检索结果-内蒙古大学图书馆

Cyber Attack Detection and Classification for Integrated On-board Electric Vehicle Chargers subject to Stochastic Charging Coordination

引用

Transportation Research Procedia 2023年 70卷 44-51页

作者： Ali Arsalan Laxman Timilsina Behnaz Papari Grace Muriithi Gokhan Ozkan Phani Kumar Christopher S. Edrington Department of Automotive Engineering Clemson University Greenville 29607 U.S. The Holcombe Department of Electrical and Computer Engineering Clemson University Clemson 29631 U.S Distribution A. Approved for public release distribution unlimited. (OPSEC 7474)

Cyber-physical system (CPS) of EV on-board chargers is connected to an IOT-based communication network for coordinated control, which is highly vulnerable to cyber-attacks. This charging coordination control incorporating hundreds of EVs and associated charging sessions, feed in a stochastic reference input to energy management system (EMS) of on-board EV chargers. Hence, under these varying operating conditions, a pure data-driven-based detection model can experience a disturbance detection failure. Therefore, a model predictive control (MPC) based machine learning (ML) network, integrated with a residual based training data pre-processing is proposed in this paper. This MPC based ML approach can effectively detect a tempered response while addressing the aleatory behaviour of cooperative control with enhanced disturbance detection accuracy. The proposed model utilizing various system level signals can also efficiently classify a normal condition, cyber-attack, and a physical fault. The superior performance of the proposed approach is validated by using different case study scenarios of training datasets.

关键词： Integrated on-board chargers (IOBCs) cyber-attack MOSFET fault, neural networks model predictive control direct power control

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of an EMG-based System for Monitoring and Help Request

Design and Implementation of an EMG-based System for Monitor...

引用

2022 International Conference on Smart Systems and Power Management, IC2SPM 2022

作者： Zeine, Carla Daou, Roy Abi Zeid Telawi, Samer Boercsoek, Josef Hayek, Ali Haidar, Gaby Abou University of Kassel Faculty of Electrical Engineering /Computer Science Department of Computer Architecture and System Programming Kassel Germany Lebanese German University Faculty of Public Health Jounieh Department of Computer Architecture and System Programming Biomedical Technologies Department Jounieh Lebanon Université la Sagesse Faculty of Engineering Furn El Chebbak Mechatronics Department Beirut Lebanon University of Applied Science Hamm-Lippstadt Department Lippstadt 2 Hardware Engineering Marker Allee 76-78 Hamm59063 Germany American University of Science and Technology Faculty of Engineering Zahle Lebanon

ISBN: (数字)9781665452915

ISBN: (纸本)9781665452915

Integrating electrophysiological signals in larger systems is getting wider due to the fact that such modalities facilitate the daily tasks of users. However, the high cost of monitoring systems (e.g., oscilloscopes) limits the testing and analysis of the acquired signal from such noisy systems (i. e., electrophysiological devices). The proposed system is a part of a larger proj ect that deals with the identification of sign language movements through the use of Muscle-computer Interfaces. On one hand, the user is able to display the signal acquired by the electrodes on an LCD screen. On the other hand, the system helps a mute patient to issue a special message to his surrounding environment that does not know the sign language to ask for help. The second feature is not unique, as it can be replaced by any other application based on the user's needs. The system was tested on several persons, and the results are promising. © 2022 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Ensembles for the Detection of Alzheimer's Disease Using Imbalanced Clock Drawing Test Images

Deep Neural Network Ensembles for the Detection of Alzheimer...

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Sai Santosh Reddy Danda Alper Kursat Uysal Tian Qin Anu Kumar Varshitha Sannareddy Mengyao Hu Richard Gonzalez Yi Lu Murphey Department of Electrical&Computer Engineering University of Michigan-Dearborn Dearborn USA Department of Computer Engineering Alanya Alaaddin Keykubat University Alanya Turkiye School of Public Health The University of Texas Health Science Center at Houston Houston United States Department of Psychology and Statistics University of Michigan Ann Arbor MI USA

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

This paper explores innovative machine learning technologies for the detection of Alzheimer's Disease (AD) from large and imbalanced clock drawing test (CDT) images. We present a deep ensemble learning framework, 2Level MM-MD, which includes two-level ensemble of MultiModel deep neural networks (DNN) trained on MultiData blocks. The data blocks are generated by applying partition based and bootstrap statistical data resampling methods to the large but imbalanced CDT image data. To produce a more robust system that is better adapted to imbalanced CDT data, the 2Level MM-MD ensemble framework attempts to leverages both 1) the richness of large data blocks generated using effective data re-sampling schemes, and 2) multiple deep neural network systems that are trained on the resembled data blocks through transfer learning to produce a more robust system that is better adapted to more generalized CDT image domains. Three deep neural network models (EfficientNet, ResNet101, and ViT), along with six different sampling methods are used to generate re-balanced data blocks, and five different decision schemes are implemented and evaluated. The ensemble systems are trained and evaluated using a large CDT image dataset from Rounds 1 to 9 of the National Health and Aging Trends Study (NHATS), which contains over 47,723 CDT images, where 92% are class 0 (no dementia) and 8% are class 1 (probable dementia). The top classification system is a 2Level MM-MD system E5 with a two-level decision rule SoM. The system generated 0.67 Recall and 0.35 F1-Score on the test data. This represents a 123% improvement in Recall and a 25% improvement in F1-Score compared to the best baseline system, which is a classifier trained using EfficientNet with the training data balanced by oversampling the minority class.

关键词： Transfer learning Training data Artificial neural networks Aging Sampling methods Probabilistic logic Data models Ensemble learning Alzheimer's disease Clocks

来源：评论

学校读者我要写书评

暂无评论

Design Considerations for Building Credible Security Testbeds: Perspectives from Industrial Control System Use Cases

引用

Journal of Cyber Security Technology 2021年第2期5卷 71-119页

作者： Ani, Uchenna P. Daniel Watson, Jeremy M. Green, Benjamin Craggs, Barnaby Nurse, Jason R. C. Department of Science Technology Engineering and Public Policy University College London United Kingdom Computing and Communications Lancaster University United Kingdom Department of Computer Science University of Bristol United Kingdom School of Computing University of Kent United Kingdom

This paper presents a mapping framework for design factors and an implementation process for building credible Industrial Control Systems (ICS) security testbeds. The security and resilience of ICSs has become a critical concern to operators and governments following widely publicised cyber security events. The inability to apply conventional Information Technology security practice to ICSs further compounds challenges in adequately securing critical systems. To overcome these challenges, and do so without impacting live environments, testbeds are widely used for the exploration, development, and evaluation of security controls. However, how a testbed is designed and its attributes, can directly impact not only its viability but also its credibility. Combining systematic and thematic analysis, and the mapping of identified ICS security testbed design attributes, we propose a novel relationship map of credibility-supporting design factors (and their associated attributes) and a process implementation flow structure for ICS security testbeds. The framework and implementation process highlight the significance of demonstrating some design factors such as user/experimenter expertise, clearly defined testbed design objectives, simulation implementation approach, covered architectural components, core structural and functional characteristics covered, and evaluations to enhance confidence, trustworthiness and acceptance of ICS security testbeds as credible. These can streamline testbed requirement definition, improve design consistency and quality while reducing implementation costs. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Integration of 5G and Motion Sensors for Vehicular Positioning: A Loosely-Coupled Approach

arXiv

引用

arXiv 2024年

作者： Saleh, Sharief Bader, Qamar Karaim, Malek Elhabiby, Mohamed Noureldin, Aboelmagd Lab Department of Electrical and Computer Engineering Royal Military College of Canada KingstonONK7K 7B4 Canada The Department of Electrical and Computer Engineering Queen's University KingstonONK7L 3N6 Canada Micro Engineering Tech. Inc The Public Works Department Ain Shams University Cairo11566 Egypt

Autonomous vehicles (AVs) are poised to revolutionize the transportation industry by enhancing traffic efficiency and road safety. However, achieving optimal vehicular autonomy demands an uninterrupted and precise positioning solution, especially in deep urban environments. 5G mmWave holds immense potential to provide such a service due to its accurate range and angle measurements. Yet, as mmWave signals are prone to signal blockage, severe positioning errors will occur. Most of the 5G positioning literature relies on constant motion models to bridge such 5G outages, which do not capture the true dynamics of the vehicle. Few proposed methodologies rely on inertial measurement units (IMUs) to bridge such gaps, where they predominantly use tightly coupled (TC) integration schemes, introducing a nonlinear 5G measurement model. Such approaches, which rely on Kalman filtering, necessitate the linearization of the measurement model, leading to pronounced positioning errors. In this paper, however, we propose a loosely coupled (LC) sensor fusion scheme to integrate 5G, IMUs, and odometers to mitigate linearization errors. Additionally, we propose a novel method to design the process covariance matrix of the extended Kalman filter (EKF). Moreover, we propose enhancements to the mechanization of the IMU data to enhance the standalone IMU solution. The proposed methodologies were tested using a novel setup comprising 5G measurements from Siradel's S_5G simulation tool and real IMU and odometer measurements from an hour-long trajectory. The proposed method resulted in 14 cm of error for 95% of the time compared to 1 m provided by the traditional constant velocity model approach. © 2024, CC BY.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Understanding the Transit Gap: A Comparative Study of On-Demand Bus Services and Urban Climate Resilience in South End, Charlotte, NC and Avondale, Chattanooga, TN

arXiv

引用

arXiv 2024年

作者： Hosseini, Sanaz Sadat Ardabili, Babak Rahimi Azarbayjani, Mona Pulugurtha, Srinivas Tabkhi, Hamed Department of Civil and Environmental Engineering University of North Carolina at Charlotte CharlotteNC United States Department of Public Policy University of North Carolina at Charlotte CharlotteNC United States School of Architecture University of North Carolina at Charlotte CharlotteNC United States Department of Electrical and Computer Engineering University of North Carolina at Charlotte CharlotteNC United States

Urban design significantly impacts sustainability, particularly in the context of public transit efficiency and carbon emissions reduction. This study explores two neighborhoods with distinct urban designs: South End, Charlotte, NC, featuring a dynamic mixed-use urban design pattern, and Avondale, Chattanooga, TN, with a residential suburban grid layout. Using the TRANSIT-GYM tool, we assess the impact of increased bus utilization in these different urban settings on traffic and CO2 emissions. Our results highlight the critical role of urban design and planning in transit system efficiency. In South End, the mixed-use design led to more substantial emission reductions, indicating that urban layout can significantly influence public transit outcomes. Tailored strategies that consider the unique urban design elements are essential for climate resilience. Notably, doubling bus utilization decreased daily emissions by 10.18% in South End and 8.13% in Avondale, with a corresponding reduction in overall traffic. A target of 50% bus utilization saw emissions drop by 21.45% in South End and 14.50% in Avondale. At an idealistic goal of 70% bus utilization, South End and Avondale witnessed emission reductions of 37.22% and 27.80%, respectively. These insights are crucial for urban designers and policymakers in developing sustainable urban landscapes. Copyright © 2024, The Authors. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spectrum

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spect...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Rizvi, Syed Naheel Raza Sarfraz, Muhammad Alibakhshikenari, Mohammad Dalarsson, Mariana Falcone, Francisco Chungbuk National University Department of Information and Communication Engineering Cheongju Korea Republic of Virtual University of Pakistan Department of Computer Science Lahore Pakistan Universidad Carlos III de Madrid Department of Signal Theory and Communications Madrid Leganés28911 Spain KTH Royal Institute of Technology School of Electrical Engineering and Computer Science StockholmSE 100-44 Sweden Public University of Navarre Electric Electronic and Communication Engineering Department Pamplona31006 Spain Public University of Navarre Institute of Smart Cities Pamplona31006 Spain

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

We present a compact wideband antenna operating in the 28 GHz and 38 GHz millimeter-wave spectrum. The proposed antenna is designed on the Rogers RT/duroid 5880 substrate. The proposed antenna has a simple geometry and compact dimensions of 17 mm × 12 mm × 0.79 mm. The antenna design is simulated using the ANSYS HFSS software. The features of the proposed antenna are also compared to similar designs from the literature, to demonstrate the potential of our antenna for use in the targeted frequency band. The results in the present paper indicate that our design is a good candidate for use in future wireless communication systems. © 2022 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

ENHANCING SYMBOLIC REGRESSION AND UNIVERSAL PHYSICS-INFORMED NEURAL NETWORKS WITH DIMENSIONAL ANALYSIS

arXiv

引用

arXiv 2024年

作者： Podina, Lena Darooneh, Diba Grewal, Joshveer Kohandel, Mohammad Cheriton School of Computer Science University of Waterloo Canada Department of Electrical and Computer Engineering University of Waterloo Canada Northville High School Public school in Northville MI United States Department of Applied Mathematics University of Waterloo Canada

We present a new method for enhancing symbolic regression for differential equations via dimensional analysis, specifically Ipsen’s and Buckingham π methods. Since symbolic regression often suffers from high computational costs and overfitting, non-dimensionalizing datasets reduces the number of input variables, simplifies the search space, and ensures that derived equations are physically meaningful. As our main contribution, we integrate Ipsen’s Method of dimensional analysis with Universal Physics-Informed Neural Networks. We also combine dimensional analysis with the AI Feynman symbolic regression algorithm to show that dimensional analysis significantly improves the accuracy of the recovered equation. The results demonstrate that transforming data into a dimensionless form significantly decreases computation time and improves accuracy of the recovered hidden term. For algebraic equations, using the Buckingham π Theorem reduced complexity, allowing the AI-Feynman model to converge faster with fewer data points and lower error rates. For differential equations, Ipsen’s Method was combined with Universal Physics-Informed Neural Networks (UPINNs) to identify hidden terms more effectively. These findings suggest that integrating dimensional analysis with symbolic regression can significantly lower computational costs, enhance model interpretability, and increase accuracy, providing a robust framework for automated discovery of governing equations in complex systems when data is limited. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Heuristics for Multi-Objective Sensor Placement in Traffic Networks

Low Complexity Heuristics for Multi-Objective Sensor Placeme...

引用

International Conference on Intelligent Transportation

作者： Marina Sofokleous Yiolanda Englezou Aristotelis Savva Stelios Timotheou Christos G. Panayiotou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Public Works Department of the Ministry of Transport Communications & Works Nicosia Cyprus

Monitoring the traffic state of the road network is very important for a plethora of reasons, such as the prevention of traffic congestion and the development of estimation and control policies. In order to efficiently obtain high-quality information on traffic, the sensors must be installed at optimal locations in the road network under study. This problem is known as the Network Sensor Location Problem (NSLP). In this work, a multi-objective NSLP is proposed for the installation of a pre-defined number of sensors to maximise (i) the covered traffic flow volume and (ii) the minimum distance between candidate links for sensor installation, while taking into account pre-installed sensors. We reformulate the problem into a single-objective mixed-integer linear program (MILP) that yields the optimal sensor locations. In addition, we propose four low-complexity heuristics for the solution of the problem. The performance of the proposed algorithms is evaluated for the traffic network of the Republic of Cyprus under real-life conditions and traffic data. Results show that the four low-complexity approaches yield a different trade-off between execution speed and solution quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Based Stochastic Dynamical Model to Measure Community Resilience

引用

Journal of Social Computing 2022年第3期3卷 262-286页

作者： Jaber Valinejad Lamine Mili C.Natalie Van Der Wal Data and System Science Lab Harvard Medical SchoolHarvard UniversityCambridgeMA 02138USA Bradley Department of Electrical and Computer Engineering Virginia TechNorthern Virginia CenterFalls ChurchVA 22043USA Department of Multi-Actor Systems Faculty of TechnologyPolicy and ManagementDelft University of TechnologyDelft2600 AAthe Netherlands.

Emergency services and utilities need appropriate planning tools to analyze and improve infrastructure and community resilience to *** as a key metric of community resilience is the social well-being of a community during a disaster,which is made up of mental and physical social *** factors influencing community resilience directly or indirectly are emotional health,emergency services,and the availability of critical infrastructures services,such as food,agriculture,water,transportation,electric power,and communications *** turns out that in computational social science literature dealing with community resilience,the role of these critical infrastructures along with some important social characteristics is not *** address these weaknesses,we develop a new multi-agent based stochastic dynamical model,standardized by overview,design concepts,details,and decision(ODD+D)protocol and derived from neuro-science,psychological and social sciences,to measure community resilience in terms of mental and physical *** this model,we analyze the micro-macro level dependence between the emergency services and power systems and social characteristics such as fear,risk perception,informationseeking behaviour,cooperation,flexibility,empathy,and experience,in an artificial ***,we simulate this model in two case studies and show that a high level of flexibility,experience,and cooperation enhances community *** for both theory and practice are discussed.

关键词： community resilience collective behavior emergency services power systems critical infrastructures artificial society overview,design concepts,details,and decision(ODD+D) cyber-physical-social system

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：