检索结果-内蒙古大学图书馆

IEEE Conference on Wireless communications and Networking

作者： Lingyun Zhou Wenqiang Pu Ming-yi You Rongqing Zhang Qingjiang Shi School of Software Engineering Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

In this paper, we consider the problem of cooperative sensing via a system of multi-unmanned aerial vehicles (UAVs), where each UAV is equipped with a directional antenna to cooperatively perform detection tasks for several targets of interest. To measure the perception ability of the system, we choose the detection probability as the metric, aiming to maximize the sum detection probability of targets by jointly optimizing UAVs’ deployment and directional antenna orientations. To tackle the inherent nonconvexity of the formulated problem, we first decompose it into two sub-problems, i.e., a slave problem for optimizing the antenna orientations with a given UAVs’ deployment, and a master problem for optimizing the UAVs’ deployment. By virtue of the slave problem structure, an efficient block coordinate descent (BCD) algorithm is developed. Meanwhile, to deal with the lack of the closed expression of the sum detection probability with respect to the UAVs’ deployment, we further develop an iterative algorithm to acquire an efficient solution with the aid of Gibbs Sampling (GS) approach. Extensive simulations demonstrate the efficacy of the proposed algorithm.

关键词： Antenna measurements Directional antennas Autonomous aerial vehicles Sensors Iterative methods Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

An Improved Unet Algorithm for the Processing of Magnetic Resonance Imaging (MRI) Images

An Improved Unet Algorithm for the Processing of Magnetic Re...

引用

Computer Information Science and Application technology (CISAT), International Conference on

作者： Lipin Li Yiyu Wu Zhao’En Yan Wei Tian Yixuan Wang Yanni Hui Shanxi Key Laboratory of Measurement and Control Technology for Oiland Gas Wells Xi’an Shiyou University Xi’an China PetroChina Changqing Oilfield Company National Engineering Laboratory for exploration and development of low permeability oil and gas fields Oil and Gas Technology Research Institute Xi’an China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

A machine learning algorithm has been proposed to address the issues of low image resolution, long sampling times, and high costs in MRI. It processes under-sampled MRI K-space data, enabling the reconstruction of high-quality images while significantly reducing sampling time and costs. This paper utilizes a Unet fully convolutional neural network for feature extraction and fusion of K-space data, incorporating an attention module to highlight important image features and suppress irrelevant information. The total variation minimization algorithm is used for the preliminary reconstruction of under-sampled data. High-quality images are then input into a Unet network with a gated attention module for training, achieving high-quality reconstruction of under-sampled data. Experimental results prove that the proposed image reconstruction algorithm outperforms the conventional convolutional neural network Unet, significantly enhancing image reconstruction performance. It improves the PSNR metric by over 4dB and the SSIM metric by approximately 5% compared to the conventional convolutional neural network Unet.

关键词： measurement Visualization Machine learning algorithms Costs Magnetic resonance imaging Logic gates Minimization Feature extraction Convolutional neural networks Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Robust Two-Dimensional DOA Estimation Approach Based on Convolutional Attention Network

A Robust Two-Dimensional DOA Estimation Approach Based on Co...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Rui Xiao Ming–Yi You Rui Zhou Qingjiang Shi School of Software Engineering Tongji University Shanghai China Science and Technology on Communication Information Security Control Laboratory Jiaxing China Shenzhen Research Institute of Big Data Shenzhen China

The direction of arrival (DOA) estimation of the signal is an important task in radio signal positioning. Various methods have been investigated to cope with the DOA task. However, since the imperfect interference factors are often present in practical antenna arrays, the performance of DOA estimation is often significantly degraded. Besides, few methods deal with the DOA estimation for signals of multiple frequencies. In this paper, we consider the problem of two-dimensional DOA estimation in the presence of imperfect factors, and propose a novel approach where the convolutional attention network is used for DOA estimation. The frequency information is introduced as a token added to the network, which improves the network robustness while taking into account the case of the signal of multiple frequencies. Besides, we extend the mean square error (MSE) to the design of a new loss function for training to improve the accuracy of the model. The advantages of the proposed DOA estimation scheme are demonstrated through numerical experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Cascade control System for Continuous Process Based on control Logix 5571 PLC

Design and Implementation of a Cascade Control System for Co...

引用

communication, Computing and Industry 4.0 (C2I4), International Conference on

作者： Kumaresan K Mohanraj K Ruban Thomas Deepa R Madhumita S Nithishkumar K Electronics and Instrumentation Engineering Bannari Amman Institute of Technology Sathyamangalam India Instrumentation and Control Engineering Sri Sairam Engineering college Chennai India Electronics and communication Engineering Vel Tech Multi Tech Engineering College Chennai India Electronics and Communication Engineering CMR Institute of Technology Bangalore India

ISBN: (数字)9781665474979

ISBN: (纸本)9781665474986

In modern industrial automation, one of the most frequent control systems in process industries is cascade control. If, in addition to the main process variable, additional system variables are measured and given back as secondary process variables, generating subordinate control loops, a cascade control system can be constructed. The integrated cascade control system based on Logix 5571 was developed to resolve the problem of nonlinear and more time delays in chemical process. Steam pressure, steam temperature, air/fuel ratio, drum level, and drum flow are all sensitive to variations in working conditions when considering the primary variables of the continuous chemical process. A temperature process is master control and a steam flow process is slave control have become so integrated. This paper used the velocity form algorithm in PID to optimize the values and design a cascade enhanced proportional integral derivative controller (PIDE) to solve the large time delay in chemical processes. The real-time monitoring, a process parameter actual values and configure I\O tag to Human Machine Interface (HMI) using a factory talk automation software. The logix structure of cascade control loops is especially important for obtaining quick dynamics and proper behavior in all real-world operating modes. In the field of industrial control, which uses PLC Modbus TCP/IP to communicate between one master station and more slave stations.

关键词： Temperature sensors Temperature measurement Delay effects Process control TCPIP control systems Chemical processes

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Jamming Algorithm Based on Multi-UAV Scheduling

A Collaborative Jamming Algorithm Based on Multi-UAV Schedul...

引用

International Conference on communication technology (ICCT)

作者： Yixin Jiang Lingyun Zhou Yijia Tang Ya Tu Chunhong Liu Qingjiang Shi School of Software Engineering Tongji University Shanghai China Science and Technology on Communication Information Security Control Laboratory Jiaxing China Shenzhen Research Institute of Big Data Shenzhen China

In this paper, we consider the problem of multi-unmanned aerial vehicles' (UAVs), scheduling for cooperative jamming, where UAVs equipped with directional antennas perform collaborative jamming tasks against several targets of interest. To ensure effective jamming towards the targets, we formulate it as an non-convex optimization problem, aiming to minimize the communication performance of the targets by jointly optimizing UAVs' deployment and directional antenna orientations. Due to the unique structure of the problem, we derive an equivalent transformation by introducing a set of auxiliary matrices. Subsequently, we propose an efficient iterative algorithm based on the alternating direction method of multi-pliers (ADMM), which decomposes the problem into multiple tractable subproblems solved in closed-form or by gradient projection method. Extensive simulations validate the efficacy of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision

arXiv

引用

arXiv 2024年

作者： Jin, Chengxiang Zhou, Jiajun Xie, Chenxuan Yu, Shanqing Xuan, Qi Yang, Xiaoniu Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology Hangzhou310023 China Binjiang Institute of Artificial Intelligence ZJUT Hangzhou310056 China Institute of Cyberspace Security College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China

he rampant fraudulent activities on Ethereum hinder the healthy development of the blockchain ecosystem, necessitating the reinforcement of regulations. However, multiple imbalances involving account interaction frequencies and interaction types in the Ethereum transaction environment pose significant challenges to data mining-based fraud detection research. To address this, we first propose the concept of meta-interactions to refine interaction behaviors in Ethereum, and based on this, we present a dual self-supervision enhanced Ethereum fraud detection framework, named Meta-IFD. This framework initially introduces a generative self-supervision mechanism to augment the interaction features of accounts, followed by a contrastive self-supervision mechanism to differentiate various behavior patterns, and ultimately characterizes the behavioral representations of accounts and mines potential fraud risks through multi-view interaction feature learning. Extensive experiments on real Ethereum datasets demonstrate the effectiveness and superiority of our framework in detecting common Ethereum fraud behaviors such as Ponzi schemes and phishing scams. Additionally, the generative module can effectively alleviate the interaction distribution imbalance in Ethereum data, while the contrastive module significantly enhances the framework’s ability to distinguish different behavior patterns. The source code will be available in https://***/GISec-Team/Meta-IFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Edge Node Cooperation and Resource Sharing in Mobile Edge Computing

Edge Node Cooperation and Resource Sharing in Mobile Edge Co...

引用

International Conference on Wireless communications and Signal Processing (WCSP)

作者： Anqi Meng Xiaozheng Gao Yuting Huang Zhan Xu Jiadong Shang Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Institute of Remote Sensing Equipment Beijing China

As edge computing undergoes ongoing development propelled by the advancements in Internet of Things and mobile communication technologies, the issue of edge node cooperation and resource sharing needs to be investigated. In this paper, the issue of edge node cooperation and resource sharing is modeled as a two-layer framework. In the lower layer, a heuristic matching algorithm between users and edge nodes is developed, and a resource sharing algorithm among edge nodes in the same coalition is proposed. In the upper layer, a coalition formation algorithm is designed based on the coalition game. Simulation results show that the proposed algorithms reduce the network cost effectively compared with non-cooperative scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizability of Navigation2/ROS2 in Highly Automated and Distributed Multi-Robotic Systems for Industrial Facilities

引用

IFAC-PapersOnLine 2022年第4期55卷 109-114页

作者： Tomas Horelican Central European Institute of Technology Brno University of Technology Brno 612 00 Czech Republic Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno 616 00 Czech Republic

The field of mobile robotics is a rapidly evolving space with a constant stream of new advancements. As the available technology matures and new features get accessible for lower prices, the scope of applicability for autonomous mobile robots naturally expands. Apart from simple home appliances, a particular area that currently attracts a surge of transformative research is that of industrial facilities and intelligent factories. A higher emphasis is gradually being placed on autonomous operations, where mobile robots start being suitable complements to human workers. Such an application, however, requires complex mechanisms to be able to handle even simple tasks, such as transferring cargo from one place to another while navigating a changing environment and avoiding dynamic obstacles. Robust localization and navigation solutions utilizing the most effective algorithms are necessary for such long and continuous operations that require a high degree of reliability and low error rates. Robot Operating System (ROS) is a highly flexible open-source framework enjoying wide adoption over the years. Its next-generation implementation (ROS2), together with the Navigation2 project (created as a successor to the original ROS Navigation Stack ), provide substantial conceptual enhancements with a strong focus on reliability, security, and performance, promising better compatibility with numerous sensor types, higher modularity, and a more controllable deterministic behavior. This paper will guide the reader through necessary steps to deploy the Navigation2 stack onto an existing custom-built ROS2-operating robotic test-bed platform, serving as a concept for future research.

关键词： ROS2 Navigation2 mobile robot smart factory multi-robot system autonomous navigation dynamic environment

来源：评论

学校读者我要写书评

暂无评论

Underwater Electric Dipole Source Localization Based on Hybrid Particle Swarm Optimization-Gravitational Search Algorithm

Underwater Electric Dipole Source Localization Based on Hybr...

引用

IEEE/OES China Ocean Acoustics (COA)

作者： Jiahui Liu Wentie Yang Zuoshuai Wang Jiong Chen Yidong Xu College of Information and Communication Engineering Harbin Engineering University Harbin China Hubei Key Laboratory of Marine Electromagnetic Detection and Control Wuhan Second Ship Design and Research Institute Wuhan China SiEngine Technology Co. Ltd. Wuhan China Yantai Research Institute of Harbin Engineering University Yantai China

ISBN: (数字)9798350340297

ISBN: (纸本)9798350340303

The localization process of the underwater electric dipole source involves solving the global optimal solution of a nonlinear function, which necessitates a multidimensional search and remarkable computational resources. Challenges including slow solution speed and the risk of missing the global optimal solution also exist. To address these challenges, in this study, a global search and localization method based on normalized electric field amplitude, which simultaneously matches and solves the target source position and dipole moment, is proposed. Moreover, the particle swarm optimization (PSO) algorithm is integrated with the gravitational search (GSA) algorithm to propose the improved time-varying inertia-weighted PSO and GSA hybrid optimization algorithm (TVIW-PSO-GSA), enabling rapid optimization and solution of underwater electric dipole source localization. The proposed algorithm exhibits strong convergence capabilities while ensuring local search accuracy. The simulation results reveal that the proposed algorithm achieves faster convergence speed and more accurate estimation performance when compared with traditional optimization algorithms.

关键词： Location awareness Accuracy Simulation Oceans Estimation Search problems Electric fields Particle swarm optimization Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Blind identification of MIMO Space-Time Block Codes Based on Convolutional Neural Network 21

Blind identification of MIMO Space-Time Block Codes Based on...

引用

Proceedings of the 7th International Conference on communication and Information Processing

作者： Conglin Pan Si Chen Huijie Zhu Wei Wu Jiachuan Qian Lijun Wang Science and Technology on Communication Information Security Control Laboratory No.36 Research Institute of CETC China and School of Electronic and Optical Engineering Nanjing University of Science and Technology China Science and Technology on Communication Information Security Control Laboratory No.36 Research Institute of CETC China

ISBN: (纸本)9781450385190

Aiming at the blind identification of space-time block codes (STBC) in multiple input multiple output (MIMO) system, this paper proposes a new convolutional neural network (CNN-N) to realize the blind identification. Compared to traditional algorithms using statistical features of received signal, CNN-N can reduce the computation with a higher correct identification rate. Consist of multiple layers with special functions, CNN-N has good generalization ability in complex MIMO channels. The network in this paper can recognize 6 STBC codes include spatial multiplexing signal (SM) and some OSTBC codes. The simulation result shows that this new convolutional neural network can finish STBC identification with a high correct rate even in low SNR by consuming moderate amounts of time.

关键词： Generalization Ability Convolutional Neural Network Blind Identification STBC MIMO

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：