检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Antonios Georgantas Stelios Timotheou Christos G. Panayiotou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus 2109 Cyprus

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Urban traffic congestion during morning rush hour is a source of severe discomfort for commuters. Some commuters must make an intermediate stop at a school to drop off their children before heading to their destination. On the other hand, a different portion of commuters utilize the same network infrastructure to arrive at their destination directly. The fact that schools start at the same time implies that the school-oriented commuters depart from their homes almost simultaneously, significantly contributing to congestion. To address this issue, we propose a feedback-based mechanism that in conjunction with different optimization solvers, staggers the start time of schools such that the peak demand is redistributed. The related problem is formulated as a bi-objective mixed integer nonlinear program that jointly minimizes i) the total time spent by all vehicles inside the network and ii) the overall change between the initial and the staggered start time of the schools. Simulation experiments verify that for the examined network architecture, the developed approach can pinpoint school start times that can completely eliminate congestion.

关键词： Hands Feedback loop Prevention and mitigation Network architecture Vehicle dynamics Optimization Traffic congestion Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time and On-Board Anomalous Command Detection in UAV Operations via Simultaneous UAV-Operator Monitoring

Real-Time and On-Board Anomalous Command Detection in UAV Op...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Rafaella Elia Theocharis Theocharides Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

Constant technological advancements in the area of Remotely Operated Vehicles (ROVs) and specifically Unmanned Aerial Vehicles (UAVs), facilitate their widespread use in a variety of safety-critical applications. Sometimes, the operator is required to control the vehicle in harsh and stressful situations. Stress and fatigue can be challenging factors that can compromise the outcome and safety of the mission. Therefore, the operator is prone to potentially issue involuntary movements to the controller of the UAV. Nevertheless, real-time monitoring of the operator and the UAV can prevent possible accidents. In this work, we present a feature-based Machine Learning (ML) approach for the classification of abnormal commands, via simultaneous monitoring of the human operator and the UAV, during a mission. The proposed classification targets onboard implementation on the UAV and operates in real-time. We provide experimental results using Jetson Xavier NX as an experimental platform that includes trade-offs across all the performance metrics, where we achieve 82% accuracy with minimal processing time (9ms) and energy consumption (5mJ).

关键词： Measurement Energy consumption Remotely guided vehicles Machine learning Autonomous aerial vehicles Fatigue Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Rare Event Detection in Imbalanced Multi-Class Datasets Using an Optimal MIP-Based Ensemble Weighting Approach

arXiv

引用

arXiv 2024年

作者： Tertytchny, Georgios Stavrinides, Georgios L. Michael, Maria K. KIOS Research and Innovation Center of Excellence Cyprus Department of Electrical and Computer Engineering University of Cyprus Cyprus

To address the challenges of imbalanced multi-class datasets typically used for rare event detection in critical cyber-physical systems, we propose an optimal, efficient, and adaptable mixed integer programming (MIP) ensemble weighting scheme. Our approach leverages the diverse capabilities of the classifier ensemble on a granular per class basis, while optimizing the weights of classifier-class pairs using elastic net regularization for improved robustness and generalization. Additionally, it seamlessly and optimally selects a predefined number of classifiers from a given set. We evaluate and compare our MIP-based method against six well-established weighting schemes, using representative datasets and suitable metrics, under various ensemble sizes. The experimental results reveal that MIP outperforms all existing approaches, achieving an improvement in balanced accuracy ranging from 0.99% to 7.31%, with an overall average of 4.53% across all datasets and ensemble sizes. Furthermore, it attains an overall average increase of 4.63%, 4.60%, and 4.61% in macro-averaged precision, recall, and F1-score, respectively, while maintaining computational efficiency. © 2024, CC BY.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Optimal Multi-Constrained Workflow Scheduling for Cyber-Physical Systems in the Edge-Cloud Continuum

Optimal Multi-Constrained Workflow Scheduling for Cyber-Phys...

引用

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： Andreas Kouloumpris Georgios L. Stavrinides Maria K. Michael Theocharis Theocharides Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The emerging edge-hub-cloud paradigm has enabled the development of innovative latency-critical cyber-physical applications in the edge-cloud continuum. However, this paradigm poses multiple challenges due to the heterogeneity of the devices at the edge of the network, their limited computational, commu-nication, and energy capacities, as well as their different sensing and actuating capabilities. To address these issues, we propose an optimal scheduling approach to minimize the overall latency of a workflow application in an edge-hub-cloud cyber-physical system. We consider multiple edge devices cooperating with a hub device and a cloud server. All devices feature heterogeneous multi core processors and various sensing, actuating, or other specialized capabilities. We present a comprehensive formulation based on continuous-time mixed integer linear programming, encapsulating multiple constraints often overlooked by existing approaches. We conduct a comparative experimental evaluation between our method and a well-established and effective scheduling heuristic, which we enhanced to consider the constraints of the specific problem. The results reveal that our technique outperforms the heuristic, achieving an average latency improvement of 13.54 % in a relevant real-world use case, under varied system configurations. In addition, the results demonstrate the scalability of our method under synthetic workflows of varying sizes, attaining a 33.03 % average latency decrease compared to the heuristic.

关键词： Program processors Processor scheduling Multicore processing Scalability Optimal scheduling Cyber-physical systems software

来源：评论

学校读者我要写书评

暂无评论

Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Response

Synergising Human-like Responses and Machine Intelligence fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Savvas Papaioannou Panayiotis Kolios Christos G. Panayiotou Marios M. Polycarpou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In the rapidly changing environments of disaster response, planning and decision-making for autonomous agents involve complex and interdependent choices. Although recent advancements have improved traditional artificial intelligence (AI) approaches, they often struggle in such settings, particularly when applied to agents operating outside their well-defined training parameters. To address these challenges, we propose an attention-based cognitive architecture inspired by Dual Process Theory (DPT). This framework integrates, in an online fashion, rapid yet heuristic (human-like) responses (System 1) with the slow but optimized planning capabilities of machine intelligence (System 2). We illustrate how a supervisory controller can dynamically determine in real-time the engagement of either system to optimize mission objectives by assessing their performance across a number of distinct attributes. Evaluated for trajectory planning in dynamic environments, our framework demonstrates that this synergistic integration effectively manages complex tasks by optimizing multiple mission objectives.

关键词： Training Trajectory planning Disasters Decision making Process control Real-time systems Planning

来源：评论

学校读者我要写书评

暂无评论

Passivity Preserving Safety-Critical Control of Switched Systems

Passivity Preserving Safety-Critical Control of Switched Sys...

引用

IEEE Conference on Decision and Control

作者： Qingkai Meng Andreas Kasis Marios M. Polycarpou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

System safety refers to the property of the state trajectories to remain within some predefined set at all times. Integrating safety and stability offers significant advantages, such as resilience to disturbances and enhanced reliability and predictability. This paper combines control barrier functions and passivity methodologies, in the context of switched systems, to simultaneously ensure stability and safety. We derive conditions under which the passivity of switched systems is preserved under control barrier function-based switched safety-critical control. This enables the construction of a suitable design framework for observer-based output feedback controllers and switching laws, that achieve simultaneous stability and safety guarantees, without imposing any assumption on the safety of individual subsystems. Furthermore, we show that the simultaneous passivity and safety of interconnected switched systems under feedback and parallel configurations can be guaranteed by applying the developed conditions on each local switched subsystem. The applicability of the developed theoretical results is validated through a planar moving body example.

关键词： Switched systems Simulation Switches Control systems Stability analysis Safety Trajectory Reliability Output feedback Resilience

来源：评论

学校读者我要写书评

暂无评论

Inpainting Technique for Removing Vehicle Logos Using Haar-Like and Fast Marching Methods

Inpainting Technique for Removing Vehicle Logos Using Haar-L...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Meryem Durmuş Burhan Ergen Ömer Durmuş Ferhat Atasoy Center for Distance Education Samsun University Samsun Turkey Department of Computer Engineering College of Engineering Firat University Elazig Turkey Department of Software Engineering College of Engineering Samsun University Samsun Turkey Department of Computer Engineering College of Engineering Karabuk University Karabuk Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

Inpainting is the process of removing an unwanted object or region in an image without degrading the image quality. Inpainting offers a solution to problems such as repairing damaged images or removing unwanted parts of the image. In this study, we focus on the detection of brand logos in vehicle images and the removal of these regions using inpainting. The study consists of two main phases: First, the Haar-like features method is used to detect vehicle logos. Then, the detected logos are removed from the image by applying inpainting with the Fast Marching Method. As a result of the experimental studies, it was found that the methods successfully detected and removed the logos with an accuracy of 98%, and the PSNR value ranged between 25.36 dB and 25.41 dB, and the SSIM value ranged between 0.96692 and 0.96994 while maintaining the image quality. These results show that the proposed method exhibits high performance in removing vehicle logos efficiently.

关键词： Image quality Measurement Accuracy Object detection Feature extraction Data processing Artificial intelligence Noise level

来源：评论

学校读者我要写书评

暂无评论

Analytical Modeling of Multiple Access Interference in C-V2X Sidelink Communications 2

Analytical Modeling of Multiple Access Interference in C-V2X...

引用

2nd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2022

作者： Rehman, Abdul Di Marco, Piergiuseppe Valentini, Roberto Santucci, Fortunato Computer Science and Mathematics Center of Excellence EX-EMERGE University of l'Aquila Department of Information Engineering L'Aquila67100 Italy

ISBN: (数字)9781665498258

ISBN: (纸本)9781665498258

Cellular vehicle-to-everything (C-V2X) communications will play a pivotal role in the realization of connected and cooperative autonomous driving. Applications such as ve-hicle platooning benefit from sidelink communications to fulfill stringent latency requirements at the cost of uncertainty in the reliability due to the multiple access interference. In this paper, we propose an analytical framework to model the performance of C-V2X sidelink communications in a vehicle platooning scenario, depending on the available resources, the number of interfering vehicles and their relative positions. A Nakagami-Lognormal composite channel model is assumed, and the moment matching approximation (MMA) is used to approximate the statistics of the signal-to-interference-plus-noise ratio (SINR). Compared to existing simulation studies in the literature, the proposed model offers a compact, yet accurate, approximation of the achievable performance in terms of packet success rate, and allows for planning and adapting the configuration and parameters setup of the vehicle platoon. © 2022 IEEE.

关键词： Vehicle to Everything

来源：评论

学校读者我要写书评

暂无评论

Quantum Calculus-Based Two-Dimensional Least Mean Square Algorithm 58

Quantum Calculus-Based Two-Dimensional Least Mean Square Alg...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Moinuddin, Muhammad Zerguine, Azzedine Al-Saggaf, Ubaid M. Arif, Muhammad King Abdulaziz University Electrical and Computer Engineering Department The Centre of Excellence in Intelligent Engineering Systems Jeddah Saudi Arabia Kfupm Electrical Engineering Department The Interdisciplinary Research Center for Communication Systems and Sensing Dhahran31261 Saudi Arabia Institute of Networked and Embedded Systems University of Klagenfurt Klagenfurt Austria The Ubiquitous Sensing Systems Lab University of Klagenfurt-Silicon Austria Labs Klagenfurt Austria

ISBN: (纸本)9798350354058

Recent work of the one-dimensional q-LMS algorithm give insight that the Quantum Calculus based gradient called the q-gradient is capable of improving the convergence behavior in contrast to the standard LMS algorithm. The reason for this is the fact that the q-derivative takes larger steps in minimizing a cost function as it evaluates the secant in contrast to the tangent of the cost function. Motivated by this, we propose a two-dimensional version of the q-LMS algorithm. More precisely, we employ Quantum Calculus based q-gradient in steepest descent optimization of mean-square-error (MSE) cost function in 2D adaptive filtering scenario to obtain two-dimensional q-LMS (2D q-LMS) algorithm. A thorough analytical investigation of the proposed 2D q-LMS algorithm in both mean and mean-square sense is provided. Both the transient and steady-state convergence behaviours are examined. Consequently, excess MSE (EMSE) learning curve and its steady-state expression are evaluated in closed form. Simulation results are presented for the application of noise cancelation in images to show the superiority of the proposed 2D q-LMS algorithm. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Feature selection and prediction of small-for-gestational-age infants

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第3期15卷 1881-1895页

作者： Li, Jianqiang Liu, Lu Zhou, MengChu Yang, Ji-Jiang Chen, Shi Liu, HuiTing Wang, Qing Pan, Hui Sun, ZhiHua Tan, Feng School of Software Engineering Beijing University of Technology Beijing China Department of Electronical and Computer Engineering New Jersey Institute of Technology NewarkNJ United States Tsinghua University Beijing China Department of Endocrinology Peking Union Medical College Hospital Beijing China Department of Internal Medicine Peking Union Medical College Hospital Beijing China Beijing Chaoyang District Maternal and Child Healthcare Hospital Beijing China Chinese Center For Disease Control And Prevention Beijing China

The small-for-gestational-age (SGA) condition often causes serious problems. Therefore, identifying the risk factors for SGA is important. Traditional statistical methods such as stepwise logistic regression (LR) have been widely utilized to discover possible risk factors. However, other feature selection methods from machine learning field have rarely been employed for the task. In this paper, a comparison of five feature selection methods from both fields for SGA risk factors analysis is conducted for the first time. To evaluate their performance, four classification algorithms are used to construct SGA prediction models. The evaluation criteria are precision and the area under the receiver operator characteristic curve. Stepwise LR achieves the best performance among the five feature selection methods, because it conducts both a univariate significance test and a model significance test, which make it more suitable for handling the complex relations among features. The top 20 features selected by each feature selection method and the 27 features selected by four or five of them could assist physicians to revise traditional SGA evaluation models. Ensemble method is also exploited to build effective SGA prediction models based on the feature subsets, which is indeed superior compared with the individual ones shown in the results. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Feature Selection

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：