检索结果-内蒙古大学图书馆

Reduced-RSS: Reduced Residual Search Space for Nash Bargaining Solutions

IEEE Transactions on Vehicular Technology 2025年

作者： Cha, Chaeyeon Park, Hyunggon Ewha Womans University Graduate Program in Smart Factory Department of Electronic and Electrical Engineering Seoul03760 Korea Republic of

A fair and efficient resource allocation is crucial to maximize the efficiency of vehicular networks with time-varying resources among dynamically changing vehicles. The Nash Bargaining Solution (NBS) from the cooperative game theory has been one of the fair and optimal resource management solutions for multiple users. However, the computational complexity required to find the NBS for general utility functions exponentially increases either as the number of users increases or as the resources change over time. This is because the size of bargaining sets where the NBS should be found changes. In this paper, we propose an algorithm to reduce the size of the search spaces by considering the adjacent bargaining sets correlated by resource changes. We use the axiom of independence of linear transformations in NBS for the linear approximation of NBS in the adjacent bargaining sets based on its linear transform, leading to reduced residual search space. Moreover, we prove that the NBS is always included in the reduced residual search space based on the axiom of independence of irrelevant alternatives in NBS. Through simulations and experiments on synthetic and real traffic data, we demonstrate that the complexity of existing algorithms for NBS is lowered with the reduced residual search spaces. © 1967-2012 IEEE.

关键词： concave function Nash Bargaining Solution (NBS) residual search space resource allocation

来源：评论

学校读者我要写书评

暂无评论

Degradation of Organic LEDs Characterized with Algebraic Decay Relaxation Function

Degradation of Organic LEDs Characterized with Algebraic Dec...

引用

Advances in Display Technologies XV 2025

作者： Aygen, Can Richards, Michael Yazdaanpanah, Ramin Kulkarni, Sachin Tanriover, Ibrahim Onsager, Claire Lin, BoYen Lee, Jiun-Haw Aydin, Koray Grayson, Matthew A. Department of Electrical & Computer Engineering Northwestern University EvanstonIL United States Department of Opto-Electronic Engineering National Dong Hwa University Hualien Taiwan Graduate Institute of Photonics and Optoelectronics Department of Electrical Engineering National Taiwan University Taipei Taiwan Program in Applied Physics Northwestern University EvanstonIL United States

ISBN: (纸本)9781510685246

Lifetime studies of organic light emitting diodes are necessary to both understand and mitigate causes of degradation. Here, electroluminescence (EL) studies of green organic light-emitting diode (OLED) pixels are measured continuously using three different dc currents over a period of one week, and their slow EL degradation is accurately fit to an analytical expression with only two fit parameters. The slower-than-exponential EL decay is fit to an empirical unified heavy-tail function that can interpolate between power-law algebraic decays (AD) and stretched-exponential decays (SE). Whereas SE and AD are largely indistinguishable down to 50% of the initial luminance, here we report degradation down to 10% of the initial luminance which most closely fits an AD function with remarkable precision over the entire duration of the experiment. All relaxations share the same characteristic exponent β = 0.53 in the power law decay, whereas the characteristic time-scale τ for degradation decreases with a power-law exponent B = 1.9 as the current increases. The high degree of accuracy in the fit allows asymptotic predictions at time scales that are orders of magnitude longer than the duration of the data collection. The voltage across the OLED is simultaneously monitored under constant-current degradation and reveals an early-onset time scale where the voltage reaches a minimum before degradation runoff. © 2025 SPIE.

关键词： Organic light emitting diodes (OLED)

来源：评论

学校读者我要写书评

暂无评论

CNN-based multiplexed optical fiber sensors for multi-load mapping on 2D structures

引用

Optical Fiber Technology 2025年 93卷

作者： de Carvalho, Vinicius Martins, Victor Hugo Flores, Walter Oswaldo C. Muller, Marcia Fabris, José Luís Lazzaretti, André Eugenio UTFPR Graduate Program in Electrical and Computer Engineering Av. Sete de Setembro 3165 Paraná Curitiba80230-901 Brazil

This paper reports the application of a Convolutional Neural Network specifically designed for one-dimensional optical signal processing to determine the magnitude and position of loads acting on a structure instrumented with multiplexed macrobend optical fiber sensors, offering a cost-effective and low complexity alternative for force monitoring solutions. The system effectively localized and quantified one, two, or three simultaneous loads within 16 distinct sensing areas, utilizing only five in-series optical fiber sensors, which were spectrally interrogated in transmission mode. The monitored loads ranged from 1000 to 2000 gf. The use of the Huber loss function allows the model to adaptively predict values associated with regions with or without loads. Experimental results showed an average mean absolute error of 224±65 gf during testing. By applying a straightforward post-processing method for load presence detection in each region, the system achieved average F1 scores ranging from 0.84 to 0.93 across the monitored regions, and an average Hamming score of 0.93. These findings demonstrate the system's effectiveness in monitoring multiple loads, underscoring the potential of optical fiber sensors and CNNs in sensing applications. © 2025 Elsevier Inc.

关键词： Convolutional neural network Load mapping Macrobend sensor Optical fiber sensor

来源：评论

学校读者我要写书评

暂无评论

SNeRV: Spectra-preserving Neural Representation for Video

arXiv

引用

arXiv 2025年

作者： Kim, Jina Lee, Jihoo Kang, Je-Won Department of Electronic and Electrical Engineering Graduate Program in Smart Factory Ewha Womans University Seoul Korea Republic of

Neural representation for video (NeRV), which employs a neural network to parameterize video signals, introduces a novel methodology in video representations. However, existing NeRV-based methods have difficulty in capturing fine spatial details and motion patterns due to spectral bias, in which a neural network learns high-frequency (HF) components at a slower rate than low-frequency (LF) components. In this paper, we propose spectra-preserving NeRV (SNeRV) as a novel approach to enhance implicit video representations by efficiently handling various frequency components. SNeRV uses 2D discrete wavelet transform (DWT) to decompose video into LF and HF features, preserving spatial structures and directly addressing the spectral bias issue. To balance the compactness, we encode only the LF components, while HF components that include fine textures are generated by a decoder. Specialized modules, including a multi-resolution fusion unit (MFU) and a high-frequency restorer (HFR), are integrated into a backbone to facilitate the representation. Furthermore, we extend SNeRV to effectively capture temporal correlations between adjacent video frames, by casting the extension as additional frequency decomposition to a temporal domain. This approach allows us to embed spatio-temporal LF features into the network, using temporally extended up-sampling blocks (TUBs). Experimental results demonstrate that SNeRV outperforms existing NeRV models in capturing fine details and achieves enhanced reconstruction, making it a promising approach in the field of implicit video representations. The codes are available at https://***/qwertja/SNeRV. Copyright © 2025, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

Vision-Based Landing Guidance Through Tracking and Orientati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： João P. K. Ferreira João P. Pinto Júlia Moura Yi Li Cristiano L. Castro Plamen Angelov Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais School of Computing and Communications Lancaster University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Fixed-wing aerial vehicles are equipped with functional-ities such as ILS (instrument landing system), PAR (precision approach radar) and, DGPS (differential global positioning system), enabling fully automated landings. How-ever, these systems impose significant costs on airport op-erations due to high installation and maintenance requirements. Moreover, since these navigation parameters come from ground or satellite signals, they are vulnerable to in-terference. A more cost-effective and independent alternative for guiding landing is a vision-based system that de-tects the runway and aligns the aircraft, reducing the pi-lot's cognitive load. This paper proposes a novel frame-work that addresses three key challenges in developing au-tonomous vision-based landing systems. Firstly, to over-come the lack of aerial front-view video data, we created high-quality videos simulating landing approaches through the generator code available in the LARD (landing approach runway detection dataset) repository. Secondly, in contrast to former studies focusing on object detection for finding the runway, we chose the state-of-the-art model Lo-RAT to track runways within bounding boxes in each video frame. Thirdly, to align the aircraft with the designated landing runway, we extract runway keypoints from the re-sulting LoRAT frames and estimate the camera relative pose via the Perspective-n-Point algorithm. Our experimental re-sults over a dataset of generated videos and original images from the LARD dataset consistently demonstrate the proposed framework's highly accurate tracking and alignment capabilities. Our approach source code and the Lo-RAT model pre-trained with LARD videos are available at https://***/jpklock2/vision-based-landing-guidance

关键词： Visualization Codes Accuracy Atmospheric modeling Pose estimation Video sequences Radar tracking Generators Aircraft navigation Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Evaluation of Convolutional Neural Network Architectures for Thermal Image Classification of Solar Modules

Transfer Learning Evaluation of Convolutional Neural Network...

引用

International electrical engineering Congress (iEECON)

作者： Chutinun Phungket Prasit Nangtin The Graduate Program Faculty of Engineering Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand Department of Electrical Engineering Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

Accurate anomaly classification in solar modules is crucial for efficient solar power system monitoring and maintenance. This study explores deep learning, specifically Convolutional Neural Networks (CNNs), for automated defect classification in thermal images. We employed transfer learning with pre-trained AlexNet and GoogleNet architectures, comparing static feature extraction and fine-tuning. Using a dataset of thermal images categorized as no anomaly, cracked, or soiled modules, the fully fine-tuned GoogleNet model achieved the highest classification accuracy 95.5%, outperforming AlexNet and traditional feature-based methods. GoogleNet's superior performance stems from its Inception modules, which learn more discriminative features by employing multiple convolutional filter sizes within the same layer, capturing complex thermal image patterns. Fine-tuning further boosts performance by adapting pre-trained knowledge to the specific task. These results demonstrate deep learning's potential for enhancing solar system maintenance reliability and efficiency.

关键词： Deep learning Adaptation models Accuracy Transfer learning Solar energy Feature extraction Maintenance Solar panels Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Multiplexing B5G/6G Services Over Aerial VLC Networks: A Comprehensive Radio Resource Management Framework

引用

IEEE Internet of Things Journal 2025年第9期12卷 11600-11621页

作者： Zarini, Hosein Gholipoor, Narges Mili, Mohammad Robat Rasti, Mehdi Movaghar, Ali Choi, Jinho Chae, Chan-Byoung Sharif University of Technology Department of Computer Engineering Tehran11365-8639 Iran University of Oulu Center for Wireless Communications Oulu90570 Finland Pasargad Institute for Advanced Innovative Solutions Tehran1111111 Iran The University of Adelaide School of Electrical and Mechanical Engineering North Terrace AdelaideSA5005 Australia Yonsei University School of Integrated Technology BK21 Graduate Program in Intelligent Semiconductor Technology Seoul03722 Korea Republic of

Downlink transmission of a nonorthogonal visible light communication (VLC) system, empowered by autonomous aerial vehicles (AAVs), is studied for coexisting enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and massive machine-type communication (mMTC) services. A joint resource allocation problem involving user association, transmit power, and flight trajectory of AAVs is formulated, with the goal of characterizing a multiobjective tradeoff as a weighted sum of the power consumption of each AAV and the perceived Quality of Experience (QoE) of its associated eMBB users, while ensuring the service-specific requirements for eMBB, mMTC, and URLLC are met. Assuming the imperfection of channel state information (CSI), we invoke a generalized Benders decomposition (GBD) methodology, leveraging tools from convex optimization and multiagent deep reinforcement learning to address this problem. We further analytically derive the upper and lower bounds on the reward function for each AAV as a learning agent. Extensive simulations confirm that our proposed method outperforms the single-agent counterpart in the literature, with up to a 22% reduction in power consumption and a 13% gain in perceived QoE. Additionally, compared to the globally optimal brute-force method for AAV-user association, our proposed method experiences only a trivial performance loss in a small-scale scenario. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Impact of Latency and Packet Error on Communication in Centralized Microgrid Control: Modeling and Guidelines

引用

IEEE Access 2025年 13卷 82732-82746页

作者： Chaves, Lucas S. Callegari, Joao Marcus S. Araujo, Lucas S. Brandao, Danilo I. Universidade Federal de Minas Gerais Graduate Program in Electrical Engineering Av. Antônio Carlos 6627 Belo Horizonte 31270-901 Brazil Department of Electrical Engineering Federal Center for Technological Education of Minas Gerais Nepomuceno Brazil

This paper proposes a novel dynamic model in the Laplace domain for an advanced ac microgrid with centralized secondary control. The model applies a centralized power-based control strategy and incorporates communication non-idealities such as latency and packet error. Packet loss and communication failure are considered herein as latency issues. The central controller incorporates an anti-aliasing filter that constrains the frequency of the transmitted signal and the packet transmission rate in compliance with Nyquist’s sampling theorem. The model is validated on a test bench, with experimental implementation of the communication system and central controller, and a real-time simulation of the electrical power system via hardware-in-the-loop. The impact of latency on the controller’s performance is evaluated through stability, control bandwidth, load rejection bandwidth, settling time, and rejection of packet errors. The results show that communication latency directly impacts the controller’s performance, affecting all analyzed performance metrics. Meanwhile, the cutoff frequency of anti-aliasing filter and packet transmission rate influence control stability, response dynamics, and the system ability to reject load variations and packet errors. Finally, the paper proposes a flowchart-based guideline for configuring the microgrid central controller and selecting communication technologies to implement ancillary services with predefined durations in advanced microgrids. © 2013 IEEE.

关键词： Centralized control communication latency microgrids packet loss stability

来源：评论

学校读者我要写书评

暂无评论

The Impact of High Penetration of Renewable Energy Generation to Locational Marginal Price and Security of Supply: Case Study at Mae Hong Son City Thailand

The Impact of High Penetration of Renewable Energy Generatio...

引用

Power, Energy and electrical engineering (CPEEE), International Conference on

作者： Patompong Boonsiri Suttichai Premrudeeprechacharn Paramet Wirasanti Watcharin Srirattanawichaikul Dept. of Electrical Engineering Faculty of Engineering Graduate Program in Electrical Engineering Chiang Mai University Chiang Mai Thailand Provincial Electricity Authority Bangkok Thailand Dept. of Electrical Engineering Faculty of Engineering Chiang Mai University Chiang Mai Thailand

ISBN: (数字)9798331520090

ISBN: (纸本)9798331520106

As the dramatically increasing power supply of renewable energy (RE) generation penetrates the distribution network, the security of the supply of the network, such as voltage level, is affected by the uncertain power output. The unstable voltage is caused by the tap of the distribution transformer, which is usually a fixed tap. In addition, the locational marginal price (LMP) depends on the number of power supplies from RE generation. The LMP of the whole local system is not lower, although the selling price of RE generation is lower than that of others, which results from the oversupply of RE generation to the network. The Provincial Electricity Authority (PEA) distribution network in Mae Hon Son City is also affected by the high penetration of renewable energy generation (RE generation). Currently, the proportion of power supply from RE generation is approximately 38% (in May) and 143% (in October) of total power supply to the load. During an oversupply of RE generation, the excess power reverses to PEA transmission network at approximately 8.79 MWh, which results in the security of supply and cost efficiency of distribution network companies such as PEA. The locational marginal price (LMP) in case of high penetration of RE generation is, however, slightly the same price as the non-penetration of RE generation under the Thailand electricity market condition. Therefore, the local generation management and dispatching are consequently considered for local power supply and demand balancing, maintaining the security of supply and reducing power losses and locational marginal price.

关键词： Renewable energy sources Costs Substations Power supplies Electricity Urban areas Distribution networks Companies Voltage Security

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Real-Time PPE Usage Monitoring Using Wearable IMU Sensors

引用

IEEE Access 2025年 13卷 82492-82502页

作者： Guimarães, Pedro Carvalho da Fonseca De Cristo, Leonardo Braga Monteiro, Marcos Eduardo Pivaro Rebelatto, João Luiz Peron, Guilherme de Santi Rayel, Ohara Kerusauskas Moritz, Guilherme Luiz Federal University of Technology - Paraná (UTFPR) Curitiba Brazil Federal University of Technology - Paraná (UTFPR) Graduate Program in Electrical and Computer Engineering (CPGEI-CT) Curitiba Brazil Federal University of Technology - Paraná (UTFPR) Graduate Program in Energy Systems (PPGSE-CT) Curitiba Brazil

Ensuring the proper use of Personal Protective Equipment (PPE) is critical for safeguarding workers in high-risk environments, such as power distribution systems. This work presents an innovative approach to monitoring PPE usage through Deep Neural Networks (DNNs). Using data from inertial measurement units (IMUs) integrated into PPE items, we propose a solution to classify three usage states—namely carrying, still, and wearing—using raw accelerometer and gyroscope data. More specifically, thiswork assesses the effectiveness of three distinct network architectures—Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and CNN-BiLSTM—on a publicly released dataset on PPE usage provided by this study, while also comparing them against a traditional baseline Multi- Layer Perceptron (MLP) architecture. Our results demonstrate the superiority of BiLSTM in balancing high accuracy with computational efficiency, achieving above 98% accuracy regardless of the PPE type. Thiswork represents the first application of DNNs for PPE monitoring using IMU data, offering significant implications for enhancing safety compliance and operational monitoring in power distribution. © 2013 IEEE.

关键词： AI BiLSTM CNN DNN IoT PPE

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：