检索结果-内蒙古大学图书馆

3rd International Conference on Internet of Things and Smart City, IoTSC 2023

作者： Yang, Ruolin Yang, Lin Zuo, Zejun Wei, Jing National Engineering Research Center of Geographic Information System China University of Geosciences Wuhan China School of Computer Science China University of Geosciences Wuhan China

ISBN: (纸本)9781510666375

Building pattern informs urban spatial structure understanding and modeling. However, previous studies showed limitations on the identification of building groups which has complex spatial distribution. Specifically, they usually use original spatial or non-spatial characteristics but omit certain complementary among multi-faceted features of buildings. In this paper, we give a novel method based on a multi-view clustering framework, which establishes a centroid distance view and a building attribute view to recognize building patterns accurately. The two views are based on both the spatial structure and non-spatial attributes. The similarity graphs on these views, which are obtained by the Gaussian kernel function, are executed graph diffusion and fusion process to obtain a unified graph. Then, the clustering results are obtained via the Normalized cut algorithm. We conduct experiments to recognize building patterns by four real-world community building footprint datasets of two cities in China: Wuhan and Chengdu. The experimental results show that our proposed method identifies building groups with grid, grid-like and unstructured patterns more effectively. Our method performs better in seven evaluation indexes compared with the baseline model. © 2023 SPIE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication 38

LibAMM: Empirical Insights into Approximate Computing for Ac...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zeng, Xianzhi Jiang, Wenchao Zhang, Shuhao National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Nanyang Technological University Singapore Singapore University of Technology and Design Singapore

Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, parallel and distributed computing, hardware acceleration, and approximate computing techniques, namely AMM algorithms. Amidst growing concerns over the resource demands of large language models (LLMs), AMM has garnered renewed focus. However, understanding the nuances that govern AMM's effectiveness remains incomplete. This study delves into AMM by examining algorithmic strategies, operational specifics, dataset characteristics, and their application in real-world tasks. Through comprehensive testing across diverse datasets and scenarios, we analyze how these factors affect AMM's performance, uncovering that the selection of AMM approaches significantly influences the balance between efficiency and accuracy, with factors like memory access playing a pivotal role. Additionally, dataset attributes are shown to be vital for the success of AMM in applications. Our results advocate for tailored algorithmic approaches and careful strategy selection to enhance AMM's effectiveness. To aid in the practical application and ongoing research of AMM, we introduce LibAMM -a toolkit offering a wide range of AMM algorithms, benchmarks, and tools for experiment management. LibAMM aims to facilitate research and application in AMM, guiding future developments towards more adaptive and context-aware computational solutions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mixed Hierarchical Networks for Deep Entity Matching

引用

Journal of computer science & Technology 2021年第4期36卷 822-838页

作者： Chen-Chen Sun De-Rong Shen Engineering Research Center of Learning-Based Intelligent System(Ministry of Education)Tianjin University of Technology Tianjin 300384China School of Computer Science and Engineering Tianjin University of TechnologyTianjin 300384China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China

Entity matching is a fundamental problem of data *** groups records according to underlying real-world *** is a growing trend of entity matching via deep learning *** design mixed hierarchical deep neural networks(MHN)for entity matching,exploiting semantics from different abstract levels in the record internal hierarchy.A family of attention mechanisms is utilized in different periods of entity ***-attention focuses on internal dependency,inter-attention targets at alignments,and multi-perspective weight attention is devoted to importance ***,hybrid soft token alignment is proposed to address corrupted *** order is for the first time considered in deep entity ***,to reduce utilization of labeled training data,we propose an adversarial domain adaption approach(DA-MHN)to transfer matching knowledge between different entity matching tasks by maximizing classifier ***,we conduct comprehensive experimental evaluations on 10 datasets(seven for MHN and three for DA-MHN),which illustrate our two proposed approaches1 *** apparently outperforms previous studies in accuracy,and also each component of MHN is ***-MHN greatly surpasses existing studies in transferability.

关键词： entity matching attention mechanism mixed hierarchical neural network(MHN) domain adaption data integration

来源：评论

学校读者我要写书评

暂无评论

BuildingMap-GAN: A Map Translator From Road to Building Footprint 3

BuildingMap-GAN: A Map Translator From Road to Building Foot...

引用

3rd International Conference on Internet of Things and Smart City, IoTSC 2023

作者： Wei, Jing Zuo, Zejun Yang, Lin Yang, Ruolin School of Computer Science China University of Geosciences Wuhan China National Engineering Research Center of Geographic Information System China University of Geosciences Wuhan China

ISBN: (纸本)9781510666375

Building footprint information is crucial for urban-related applications. Due to the rapid growth of the number and types of community-level buildings, the completeness and coverage of building footprint data at the community level are lagging. Efficiently and accurately generating community-level building footprint maps for the update of community electronic maps, post-disaster assessment, navigation services, etc. is an urgent and challenging task. To fill the data gaps of community-level building footprint with high accuracy, we design a building map translator named BuildingMap-GAN that is configured with a novel generator: MACU-Net. It has multi-scale connections with channel attention and asymmetric convolution blocks (ACB), which are used for fully capturing the spatial structure information of buildings and roads. An experiment is conducted on real-world community dataset in Wuhan, China, in which the street network data of 700 communities were used for training and the street network data of 42 communities were used for verification. Compared with the two baseline models, F1 scores are improved by 6.7% and 4.5%, respectively, and IoU values increase by 5.0% and 3.2%, respectively. Our model can generate refined building footprint data with higher precision and is closer to the real building distribution. © 2023 SPIE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Routing Performance Through Trajectory Planning With DRL in UAV-Aided VANETs

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 517-533页

作者： Chen, Jingxuan Huang, Dianrun Wang, Yijie Yu, Ziping Zhao, Zhongliang Cao, Xianbin Liu, Yang Quek, Tony Q. S. Oliver Wu, Dapeng Beihang University School of Electronic and Information Engineering Beijing100191 China State Key Laboratory of CNS/ATM Beijing100191 China Nanyang Technological University School of Computer Science and Engineering Nanyang Avenue 639798 Singapore Singapore University of Technology and Design Information System Technology and Design Pillar Somapah Rd 487372 Singapore Yonsei University Yonsei Frontier Laboratory Seoul03722 Korea Republic of City University of Hong Kong Department of Computer Science Kowloon Hong Kong

Vehicular Ad-hoc Networks (VANETs) have gained significant attention as a key enabler for intelligent transportation systems, facilitating vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Despite their potential, VANETs face critical challenges in maintaining reliable end-to-end connectivity due to their highly dynamic topology and sparse node distribution, particularly in areas with limited infrastructure coverage. Addressing these limitations is crucial for advancing the reliability and scalability of VANETs. To bridge these gaps, this work introduces a heterogeneous UAV-aided VANET framework that leverages uncrewed aerial vehicles (UAVs), also known as autonomous aerial vehicles, to enhance data transmission. The key contributions of this paper include: 1) the design of a novel adaptive dual-model routing (ADMR) protocol that operates in two modes: direct vehicle clustering for intra-cluster communication and UAV/RSU-assisted routing for inter-cluster communication;2) the development of a modified density-based clustering algorithm (MDBSCAN) for dynamic vehicle node clustering;and 3) an improved UAV trajectory planning method based on a multi-agent soft actor-critic (MASAC) deep reinforcement learning algorithm, which optimizes network reachability. Simulation results reveal that the UAV trajectory optimization method achieves higher network reachability ratios compared to existing approaches. Also, the proposed ADMR protocol improves the packet delivery ratio (PDR) while maintaining low end-to-end latency. These findings demonstrate the potential to enhance VANET performance, while also providing valuable insights for the development of intelligent transportation systems and related fields. © 2025 The Authors.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Coarse to Fine Detection Method for Prohibited Object in X-ray Images Based on Progressive Transformer Decoder 24

A Coarse to Fine Detection Method for Prohibited Object in X...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ma, Chunjie Du, Lina Gao, Zan Zhuo, Li Wang, Meng Shandong Jinan China School of Computer Science and Technology Shandong Jianzhu University Shandong Jinan China Faculty of Information Technology Beijing University Of Technology Beijing China School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9798400706868

Currently, Transformer-based prohibited object detection methods in X-ray images appear constantly, but there are still some shortcomings such as poor performance and high computational complexity for prohibited object detection with heavily occlusion. Therefore, a coarse to fine detection method for prohibited object in X-ray images based on progressive Transformer decoder is proposed in this paper. Firstly, a coarse to fine framework is proposed, which includes two stages: coarse detection and fine detection. Through adaptive inference in stages, the computational efficiency of the model is effectively improved. Then, a position and class object queries method is proposed, which improves the convergence speed and detection accuracy of the model by fusing the position and class information of prohibited object with object queries. Finally, a progressive Transformer decoder is proposed, which distinguishes high and low score queries by decreasing confidence thresholds, so that high-score queries are not affected by low-score queries in the decoding stage, and the model can focus more on decoding low-score queries, which usually correspond to prohibited object with severe occlusion. The experimental results on three public benchmark datasets (SIXray, OPIXray, HiXray) demonstrate that compared with the baseline DETR, the proposed method achieves the state-of-the-art detection accuracy with a 21.6% reduction in model computational complexity. Especially for prohibited objects with heavily occlusion, accurate detection can be carried out. © 2024 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Honeypot Comparison of Attack Detection and Mitigation of SSH Attack 3

Honeypot Comparison of Attack Detection and Mitigation of SS...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Ali, Wasif Sajid, Ahthasham Ghodke, Tanvi Ajit Malik, Rida Malik, Neeru Kaushik, Keshav Riphah Institute of System Engineering Riphah International University Department of Cyber Security Islamabad Pakistan Pimpri Chinchwad University Department of Computer Science and Engineering Maharashtra India School of Engineering & Technology Pimpri Chinchwad University Maharashtra Pune India Amity School of Engineering and Technology Amity University Mohali India

ISBN: (纸本)9798331518592

This research study addresses the importance of honeypots at multiple levels, which includes but not limited to placement in network or group of networks working alongside in an organization. This paper talks about the usage of multiple honeypots working alongside to log useful data for the mitigation of ongoing bot or actual attack this approach helps the organization better understand the threat they are dealing and the techniques which they can use to overcome the gap of the unseen security risks. The comparison will shed better light to the working and attack patterns of the ongoing attacks, gaining more confidence on using the honeypot for better protection. This allows strategic, optimized and critical insight to the evolving attack patterns. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6369-6384页

作者： Wang, Xiuhua Wang, Shuai Li, Yiwei Fan, Fengrui Li, Shikang Lin, Xiaodong Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients' private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients' privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Quantile-Based SUM/MAX Operating Method for Statistical Timing Analysis 16

A Quantile-Based SUM/MAX Operating Method for Statistical Ti...

引用

16th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2022

作者： Jin, Leilei Xu, Jiajie Fu, Wenjie Shi, Xiao Southeast University School of Electronic Science & Engineering The National Asic System Engineering Technology Research Center Nanjing210096 China Southeast University School of Electronic Science & Engineering School of Computer Science and Engineering Nanjing210096 China

ISBN: (数字)9781665469067

ISBN: (纸本)9781665469067

Instead of expressing the delay distribution shape with complicated forms, we propose a quantile-based statistical SUM/MAX operating method by converting the distribution to several quantiles. Based on the numerical convolution, the SUM/MAX operations are converted to DNN with two groups of quantiles. The configuration of DNN models is discussed in this work, such as the hidden layer number and the transfer function. With 28 nm technology, the average errors of the DNN models for estimating the μ+3σ arrival time are less than 3% compared to the Monte Carlo simulations. The proposed method is more efficient than the NN-SSTA which needs to fit the shape of the whole distribution. © 2022 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

system Modelling, Numerical Simulations and Experimental Validation of High Capacity FSO Data Transmission in DWDM Communication Employing Optical Frequency Comb 24

System Modelling, Numerical Simulations and Experimental Val...

引用

24th IEEE International Conference on Numerical Simulation of Optoelectronic Devices, NUSOD 2024

作者： Rajaram, Narmada Avazpour, Mahrokh Barry, Liam Hinzer, Karin Hall, Trevor Atieh, Ahmad School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada School of Electronic Engineering Dublin City University Radio and Optics Communications Laboratory GlasnevinDublin 9 Ireland University of Ottawa Optiwave System Inc 7 Capella Court Ottawa Canada

ISBN: (纸本)9798350390537

Dense Wavelength Division Multiplexing (DWDM) optical technology allows transmission of many wavelengths in a single optical channel. In this paper, system modelling and numerical simulations are demonstrated for high-capacity data transmission using an Optical Frequency Comb (OFC). An OFC is generated using fiber loop modulation technique and simulations are carried out using commercially available simulation software -Optisystem. An OFC with excellent flatness is obtained, which is essential for noise and error reduction. Each comb line is modulated with data and the DWDM multiplexed signal is transmitted over a free-space optical (FSO) channel. The system performance is assessed in terms of Bit Error Rate (BER) and range of the FSO channel. Our experimental results demonstrate that our system aligns well with simulation and can generate an OFC confirming the potential of our approach for applications such as optical communication networks. © 2024 IEEE.

关键词： Bit error rate

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：