检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Chengming Geng, Tong Guo, Anqi Tian, Jiannan Herbordt, Martin Li, Ang Tao, Dingwen School of Electrical Engineering and Computer Science Washington State University PullmanWA United States Mathematics and Computer Science Division Pacific Northwest National Laboratory RichlandWA United States Department of Electrical and Computer Engineering Boston University BostonMA United States Department of Electrical and Computer Engineering University of Rochester RochesterNY United States School of Informatics Computing and Engineering Indiana University BloomingtonIN United States

Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs. Compared with other Machine Learning (ML) modalities, the acceleration of Graph Neural Networks (GNNs) is more challenging due to the irregularity and heterogeneity derived from graph typologies. Existing efforts, however, have focused mainly on handling graphs’ irregularity and have not studied their heterogeneity. To this end we propose H-GCN, a PL (Programmable Logic) and AIE (AI Engine) based hybrid accelerator that leverages the emerging heterogeneity of Xilinx Versal Adaptive Compute Acceleration Platforms (ACAPs) to achieve high-performance GNN inference. In particular, H-GCN partitions each graph into three subgraphs based on its inherent heterogeneity, and processes them using PL and AIE, respectively. To further improve performance, we explore the sparsity support of AIE and develop an efficient density-aware method to automatically map tiles of sparse matrix-matrix multiplication (SpMM) onto the systolic tensor array. Compared with state-of-the-art GCN accelerators, H-GCN achieves, on average, speedups of 1.1∼2.3×. © 2022, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Visible Light Positioning Based on a Single Luminaire: A Novel Visual Odometry Assisted Algorithm

Visible Light Positioning Based on a Single Luminaire: A Nov...

引用

IEEE International Conference on Communications (ICC)

作者： Zhiyu Zhu Yang Yang Mingzhe Chen Caili Guo Yipeng Bai Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

Visible light positioning (VLP) is a promising positioning technique, which, however, typically requires multiple luminaires to achieve accurate positioning. This paper proposes a novel visual odometry (VO) assisted visible light positioning algorithm (VO-VLP) in achieving positioning with only a single luminaire. In the considered model, a user equipped with a camera jointly uses geometric features in the captured images and coordinates information obtained via visible light communication (VLC) for positioning. The proposed VLP algorithm does not rely on any extra inertial measurement unit and relaxes the tilted angle limitation at the user. In particular, VO-VLP first uses the circle feature of a luminaire to obtain dual normal vectors of the luminaire. Then, the basic principle of VO is used to eliminate the wrong normal vector by exploiting the geometric features in two consecutive images captured when the user moves. Finally, the pose and location of the user are obtained by using an artificially marked point on the luminaire's contour. VO-VLP can achieve accurate positioning with only a single luminaire and a camera. Simulation results show that the proposed indoor positioning algorithm can achieve a 97th-percentile positioning accuracy of around 10 cm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STAR-RIS Assisted Covert Wireless Communications with Randomly Distributed Blockages

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4690-4705页

作者： Li, Xingwang Zhao, Jingwei Chen, Gaojie Hao, Wanming Da Costa, Daniel Benevides Nallanathan, Arumugam Shin, Hyundong Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454099 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Shenzhen518107 China 5GIC 6GIC University of Surrey United Kingdom Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Queen Mary University of London School of Electronic Engineering and Computer Science London United Kingdom Kyung Hee University Department of Electronic Engineering Yongin-si17104 Korea Republic of Kyung Hee University Department of Electronics and Information Convergence Engineering Korea Republic of Nanyang Technological University School of Electrical and Electronics Engineering 639798 Singapore

As one of the promising technologies, reconfigurable intelligent surface (RIS) and simultaneous transmitting and reflecting RIS (STAR-RIS) have attracted great interest. However, the existing RISs offer broadband tuning capability without filtering function due to the absence of radio frequency (RF) units, which easily leads to the unexpected tuning of the RIS undesired signals, especially in large-scale deployments. For the target network, it is difficult to obtain the parameter settings of RISs to serve other networks, which causes the unpredictability of the wireless environment. In this paper, we consider the covert communication in a STAR-RIS assisted random wireless network with randomly distributed blockages. We investigate the impact of STAR-RIS large-scale deployment on covert communication and leverage its inherent unpredictability for improving the covertness. We derive the average detection error probability for warden within the random wireless networks. Furthermore, we optimize the passive beamforming of STAR-RIS to maximize the covert communication rate, considering both direct and indirect line-of-sight (LoS) links. To address this, we employ an alternating optimization (AO) algorithm based on the semi-definite programming (SDP) method. Finally, numerical results demonstrate significant enhancements and increase covert capability achieved through the large-scale deployment of STAR-RIS. 2002-2012 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

A transactional-behavior-based hierarchical gated network for credit card fraud detection

引用

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Xie, Yu Zhou, MengChu Liu, Guanjun Wei, Lifei Zhu, Honghao De Meo, Pasquale College of Information Engineering Shanghai Maritime University Shanghai201306 China School of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou310018 China Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science Tongji University Shanghai201804 China College of Computer Science and Information Engineering Bengbu University Bengbu233030 China Department of Ancient and Modern Civilizations University of Messina Messina98166 Italy

The task of detecting fraud in credit card transactions is crucial to ensure the security and stability of a financial system, as well as to enforce customer confidence in digital payment systems. Historically, credit card companies have used rule-based approaches to detect fraudulent transactions, but these have proven inadequate due to the complexity of fraud strategies and have been replaced by much more powerful solutions based on machine learning or deep learning algorithms. Despite significant progress, the current approaches to fraud detection suffer from a number of limitations: for example, it is unclear whether some transaction features are more effective than others in discriminating fraudulent transactions, and they often neglect possible correlations among transactions, even though they could reveal illicit behaviour. In this paper, we propose a novel credit card fraud detection (CCFD) method based on a transaction behaviour-based hierarchical gated network. First, we introduce a feature-oriented extraction module capable of identifying key features from original transactions, and such analysis is effective in revealing the behavioural characteristics of fraudsters. Second, we design a transaction-oriented extraction module capable of capturing the correlation between users' historical and current transactional behaviour. Such information is crucial for revealing users' sequential behaviour patterns. Our approach, called transactional-behaviour-based hierarchical gated network model (TbHGN), extracts two types of new transactional features, which are then combined in a feature interaction module to learn the final transactional representations used for CCFD. We have conducted extensive experiments on a real-world credit card transaction dataset with an increase in average F1 between 1.42% and 6.53% and an improvement in average AUC between 0.63% and 2.78% over the state of the art. © 2025 Institute of electrical and Electronics Engineers Inc.. All right

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of a Coupled SIS Bi-Virus Model

arXiv

引用

arXiv 2022年

作者： Gracy, Sebin Paré, Philip E. Liu, Ji Sandberg, Henrik Beck, Carolyn L. Johansson, Karl Henrik Başar, Tamer Department of Electrical Engineering and Computer Science South Dakota School of Mines and Technology SD United States School of Electrical and Computer Engineering Purdue University IN United States Department of Electrical and Computer Engineering Stony Brook University United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden Coordinated Science Laboratory University of Illinois at Urbana-Champaign United States

The paper deals with the setting where two viruses (say virus 1 and virus 2) coexist in a population, and they are not necessarily mutually exclusive, in the sense that infection due to one virus does not preclude the possibility of simultaneous infection due to the other. We develop a coupled bi-virus susceptible-infected-susceptible (SIS) model from a 4n-state Markov process, where n is the number of agents (i.e., individuals or subpopulation) in the population. We identify a sufficient condition for both viruses to eventually die out, and a sufficient condition for the existence, uniqueness and asymptotic stability of the endemic equilibrium of each virus. We establish a sufficient condition and multiple necessary conditions for local exponential convergence to the boundary equilibrium (i.e., one virus persists, the other one dies out) of each virus. Under mild assumptions on the healing rate, we show that there cannot exist a coexisting equilibrium where for each node there is a nonzero fraction infected only by virus 1;a nonzero fraction infected only by virus 2;but no fraction that is infected by both viruses 1 and 2. Likewise, assuming that healing rates are strictly positive, a coexisting equilibrium where for each node there is a nonzero fraction infected by both viruses 1 and 2, but no fraction is infected only by virus 1 (resp. virus 2) does not exist. Further, we provide a necessary condition for the existence of certain other kinds of coexisting equilibria. We show that, unlike the competitive bivirus model, the coupled bivirus model is not monotone. Finally, we illustrate our theoretical findings using an extensive set of simulations. © 2022, CC0.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Multi-residual 2D network integrating spatial correlation for whole heart segmentation

引用

computers in Biology and Medicine 2024年 172卷 108261-108261页

作者： Huang, Yan Yang, Jinzhu Sun, Qi Yuan, Yuliang Li, Honghe Hou, Yang Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang China School of Computer Science and Engineering Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang China Department of Radiology Shengjing Hospital of China Medical University Liaoning Shenyang China

Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder–decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://***/nancy1984yan/MultiResNet-SC. © 2024 Elsevier Ltd

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Addressing Non-stationarity with Stochastic Trend in the Context of Limited Time Series Data: An Experimental Survey

Research Square

引用

Research Square 2025年

作者： Batoure Bamana, Apollinaire Sokdou Bila Lamou, Yannick Fotsa-Mbogne, David Jaures Shafiee Kamalabad, Mahdi Department of Computer Engineering University Institute of Technology The University of Ngaoundere Cameroon Department of Robotic and Industrial Computing School of Chemical Engineering and Mineral Industries The University of Ngaoundere Cameroon Department of Mathematics and Computer Science Faculty of Science The University of Ngaoundere Cameroon Laboratory of Mathematics Computer Science and Applications Department of Mathematics and Computer Science National Higher School of Agro-Industrial Sciences The University of Ngaoundéré Cameroon Laboratory of Mathematics and Computer Science Department of Mathematics Statistics and Computer Science Faculty of Science The University of Bertoua Cameroon Department of Methodology and Statistics Faculty of Social and Behavioural Sciences Utrecht University Utrecht Netherlands Centre for Complex Systems Studies Utrecht University Utrecht Netherlands

Stationarity in time series is a key property for practical data analysis, inferences, and predictions particularly in biosciences. Stationarity can be either deterministic or stochastic. If a time series data is not stationary, it can be rendered stationary through detrending or differentiation techniques. Differentiation can be performed in either an integer or fractional form. This paper investigates non-stationarity in time series data, focusing specifically on stochastic trends characterised by a unit root. It hypothesises that fractional differentiation can enhance forecast accuracy for datasets with limited volume. For experiments, 24 series corresponding to weekly Malaria and Typhoid Fever from Adamawa Region (Cameroon) are analysed and forecasted. Each series comprises 156 observations covering January 2021 to December 2023. After collecting, checking and classifying the data, four forecasting models, Auto Regressive Integrated Moving Average (ARIMA), Fractional ARIMA (ARFIMA), Long Short-Term Memory (LSTM), and the proposed Fractional Differencing and LSTM (FD-LSTM), are implemented. The models' performances are evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of determination (R2) metrics, which inform further analysis and recommendations. Results reveal that ARFIMA outperformed the ARIMA by 93% in training and 100% in testing. Similarly, FD-LSTM achieved a 100% improvement over LSTM in training and testing. These findings underscore the value of achieving stationarity through fractional differentiation, enhancing model performance and providing a robust framework for forecasting in datasets with limited observations. © 2025, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

On the potential of lateral BJTs and SiGe HBTs in advanced CMOS technologies

On the potential of lateral BJTs and SiGe HBTs in advanced C...

引用

Pacific Rim Meeting on Electrochemical and Solid State Science 2020, PRiME 200

作者： Suligoj, Tomislav Žilak, Josip Osrečki, Željko Koričić, Marko Micro and Nano Electronics Laboratory Department of Electronics Microelectronics Computer and Intelligent Systems Faculty of Electrical Engineering and Computing University of Zagreb Croatia

ISBN: (纸本)9781607689003

The potential of lateral bipolar transistors, based on Horizontal Current Bipolar Transistor (HCBT), in scaled CMOS technologies are examined by TCAD simulations. Thorough and consistent simulations show that SiGe HCBT can achieve fT/fmax of 358/490 GHz outperforming standard vertical-current HBT with fT/fmax of 348/423 GHz, assuming the same intrinsic transistor doping profile. By optimizing the extrinsic base shape and width, the characteristics of SiGe HCBT can be further improved. SiGe HCBTs in bulk silicon substrates result in better performance comparing to the transistors in SOI substrates. © The Electrochemical Society

关键词： Si-Ge alloys

来源：评论

学校读者我要写书评

暂无评论

A Survey on Indoor Visible Light Positioning systems: Fundamentals, Applications, and Challenges

引用

IEEE Communications Surveys and Tutorials 2024年第3期27卷 1656-1686页

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering and Institute for Data Science and Computing Coral GablesFL33146 United States Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China The University of British Columbia Faculty of Applied Science School of Engineering KelownaBCV1V 1V7 Canada 518172 Hong Kong

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. © 1998-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

IRS Channel Estimation in Cell-free MIMO Network: A Coalition Formation Guided Federated Learning Approach

IRS Channel Estimation in Cell-free MIMO Network: A Coalitio...

引用

IEEE Conference on Wireless Communications and Networking

作者： Haoxuan Liu Nan Qi Xiaojie Li Alexandros A. A. Boulogeorgos Theodoros A. Tsiftsis Ming Xiao Juha Röning Nanjing University of Aeronautics and Astronautics Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Department of Informatics and Telecommunications University of Thessaly Lamia Greece Department of Electrical and Electronic Engineering University of Nottingham Ningbo China Ningbo China School of Electrical Engineering of KTH Royal Institute of Technology Stockholm Sweden Biomimetics and Intelligent Systems Group University of Oulu Finland

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The downlink channel estimation is currently a critical bottleneck for IRS-assisted cell-free multiple input multiple output communication. Conventionally, most studies have employed deep learning methods to estimate the high-dimensional, complex cascaded channels generated by IRS, necessitating data collection from all users for centralized model training, which results in excessively large overheads, and data privacy problems. To tackle this challenge, a federated learning (FL)-based channel estimation framework incorporates coalition formation to guide the formation of FL user groups. We propose a coalition formation-enabled federated learning framework for channel estimation, utilizing a deep reinforcement learning (DRL) approach to intelligently group users into multiple coalitions, thereby improving channel estimation accuracy. Moreover, considering that nodes with similar distances to the base station and similar received signal power have a strong likelihood that they experience similar channel fading, we designed a transfer learning method that incorporates both received reference signal power and distance similarity metrics. The transfer learning technique is designed to accelerate the convergence of DRL-federated learning process. Simulations reveal that the proposed algorithms significantly reduce communication overhead for local users and improve data privacy while maintaining commendable channel estimation accuracy.

关键词： Training Data privacy Accuracy Federated learning Transfer learning Channel estimation Deep reinforcement learning Data models Surface treatment Convergence

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：