检索结果-内蒙古大学图书馆

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2022

作者： Yang, Di Wang, Lianfa Zhang, Yufeng Jsti Group Nanjing211000 China State Key Laboratory of Safety and Health for In-Service Long Span Bridge Nanjing210012 China Key Lab. of Large Span Bridge Health Inspection Diagnosis Technology Ministry of Communications Nanjing210012 China Ctr. of Data Measured by Struct. Health Monitoring System of Long-Span Bridge in Province of Jiangsu Nanjing210012 China

ISBN: (纸本)9781665409025

This article proposes a health monitoring system platform for cross-river bridges based on big data. The system can realize regionalized bridge operation and maintenance management. The system has functions such as registration modification and deletion of sensor equipment, user registration modification and deletion, real-time display and storage of sensor monitoring data, and evaluation and early warning of bridge structure safety. The sensor is connected to the lower computer through the serial port, analog signal, fiber grating signal, etc. The lower computer converts a variety of signals into digital signals through the single-chip A/D sampling and demodulator, etc., and transmits it to the upper computer through the serial port. The upper computer uses ARMCortex-A9 Run the main program to realize multi-threaded network communication. The system platform is to test the validity of the model, and a variety of model verification methods are used for evaluation to ensure the reliability of the big data analysis method. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

arXiv

引用

arXiv 2023年

作者： Zhang, Hangtao Yao, Zeming Zhang, Leo Yu Hu, Shengshan Chen, Chao Liew, Alan Li, Zhetao School of Cyber Science and Engineering Huazhong University of Science and Technology China Swinburne University of Technology Australia Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China RMIT University Australia Xiangtan University China

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is availab.e to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllab.e attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks. © 2023, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Analysis on unbalanced compensation of star-connected Cascade H-bridge inverter

Analysis on unbalanced compensation of star-connected Cascad...

引用

2021 International Conference on Advances in Optics and Computational Sciences, ICAOCS 2021

作者： Fan, Lingyun Jiang, Yunhao Fang, Sian Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China Wuhan Wuxin Electrical Technology Co. LTD Wuhan China

In unbalanced compensation current situation, it is necessary to take appropriate control strategies to ensure that the star connection cascade static reactive power generator of the dc side voltage balance, the commonly used methods for injecting zero sequence voltage, this paper introduce current unbalance degree to analyze the compensation ability of plant, gives the scope of compensation is derived, by means of simulation demonstrate the validity of the derived, for the star connection series H bridge the application and selection of multilevel SVG has the significance. © Published under licence by IOP Publishing Ltd.

关键词： Electric inverters

来源：评论

学校读者我要写书评

暂无评论

Design of High Voltage Static Reactive Power Generator Based on SPWM Technology 5

Design of High Voltage Static Reactive Power Generator Based...

引用

5th International Conference on New Energy and Future Energy system, NEFES 2020

作者： Fan, L.Y. Jiang, Y.H. Xu, A.F. Zhao, M.Z. Fang, S.A. Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China Wuhan Wuxin Electrical Technology Co. LTD Wuhan430068 China

In order to verify the compensation effect of high voltage static var generator. The system structure of cascaded H-bridge is adopted. The bipolar CPS-SPWM and monopole frequency doubling CPS-SPWM modulation modes are compared by simulation. The instantaneous reactive power detection principle is derived theoretically. The reactive power can be compensated quickly by using monopole frequency doubling CPS-SPWM modulation mode and instantaneous reactive power detection. Using Matlab.Simulink to build 10kv High-voltage SVG, the fast and accurate reactive power compensation is realized under the switching of inductive reactive power and capacitive reactive power. The reliability of the design is verified by simulation. © Published under licence by IOP Publishing Ltd.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

Single-step model predictive control of VSC converter station supplying power to passive network 4

Single-step model predictive control of VSC converter statio...

引用

4th International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2021

作者： Shuang, Lv Yu, Yu Wenkang, Yang Lichao, Xu Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System China State Grid Hubei Electric Power Co.Ltd. Wuhan Electric Power Supply Company Wuhan430068 China

ISBN: (纸本)9781665415965

The AC power quality of the VSC converter station that supplies power to the passive network is in most cases affected by the PI control parameters. In this paper, the model predictive control algorithm without the need to modulate the PI parameters is applied to the VSC converter station control. Firstly, the discrete mathematical model of VSC inverter in αβ coordinate is derived, and the one-step prediction model of AC control voltage is established. Then, the corresponding cost function is constructed to obtain the next time optimal switching state to act on the inverter with the minimum cost function. Finally, a VSC inverter model that supplies power to the passive network is established in MATlab. and a single-step model predictive control strategy is used to do simulation studies on the conditions of linear load, sudden load change, AC voltage reference value change, and model parameter deviation. The results show that the single-step model predictive control method adopted in this paper improves the power quality and the robustness of the control system. © 2021 IEEE.

关键词： Passive networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Generalized Spatial Modulation for STAR-RIS-Aided Vehicular Communication system

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shang, Pingping Han, Xue Hou, Jia Li, Jun Wang, Shucheng Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan430068 China Soochow University School of Electronic and Information Engineering Suzhou215000 China Guangzhou University School of Electronics and Communication Engineering Guangzhou510006 China Wuhan Maritime Communication Research Institute Wuhan430205 China

In this paper, a novel scheme is proposed by introducing the concept of generalized spatial modulation (GSM) and space-time block code (STBC) into simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) for vehicular communication system. To improve spectral efficiency and diversity gain of vehicular system, STAR-RIS array elements are categorized into reflective and transmissive blocks, establishing a mapping relationship with the index bits by using GSM. Subsequently, the modulated symbols are reflected or transmitted based on the predetermined allocation patterns of the blocks. Specifically, to enhance the reliability of signal reception, one of the most renowned STBC schemes, the Alamouti code, is employed at the STAR-RIS surface by receiving and detecting signals across two consecutive time slots. Furthermore, the new design of leveraging STAR-RIS as an access point (AP) is proposed, which plays the role of source in the communication scenario. The mathematical formulas and theoretical average bit error rate (BER) of the scheme are derived based on preceding analysis. According to simulation results, the suggested scheme can outperform conventional schemes in terms of BER performance. In addition, the proposed redesigned scheme further improves the BER performance with better channel conditions, exhibiting excellent performance advantages. © 1975-2011 IEEE.

关键词： Space-time block coding (STBC)

来源：评论

学校读者我要写书评

暂无评论

Effect of O2on Partial Discharge Characteristic of C5F10O/CO2Gas Mixture

Effect of O2on Partial Discharge Characteristic of C5F10O/CO...

引用

2021 International Conference on Advanced Electrical Equipment and Reliable Operation, AEERO 2021

作者： Xia, Yalong Liu, Fan Wei, Zhuo Zhang, Xiaoxing Han, Pu Xiao, Song Li, Zhen Li, Yi Li, Yalong Research Institute State Grid Sichuan Electric Power Cheng Du China Wuhan University School of Electrical Engineering and Automation Wuhan China Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China

ISBN: (纸本)9781665402644

C5F10O, as a new eco-friendly gas insulating medium with great application potential, has attracted much attention from researchers. There are few studies on the partial discharge (PD) characteristics of C5F10O/CO2O2 gas mixture at present. In this paper, we used needle-plate electrodes to simulate the extremely inhomogeneous electric field caused by the defects of metal protrusions in electrical equipment and tested the partial discharge initial voltage (PDIV) of C5F10O/CO2O2 gas mixture. The effect of oxygen on the partial discharge characteristics of C5F10O gas mixture was revealed. We found that C5F10O gas mixture has an obvious polarity effect, and PDIV+ is always larger than PDIV-. The addition of oxygen reduces the PDIV- and PDIV+ of C5F10O gas mixture and the reduction effect on PDIV+ is more obvious. Therefore, the degrading effect of O2 on the partial discharge characteristics of C5F10O gas mixture should be considered and the proportion of oxygen in C5F10O gas mixture should be strictly controlled. © 2021 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Robust Beamforming Based on Covariance Matrix Reconstruction and ADMM

Robust Beamforming Based on Covariance Matrix Reconstruction...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Gong, Pengcheng Wang, Zhaobin Xu, Kaiyan School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan430068 China

ISBN: (纸本)9781665498142

Considering at the issue that the performance of the traditional beamforming algorithm will decrease sharply when the disturbance occurs at the disturbed position and the steering vector mismatch occurs, a new robust beamforming method based on covariance matrix reconstruction and Alternating Direction Method of Multipliers (ADMM) is proposed. Firstly, based on the maximum output power criterion of beamformers, an optimization model is designed to solve the optimal steering vector. Then, the covariance matrix is reconstructed by using the defined interference range to widen the nullity and enhance the anti-motion interference ability of the system. Then, for the quadratic inequality constraint problem of the steering vector, this paper uses ADMM to solve the model iteratively, and obtains the specific solution of the steering vector in each iteration. In addition, the complexity of the algorithm is also analyzed. The experimental results show that, compared with the existing beamforming algorithms, the proposed method Widen the width of zero notch in the interference area, improves the anti-interference performance of the beam, and can well correct the mismatched steering vector. © 2021 IEEE.

关键词： Alternating Direction Method of Multipliers Beamforming Covariance matrix reconstruction Null widening Quadratic constraint

来源：评论

学校读者我要写书评

暂无评论

GradSA: Gradient Sparsification and Accumulation for Communication-Efficient Distributed Deep Learning 15th

GradSA: Gradient Sparsification and Accumulation for Communi...

引用

15th International Conference on Green, Pervasive, and Cloud Computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Mining the value characteristics of one-way car-sharing users based on empirical data 4

Mining the value characteristics of one-way car-sharing user...

引用

2020 4th International Conference on Traffic Engineering and Transportation system, ICTETS 2020

作者： Mi, Xue Wang, Ying-Qi Xie, Dong-Fan Institute of System Science School of Traffic and Transportation Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing China

Car-sharing has been emergent in many cities all over the world due to the environmental sustainability and the diverse service for users. However, the huge investment and the long payback period hinder the development of car-sharing. To this end, this study attempts to mine the value of car-sharing users in terms of empirical data, aiming to provide suggestions for companies to enhance user management. Based on the order data of a car-sharing company, several indicators are defined. On the basis, the users are divided into three categories, namely high-value users, low-value users and potential users. Furthermore, with the proposed indicators and the personal attributes, a prediction model is developed based on random forest method to predict the category of users in advance. The results show that with the observation period of 7 weeks, the long-term value type of a user can be predicted with accuracy of more than 80%. © Published under licence by IOP Publishing Ltd.

关键词： Decision trees

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：