检索结果-内蒙古大学图书馆

International Conference on Information science and Technology (ICIST)

作者： Zhiyi Li Yi Zuo Tieshan Li Yang Xiao Navigation College Dalian Maritime University Dalian China School of Automatic Engineering University of Electronic Science Chengdu China Department of Computer Science The University of Alabama Tuscaloosa USA

In recent years, with the rapid development of the marine economy, maritime transportation industry has also steadily strengthened, leading to an increasing number of ships at sea. However, this growth has also raised safety risks for maritime vessels, making accurate and effective maritime vessel recognition technology essential for improving navigational safety. Presently, most target detection algorithms focus solely on improving model accuracy while neglecting the computational and parameter overheads resulting from the complexity of the models. To address this issue, this paper proposes an improved YOLOv5 object detection algorithm, utilizing MobileN et V3 for lightweight enhancements to minimize model size and computational demands. Additionally, to ensure model precision, Hybrid Channel Attention Mechanism (CBAM) is introduced. Experiments were conducted on the Seaships dataset, comparing the proposed improved YOLOv5 algorithm with YOLOv5 and Faster R-CNN algorithms. The experimental results demonstrate that the enhanced YOLOv5 detection network achieves accuracy of 99.1 % and mean average precision of 99.5%. Compared to other algorithms, it exhibits excellent detection performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer Route Recommendation for Metro Systems Based on Multi-source Data Fusion 24

Transfer Route Recommendation for Metro Systems Based on Mul...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Yuan, Tailan Xiong, Wen Yun, Lijun School of Information Science and Technology Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Kunming China

ISBN: (纸本)9798350319934

As the network-structure complexity and the passenger volume continuously grow, how to accurately perform passenger flow guidance is a crucial issue for metro operators. Transfer route recommendation is a core approach for passenger flow guidance. Existing works are limited in obtaining route attributes (such as transfer walking time and waiting time, etc.). Furthermore, most of existing methods may not work well in the scenario of sudden passenger flow, because of their limited capability to accurately measure the real-time crowding. To address these issues, a data fusion based transfer route recommendation method (DFTRR) is proposed. Specifically, we first propose a spatio-temporal diversity-based method (STD) to measure the trajectory similarity. Based on that, we fuse two kinds of heterogeneous data, i.e., swiping records of smart cards and Wi-Fi signal records of mobile devices to extract a passenger's complete trip. And then we present the historical median travel time to alleviate the computation issue of route attributes. Meanwhile the mean crowding level is introduced to accurately measure the real-time crowding of routes. Finally, a generalized travel cost based on median travel time, number of transfers and mean crowding level is constructed for transfer route recommendation. The experimental results illustrate that the accuracy of STD algorithm is higher than the baseline 34.92% at maximum;DFTRR can offer the optimal transfer route according to passengers' preferences under sudden passenger flow. © 2022 IEEE.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Reducing the energy consumption required for the disassembly process implemented on an assembly and disassembly line 24

Reducing the energy consumption required for the disassembly...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Marius-Adrian, Paun Elena, Dragomir Otilia Florin, Dragomir Stelian, Iliescu Sergiu Eugenia, Minca Octavian Gabriel, Duca Valentin, Gurgu Ion University 'Politehnica' of Bucharest Department of Automation and Industrial Informatics Bucharest Romania Valahia University of Targoviste Faculty of Electrical Engineering Electronics and Information Technology Targoviste Romania University 'Politehnica ' of Bucharest Faculty of Automatic Control and Computers Bucharest Romania University 'Dunarea de Jos ' of Galati Department of Automation and Electrical Engineering Galati Romania Institute of Multidisciplinary Research for Science and Technology Valahia University of Targoviste Targoviste Romania

ISBN: (纸本)9798350313390

This paper proposes a method to reduce the energy consumption of an industrial disassembly process implemented on a production line by using an energy-efficient secondary disassembly process. In the case of defective products, the flow directs the simple product with priority to be disassembled in workstation (WS) 7. Therefore, all defective products are redirected to WS7. The disassembly of all simple products in WS7 is problematic for two reasons: the power consumption of WS7 is high compared to the other workstations, additionally there is an increased possibility of bottlenecks in the production line due to the high disassembly time. The proposed solution to reduce the possibility of deadlock and reduce power consumption is to redirect the defective products to the flexible cell (FC). Handling robots located in neighboring stations will participate collaboratively in the disassembly process. The control structure ensures that the two robots 'meet' in the boundary plane of WS3 with WS4 and disassemble each component through collaborative tasks. Collaborative control of disassembly is thought of as a solution to the global 'fluidization' of production, removing the bottleneck, from the overall flow, but also as an ingenious solution to reduce energy consumption. © 2023 IEEE.

关键词： Assembly

来源：评论

学校读者我要写书评

暂无评论

Forecasting-Aided Graphical Learning for Robust State Estimation of Distribution System 1

引用

8th Purple Mountain Forum on Smart Grid Protection and control, PMF 2023

作者： Di, Cao Zhao, Junbo Hu, Jiaxiang Huang, Yuehui Huang, Qi Chen, Zhe Hu, Weihao University of Electronic Science and Technology of China Chengdu China Department of Electrical and Computer Engineering University of Connecticut StorrsCT06269 United States State Key Laboratory of Operation and Control of Renewable Energy and Storage Systems China Electric Power Research Institute Beijing China Department of Energy Technology Aalborg University Pontoppidanstraede 111 Aalborg Denmark

ISBN: (数字)9789819992515

ISBN: (纸本)9789819992508

The forecasting of of pseudo-measurements play an important role in distribution system state estimation (DSSE). This paper proposes robust DSSE method based on forecasting-aided graphical learning method. The nodal power consumption models are first built to produce pseudo-measurements based on deep neural network. Then, the pseudo-measurements and real-time measurements are represented as a graph according to the topology of the distribution network, which are further processed by a graph attention network to capture the mapping relationship between the graphical measurements and the state variables based on the error modeling of pseudo-measurements. The robustness against anomalous measurements is achieved through the embedding of structural information of DN. The modeling of pseudo-measurements further enhance its robustness by guiding the formulation of edge weights of the graph neural network. Comparative tests are carried out on a IEEE 119-node system to demonstrate the effectiveness and robustness of the proposed method. © 2024, State Grid Electric Power.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Online Federated Learning with Correlated Noise

Differentially Private Online Federated Learning with Correl...

引用

IEEE Conference on Decision and control

作者： Jiaojiao Zhang Linglingzhi Zhu Mikael Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Systems Engineering and Engineering Management Chinese University of Hong Kong

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an $(\epsilon, \delta)$ DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm.

关键词： Privacy Federated learning Heuristic algorithms Noise Signal processing algorithms Servers

来源：评论

学校读者我要写书评

暂无评论

Scheduling Delays and Curtailment for Household Appliances with Deterministic Load Profiles using MPC

arXiv

引用

arXiv 2022年

作者： Lian, Yingzhao Jiang, Yuning Jones, Colin N. Opila, Daniel F. Automatic Control Laboratory EPFL Switzerland United States Naval Academy Electrical and Computer Engineering Department United States

Smart home appliances can time-shift and curtail their power demand to assist demand side management or allow operation with limited power, as in an off-grid application. This paper proposes a scheduling process to start appliances with time-varying deterministic load profiles. Self-triggered model predictive control is used to limit the household net power demand below a given threshold. Meanwhile, deterministic load profiles are more difficult to schedule compared to variable charging or thermal loads because system failure will occur once power demand is not satisfied. The proposed scheme formulates the decision of the load shifting time as a continuous optimization problem, and an inhomogeneous time grid system is introduced to handle the optimization of different appliances and their consensus at this resolution. The efficacy of the proposed scheme is studied by numerical comparison with a mixed-integer MPC controller and by a case study of three home appliances and an interruptible washing machine. © 2022, CC BY-NC-ND.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Designing a Robust control System Based on Sliding Mode control for Two-axis Gimbal Systems

Designing a Robust Control System Based on Sliding Mode Cont...

引用

IEEE NW Russia Young Researchers in Electrical and Electronic engineering Conference (EIConRusNW)

作者： Nguyen Viet Phuong Nguyen Trong Tuyen Nguyen Duy Khanh Nguyen Ngoc Hung Department of Aerospace Control Systems Academy of Military Science and Technology Hanoi Vietnam Department of Biomedical Engineering Le Quy Don Technical University Hanoi Vietnam Department of Automatic Control Systems Saint Petersburg State Electrotechnical University Hanoi Vietnam Department of Aerospace Control Systems Le Quy Don Technical University Hanoi Vietnam

Two-axis gimbals are used in stabilizing and controlling the aiming of optical systems. The main task is to isolate the angular motion of the payload and the disturbances affecting the optical axis of the camera while maintaining the camera’s orientation locked onto the target. Currently, two commonly used gimbal structures are the Yaw-Pitch type and the Roll-Swing type. In this paper, we delve into an in-depth study to develop the full mathematical models for both types, thereby analyzing and evaluating the influence of the cross-channel noise moment effects caused by gimbal imbalance on the stability and aiming control quality under complex angular motion conditions of the payload. Simulation results conducted using MATLAB/SIMULINK with the two-axis gimbal model demonstrate that employing a robust control system significantly reduces the impact of disturbances and enhances the quality of control and stability of the transmission system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient downlink power allocation algorithms for cell-free massive mimo systems

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2021年 2卷 168-186页

作者： Chakraborty, Sucharita Demir, Ozlem Tugfe Bjornson, Emil Giselsson, Pontus Linköping University Linköping Sweden Space Application Centre Indian Space Research Organization Ahmedabad380015 India Department of Computer Science Kth Royal Institute of Technology Stockholm100 44 Sweden Department of Automatic Control Lund University Lund Sweden

Cell-free Massive MIMO systems consist of a large number of geographically distributed access points (APs) that serve the users by coherent joint transmission. The spectral efficiency (SE) achieved by each user depends on the power allocation: which APs that transmit to which users and with what power. In this article, we revisit the max-min and sum-SE power allocation policies, which have previously been approached using high-complexity general-purpose solvers. We develop and compare several different high-performance low-complexity power allocation algorithms that are appropriate for use in large systems. We propose two new algorithms for sum-SE power optimization inspired by weighted minimum mean square error (WMMSE) minimization and fractional programming (FP). Further, one new FP-based algorithm is proposed for max-min fair power allocation. The alternating direction method of multipliers (ADMM) is used to solve specific convex subproblems in the proposed algorithms. Our ADMM reformulations lead to multiple small-sized subproblems with closed-form solutions. The proposed algorithms find global or local optimal power allocation solutions for large-scale systems but with reduced computational time compared to previous work. © 2020 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Dependability Evaluation of Industrial Networks by Using Monte Carlo With Importance Sampling

Dependability Evaluation of Industrial Networks by Using Mon...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Paolo Guarino Filippo Nevi Paolo Dai Pra Davide Quaglia Tiziano Villa Department of Engineering for Innovation Medicine University of Verona Italy Pure Power Control™S.r.l. Italy Department of Computer Science University of Verona Italy

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Mechanisms for detecting communication errors are crucial in industrial networks where reliability is a primary requirement. Even if the Cyclic Redundancy Check (CRC) polynomial generator is given for each transmission protocol, an application designer could choose a specific protocol according to its robustness, or additional error detection mechanisms can be freely added at the application level (e.g., nested CRC). Therefore, a methodology is desired to evaluate the residual error probability of a given protocol, i.e., considering its packet structure and error detection mechanism. Symbolic approaches proposed in the literature are not scalable for usual packet sizes. Monte Carlo simulation can be a valid alternative to inject errors and see what happens. However, the brute force generation of error patterns takes too much simulation time if the channel error probability is very low, as in realistic scenarios. This paper presents a Monte Carlo approach enriched with Importance Sampling, implemented in a tool 1 1 https://***/guarinopaolo/residual-error-probability-simulator. The framework takes the packet structure and the error detection mechanism as input, thus being independent of them. Experimental results validate the approach with respect to state-of-the-art approaches and show its effectiveness in exploring protocol alternatives.

关键词： Cyclic redundancy check Monte Carlo methods Protocols Error probability Force Robustness Polynomials Generators Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Masquerading Email Detection 8

Masquerading Email Detection

引用

8th International Conference on Information Technology and Nanotechnology, ITNT 2022

作者： Saurabh, Raman Bhasme, Sarang Balasaheb Saeed, Muhammad Salman Kumar, Chanchal Nazarov, Alexey Moscow Institute of Physics and Technology Department of Radio Engineering and Cybernetics Moscow Russia Jamia Millia Islamia Department of Computer Science New Delhi India Ciena India Pvt. Ltd Haryana India Federal Research Centre Computer Science and Control of Russian Academy of Sciences Moscow Russia

ISBN: (数字)9781665485715

ISBN: (纸本)9781665485715

The email which contains suspicious links or malicious files is one of the considerable threats in the digital world nowadays and because of these types of emails, enormous social and financial losses occur. The different approaches of detection of masquerading emails, which are already proposed, are unceasingly being renovated, the outcomes of that are not more impressive. Moreover, the masquerading email crisis is intensifying at a higher rate in the past few years. Because of the rapid increase in masquerading email threats, there is a need to develop new techniques to eliminate these types of masquerading email which is the present need of the hour. In our proposed work, the structure of the email was thoroughly analysed and then fed on recurrent convolutional neural networks. After that the Recurrent convolutional neural network model processes the email header and body of the email for detecting the suspicious or malicious files, elements and codes at character and word level of particular email;if the suspicious elements, file extension is detected then it will automatically transfer to the spam folder. For increasing the veracity of the design, the training of the model is performed with a balanced and unbalanced data set due to which improves the efficiency to distinguish between the legitimate and non-legitimate emails. Thus, the result of the experiment implies that the filtering or recognition probability of non-legitimate email is much closer to the value one, which also symbolizes that certainty of the proposed model enhances. As a result, classification of the spam and non-spam email is done by using the neural network classifier. The masquerading emails contain the suspicious links when the user clicks on the link the redirection takes place and the user reaches the suspicious website where the confidential information is asked from the user. The details shared by users results in financial and social losses. © 2022 IEEE.

关键词： Support vector machines

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：