelligence Peking UniversityBeijing 100091China School of Informatics The University of EdinburghEdinburgh EH89JUUK Department of Computer Science University College LondonLondon WC1E 6BTUK

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision,e.g.,GPT-3 and Swin *** originally designed for prediction problems,it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems,which are typically beset by long-standing issues involving sample efficiency,credit assignment,and partial *** recent years,sequence models,especially the Transformer,have attracted increasing interest in the RL communities,spawning numerous approaches with notable effectiveness and *** survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with sequence models such as the Transformer,by discussing the connection between sequential decision-making and sequence modeling,and categorizing them based on the way they utilize the ***,this paper puts forth various potential avenues for future research intending to improve the effectiveness of large sequence models for sequential decision-making,encompassing theoretical foundations,network architectures,algorithms,and efficient training systems.

关键词： sequential decision-making sequence modeling the Transformer training system

来源：评论

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: a Case Study 27

Assistive Technical Communication of Montenegrin eServices: ...

引用

27th International Conference on Information Technology, IT 2023

作者： Simon, Aniko Lakovic, Luka Kovacevic, Pavle Kara, Peter A. Ognjanovic, Ivana Sendelj, Ramo Reich, Christoph Roganovic, Milovan Mantas, John Bokor, Laszlo Sigma Technology Budapest1093 Hungary University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece

ISBN: (纸本)9798350397512

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity. © 2023 IEEE.

关键词：

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：