检索结果-内蒙古大学图书馆

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Li, Mingze Ren, Weihang Fan, Lei Guan, Yongpei University of Houston Dept. of Electrical and Computer Engineering TX United States Engineering Technology University of Houston TX United States University of Florida Dept. of Industrial and Systems Engineering FL United States

ISBN: (纸本)9798331541125

This paper presents a preprocessing method to solve the security-constrained unit commitment with AC power flows (SCUC-ACPF), which is a large scale mixed-integer non-convex, nonlinear optimization problem. We introduce clustering algorithms and local search to reduce problem complexity, and obtain local optimal solutions within limited solving time and computational capacity. The clustering algorithms group buses into manageable clusters centered around core buses, creating smaller sub-grids for efficient optimization. The local search algorithms iteratively explore and improve solution quality. Our method ensures balanced clusters that respect physical and operational constraints, significantly enhancing optimization efficiency and contributing to more effective grid management and operation. © 2025 IEEE.

关键词： AC power flow clustering local search Unit commitment

来源：评论

学校读者我要写书评

暂无评论

Posture Recognition-Based Robot Control Using Media Pipe Pose

Posture Recognition-Based Robot Control Using Media Pipe Pos...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Woo Kim, Jong Yeong Mun, Seo Park, BoJeong Choi, Younglim Kim, Hyunseok Dong-A University Dept. of Electronic Engineering Busan Korea Republic of Dong-A University Dept.of Mechanical Engineering Busan Korea Republic of Dong-A University Dept. of Software Innovation Center Busan Korea Republic of Dong-A University Dept. of Computer Engineering Busan Korea Republic of

ISBN: (纸本)9798331510756

This study proposed a body movement-based system for efficiently controlling robots in large indoor environments. Traditional hand gesture recognition systems experience significant accuracy loss in large indoor spaces, particularly as the distance between the user and the camera grows. To address this issue, clear and large body movements were used as control signals instead of hand movements. For example, participants could give commands to the robot by raising both hands or lifting one hand in a specific direction. The system utilized MediaPipe Pose to track the user's posture in real time and communicated commands from the server to the robot via TCP/IP socket communication. This structure ensured stable data transmission, enabling smooth robot control even in expansive spaces. Consequently, this research demonstrated the feasibility of effective robot control in large indoor areas, such as screen golf courses, and suggested the potential for system expansion in various indoor environments. © 2025 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Deeper Anomaly Detection in Industrial Automation

Deeper Anomaly Detection in Industrial Automation

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Ho-Seok Jung Sung Won Jang Youngmi Baek Dept. of Computer Software Engineering Changshin University Korea Dept. of Computer Engineering Changshin University Korea

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

The security of industrial networks, particularly in industrial automation systems, is critical for ensuring system reliability and protecting sensitive data. This paper proposes a deeper anomaly detection system using the ResNet34 (Residual Network) model to identify and detect cyber-attacks in industrial networks, specifically focusing on Controller Area Network (CAN) systems. The study highlights the vulnerabilities in industrial communication protocols, such as CAN, Modbus, and Ethernet/IP, which are susceptible to cyber-attacks including replay, modification, and fuzzing attacks. These attacks can disrupt the functioning of industrial systems and cause significant damage. Experimental results show that the proposed model achieves a 100 % detection rate for all types of cyber-attacks, demonstrating its effectiveness in recognizing abnormal patterns and responding to changes in network behavior. The results confirm that the ResNet34-based deep anomaly detection model can be a valuable tool for strengthening the security of industrial networks by providing real-time detection of cyber-attacks, thereby ensuring the stability and safety of industrial automation systems.

关键词： Automation Stability analysis Real-time systems Safety Controller area networks Security Reliability Cyberattack Anomaly detection Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Reversible Data Hiding in Encrypted Images by Pixel Shifting 16

Enhanced Reversible Data Hiding in Encrypted Images by Pixel...

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Yang, Ching-Nung Lu, Yu-Quan Liu, Shu-Yu Xiong, Lizhi Dept. of Computer Sci. and Inf. Engineering National Dong Hwa University Hualien Taiwan School of Computer and Software Nanjing University of Inf. Sci. & Technology Nanjing China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

Reversible data hiding (RDH) is one special type of data hiding, and is widely used for many intended applications. Moreover, to protect the cover image, RDH in encrypted image (RDHEI) is accordingly proposed. With the reversibility and hiding data in encrypted image, RDHEI has potential utility in fields such as military and medical image transmission, and forensic analysis. Recently, Panchikkil et al. propose a RDHEI by using pixel swapping (RDHE-PSW) to swap some pixels in a block. The pixel swapping does not change pixel values, and thus Panchikkil et al.’s RDHEI-PSW can retain entropy and histogram. The smoothness of a block is calculated to extract the hidden bits and meantime recover the cover image. Panchikkil et al.’s RDHEI-PSW only hides two secret bits in every block. Recently, Kim et al. use pixel shifting (PSH), a circular right shift on a block, instead of pixel swapping to propose a RDHEI-PSH. In this paper, we still adopt PSH approach but use it in a different way (a modified PSH) to propose an enhanced RDHEI-PSH with a higher embedding capacity than Kim et al.’s RDHEI-PSH. Our enhanced RDHEI-PSH double the patterns on a block, on which we can embed more secret bits. Experimental results demonstrate that our enhanced RDHEI-PSH surpasses Panchikkil et al.’s RDHEI-PSW and Kim et al.’s RDHEI-PSH. © 2025 SPIE.

关键词： Military photography

来源：评论

学校读者我要写书评

暂无评论

Open RAN Slicing with Quantum Optimization

arXiv

引用

arXiv 2025年

作者： Keyela, Patatchona Cherkaoui, Soumaya Computer Engineering and Software Engineering Dept. Polytechnique Montreal Montreal Canada

RAN slicing technology is a key aspect of the Open RAN paradigm, allowing simultaneous and independent provision of various services such as ultra-reliable low-latency communications (URLLC), enhanced mobile broadband (eMBB), and massive machine-type communications (mMTC) through virtual networks that share a single radio access infrastructure. Efficient resource allocation is crucial for RAN slicing, as each service has specific quality of service (QoS) requirements, and a balance between different services must be maintained. Although heuristic and reinforcement learning (RL) techniques have been explored to achieve efficient resource allocation, these approaches face notable limitations: heuristic algorithms face complexity issues that limit their effectiveness in large networks, RL solutions are constrained by their dependency on training data and struggle to adapt to new scenarios and environments. This paper proposes a framework that leverages quantum optimization techniques to optimize radio resource blocks allocation in Open RAN slicing for URLLC and eMBB services. We provide a classical problem formulation and the quantum implementation using the constrained quadratic model on Dwave quantum annealing platform, showcasing the potential of quantum optimization techniques to deliver in real-time optimal solutions for optimization problems in 5G and beyond networks. © 2025, CC BY.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Open RAN Slicing with Quantum Optimization

Open RAN Slicing with Quantum Optimization

引用

International Global Information Infrastructure Symposium (GIIS)

作者： Patatchona Keyela Soumaya Cherkaoui Computer Engineering and Software Engineering Dept. Polytechnique Montreal Montreal Canada

ISBN: (数字)9798331520113

ISBN: (纸本)9798331520120

关键词： Annealing Training data Open RAN Quality of service Reinforcement learning Ultra reliable low latency communication Quantum annealing Resource management Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

Predicting Optimal Placement of Electric Vehicle Charge Stations Using Machine Learning: A Case Study in Glasgow, UK 12

Predicting Optimal Placement of Electric Vehicle Charge Stat...

引用

12th Iranian Conference on Renewable Energies and Distributed Generation, ICREDG 2025

作者： Mousaei, Arash Naderi, Yahya University of Tabriz Dept. Computer and Electrical Engineering Tabriz Iran Ricardo Aea Sustainable Energy Systems Department Glasgow United Kingdom

ISBN: (纸本)9798331525132

Given the reduced costs of establishing Electric Vehicle (EV) charging stations and the need to improve their accessibility, it is essential for EV developers and governments to identify optimized locations for new stations. This study presents a predictive modeling approach using Machine Learning to determine the optimal sites for EV charging stations in Glasgow. While various machine learning methods are available for this purpose, we focus on Linear Regression due to its simplicity and high accuracy. By analyzing a comprehensive dataset of 207 AC charging stations-including factors latitude, longitude, population density, number of kinds of plugs, total number of plugs, price per kWh, traffic conditions, distance to the nearest station, Air Quality Index (AQI), and land value - we aim to provide urban planners and policymakers with actionable insights. The study evaluates the performance of the Linear Regression model in predicting the most suitable locations for charging stations. The results indicate that the proposed model achieved impressive accuracy, with R2, Mean Absolute Error (MAE), and Mean Squared Error (MSE) values of 0.89, 0.05, and 0.08, respectively. This research contributes to the ongoing efforts in urban planning for sustainable mobility by offering a data-driven methodology for EV infrastructure development. © 2025 IEEE.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Optimizing 3D Flight Paths for Multiple UAVs with Connectivity Management in Urban Delivery systems 19

Optimizing 3D Flight Paths for Multiple UAVs with Connectivi...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Lee, Yeongmin Syahran, Raihan Muhammad Spangenberger, Mael Yang, Huigyu Oh, Jiyong Choo, Hyunseung Dept. of Artificial Intelligence Sungkyunkwan University Suwon Korea Republic of Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of Convergence Research Institute Sungkyunkwan University Suwon Korea Republic of Dept. of AI Systems Engineering Sungkyunkwan University Suwon Korea Republic of Dept. of Informatics Télécom SudParis Évry France

ISBN: (纸本)9798331507817

The dynamic deployment of aerial vehicles in urban delivery scenarios demands precise route planning, reliable data links, and efficient use of network infrastructure. Although prior efforts have explored various aspects of unmanned navigation or communication optimization, existing approaches often overlook the combined impact of three-dimensional path selection and robust connectivity maintenance. To address this gap, this paper proposes a deep reinforcement learning framework employing Independent Proximal Policy Optimization (IPPO) to steer the flight paths of unmanned vehicles while curtailing needless interactions with base stations (BSs). By incorporating communication-specific metrics, Reference Signal Received Power (RSRP), the proposed system adapts to urban conditions and upholds resilient network links. Comprehensive performance evaluations reveal the potential of the framework to reduce excessive BS connections by up to 82.24%, preserve RSRP levels above -80 dBm, and balance handover frequencies across flight trajectories. These findings affirm the scalability and effectiveness of the method for achieving efficient aerial navigation and consistent communication in urban delivery services. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust Reinforcement Learning with Human Feedback

arXiv

引用

arXiv 2025年

作者： Mandal, Debmalya Sasnauskas, Paulius Radanović, Goran Dept. of Computer Science University of Warwick United Kingdom Max-Planck Institute for Software Systems Germany

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream task differs significantly from the preference dataset used in fine-tuning. In order to mitigate this problem, we introduce a distributionally robust RLHF for fine-tuning LLMs. In particular, our goal is to ensure that a fine-tuned model retains its performance even when the distribution of prompts significantly differs from the distribution encountered during fine-tuning. We formulate distributionally robust optimization (DRO) version of two popular fine-tuning methods – (1) reward-based RLHF and (2) reward-free DPO (direct preference optimization). We propose a minibatch gradient descent based algorithms for both of them, and theoretically prove convergence guarantees for the algorithms. Subsequently, we evaluate our algorithms on an out-of-distribution (OOD) task by first training the model on the Unified-Feedback dataset and evaluating its performance on two different datasets. The experimental results show that our robust training improves the accuracy of the learned reward models on average, and markedly on some tasks, such as reasoning. Furthermore, we show that the robust versions of policy optimization methods, similarly improve performance on OOD tasks. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Data Resampling Techniques for Addressing Class Imbalance in Mosquito Classification

A Comparative Analysis of Data Resampling Techniques for Add...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Reshma Pise Abhishek Singh Chauhan Bharati Ainapure Aditya Shenolkar Leena Deshpande Shivraj Jadhav Computer Engineering Dept. Vishwakarma University Pune India CE (Software Engineering) Dept. Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Mosquitoes, as vectors of life-threatening diseases such as dengue, Zika, and West Nile virus, present a significant public health challenge. Precise and rapid identification of mosquito species is crucial for early detection and prevention of these diseases. Deep learning techniques have proven to be highly effective for automatic visual insect classification tasks. However, the imbalanced distribution of mosquito species within training datasets severely impacts the algorithm’s classification performance. This study investigates data sampling solutions for learning from imbalanced mosquito images dataset. We transfer-learn InceptionV3, a pre-trained convolutional neural network to classify images of two vector mosquito species Aedes Aegypti and Anopheles stephensi. The effectiveness of these data sampling solutions is evaluated and compared in terms of their impact on the performance of CNN classifier.

关键词： Training Visualization Technological innovation Accuracy Sensitivity Prevention and mitigation Vectors Convolutional neural networks Viruses (medical) Diseases

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：