检索结果-内蒙古大学图书馆

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Dey, Bishwajit Fose, Nande Krishnamurthy, Senthil Ratshitanga, Mukovhe Moodley, Prathaban Cape Peninsula University of Technology Centre for Intelligent Systems and Emerging Technologies Department of Electrical Electronics and Computer Engineering P.O. BOX 1906 Bellville7535 South Africa Upper Grayston Office Park Sandton2146 South Africa

ISBN: (纸本)9798331535162

By classifying loads into shiftable and non-shiftable groups and rearranging a distribution system's load demand model, demand-side management (DSM) reduces operating expenses. This is possible by shifting variable loads when utility costs per unit are lower. This work adopts a bi-level optimization technique to minimize the operational costs of a low-voltage microgrid (MG) system that incorporates plug-in hybrid electric vehicles (PHEVs), renewable energy sources, and fossil fuel generators while operating in grid-connected mode. According to the DSM participation level, the load model is reconfigured at the first optimization stage. Then, the restructured load demand models are considered, and recommendations for distributed generator scheduling are developed to reduce the production costs of the second-level microgrid system. The study's optimization technique used the popular differential evolution (DE) method applied to several power system optimization issues. When DSM, various grid participation and pricing schemes, and other factors were considered, the cost of producing active power was reduced. To ascertain their effect on the MG system's generation cost, scenarios involving different PHEV state of charge (SoC) levels and a taxable rate during V2G were also investigated. © 2025 IEEE.

关键词： Demand side management

来源：评论

学校读者我要写书评

暂无评论

Accelerating Deep Neural Networks with a Low-Cost Lossless Compression

Accelerating Deep Neural Networks with a Low-Cost Lossless C...

引用

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

作者： Kim, Seongwook Byeon, Gwangeun Lee, Seungeui Bae, Youngseok Hong, Seokin Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of Advanced R&D Center Hanwha Systems Co. Ltd. Korea Republic of Agency for Defense Development Emerging Science and Technology Directorate Korea Republic of

ISBN: (纸本)9798331510756

Since deep learning inference involves a significant amount of computations, there have been a lot of efforts to accelerate the inference process by eliminating ineffectual compu-tations. As a solution to this problem, several sparsity-aware deep learning accelerators have been proposed. These accelerators perform the inference on compressed data (filters and feature maps) and dynamically remove the ineffectual multiplications with zero operands. For efficiently handling the compressed data on the accelerators, a simple and effective compression scheme, which encodes the whole data with its nonzero values and their positions, is necessary. However, prior approaches have several shortcomings, such as low compression efficiency and high complexity in compression and decompression hardware. This paper proposes a low-cost compression scheme that can be applied to sparsity-aware deep-learning accelerators. The compression scheme synergistically combines two low-cost compression schemes: Zero-Value Compression (ZVC) and Base-Delta-Immediate Compression (BDI). Our experimental evaluation shows that the proposed compression scheme achieves an average compression ratio of 2.26, resulting in 2.33x performance improvement, © 2025 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Immoral post detection using a one-dimensional convolutional neural network-based LSTM network

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Saqia, Bibi Khan, Khairullah Rahman, Atta Ur Khan, Aurangzeb Jain, Deepak Kumar Department of Computer Science University of Science and Technology Bannu28100 Pakistan Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune India

In text mining and Natural Language Processing (NLP), extracting emotions from textual data is gaining rapid attraction. The proliferation of online content and the freedom of expression on social media platforms has compelled the advancement of more sophisticated methods for the automatic identification of unwanted content. The One-Dimensional Convolutional Neural Network (1D-CNN) performs best for feature extraction, while the Long Short-Term Memory Network (LSTM) is well-known for extracting sequential features and classification of textual data. This study proposes a novel solution by combining 1D-CNN with LSTM. Utilizing a context-aware model, this study aims to enhance the detection of immoral posts, including hate speech and other forms of immoral content on social media platforms. Various posts are extracted from social media, which are then processed using Glove word embedding models. It depicts the word representations in the text, which yields the form of a real-valued vector determining the words' meaning. The 1D convolution utilizes a filter window over the input time-series data to extract features. Relying on the acquired parameters of the filters, they act as feature extractors. This feature extraction technique allows the model to distinguish detailed patterns and nuances from the textual contents of posts. The sequential processing capabilities of the LSTM network enable an in-depth examination of the text, capturing temporal relationships and context, which is critical for successful content categorization. To validate the proposed model, we utilized a benchmark dataset, called the Twitter dataset. The proposed model achieved the highest accuracy of 95.37% and outperforms state-of-the-art works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Parameters Extraction of Photovoltaic Cell Using Particle Swarm Optimization 4th

Parameters Extraction of Photovoltaic Cell Using Particle Sw...

引用

4th International Conference on Electronic engineering and Renewable Energy systems, ICEERE 2024

作者： Chermite, Charaf Douiri, Moulay Rachid Elamri, Oumaymah Control and Computer Science for Intelligent Systems and Green Energy Department of Applied Physics Faculty of Science and Technology Cadi Ayyad University Marrakech Morocco LAMIGEP EMSI of Marrakech Systems and Applications Engineering Laboratory National School of Applied Sciences Cadi Ayyad University Marrakech Marrakesh Morocco

ISBN: (纸本)9789819799749

Extracting parameters accurately and effectively from solar photovoltaic (PV) models is crucial for detailed simulation, evaluation, and management of PV systems. Although there has been an increase in the development of analytical, numerical, and metaheuristic methods targeting this task, accurately determining these parameters continues to be a significant challenge. This study focuses on applying Particle Swarm Optimization (PSO) for the extraction of key parameters of RTC France solar cells, a critical step towards enhancing PV system efficiency and reliability. Additionally, the PSO's performance is evaluated against other metaheuristic algorithms including Enhanced Chaotic JAYA (CJAYA), Performance-Guided JAYA (PGJAYA), and Enhanced Gradient-Based Optimizer (EGBO), underscoring the effectiveness of the proposed PSO-based approach. Utilizing MATLAB-SIMULINK, comprehensive analysis and results are presented, shedding light on the efficacy of PSO in addressing the intricacies of parameter extraction in PV systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Impact of an electric vehicle, solar PV, and battery energy storage system in a distribution system 33

Impact of an electric vehicle, solar PV, and battery energy ...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Gbadamosi, Saheed Lekan Emmanuel Okafor, Chukwuemeka Krishnamurthy, Senthil Ratshitanga, Mukovhe Moodley, Prathaban Cape Peninsula University of Technology Centre for Intelligent Systems and Emerging Technologies Department of Electrical Electronics and Computer Engineering P.O. BOX 1906 Bellville7535 South Africa Upper Grayston Office Park Sandton2146 South Africa

ISBN: (纸本)9798331535162

The modern distribution power system has witnessed a tremendous increase in integrating renewable energy sources (wind and solar photovoltaic), electric vehicles, and battery energy storage systems. This is consequent upon the commitment of many countries (around the world) to reduce global carbon emissions and ensure an acceptable global temperature increase. This research focuses on the impacts of the integration of solar photovoltaic (PV) systems, electric vehicles (EVs), and battery energy storage systems (BESS) on the distribution system while minimizing the voltage deviations and power losses of the considered distribution network. Through a time-based Power System Simulation tool, the study evaluates four configurations to assess the technical impacts on the distribution network. The Simulation results showed that electric vehicle integration leads to increased power losses and a reduction in voltage deviations. Integrating battery energy storage systems into the distribution system increases the power losses (from 0.9222 MW to 1.602 MW) depending on the location of the battery energy storage system in the distribution network. Therefore, the study reveals the need for optimal sizing and placement of battery energy storage systems in the distribution network for optimal system performance. © 2025 IEEE.

关键词： battery energy storage Electric vehicle power loss solar PV voltage deviation

来源：评论

学校读者我要写书评

暂无评论

Outage Probability of Reconfigurable Intelligent Surface Assisted NOMA Cooperative System over Mixed FSO/RF Links

Outage Probability of Reconfigurable Intelligent Surface Ass...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Kehinde O. Odeyemi Pius A. Owolawi Department of Electrical and Electronic Engineering University of Ibadan Ibadan Nigeria Department of Computer Systems Engineering Tshwane University of Technology Pretoria South Africa

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

In this paper, a non-orthogonal multiple access (NOMA) dual-hop free space optical (FSO)/radio frequency (RF) relaying communication system is presented where reconfigurable intelligent surface (RIS) with phase error and hybrid automatic repeat request (H-ARQ) protocols are considered on the RF link. The FSO link is subjected to Gamma-Gamma distributions with pointing errors while the RF link follows Nakagamim distributions. To quantify the system performance, the exact outage probability expressions for the near and far users are obtained. Under the same conditions, the results reveal the superiority of NOMA over orthogonal multiple access (OMA) and the accuracy of the results are validated via the Monte-Carlo simulations.

关键词： Radio frequency NOMA Protocols Free-space optical communication Monte Carlo methods System performance Cooperative systems Reconfigurable intelligent surfaces Probability Power system reliability

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Modeling and Investigation of Intrinsic Variation Source Fluctuation in 2D-Layered Thin Film Transistors

Comprehensive Modeling and Investigation of Intrinsic Variat...

引用

Annual International Symposium on Reliability Physics

作者： Tao Du Wei Zhang Xuanyao Fong Guangxi Hu Peng Zhou Ye Lu State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China Department of Electrical and Computer Engineering National University of Singapore (NUS) Singapore Singapore

ISBN: (数字)9798331504779

ISBN: (纸本)9798331504786

In this work, a Voronoi-TCAD co-simulation framework is developed to investigate the impact of intrinsic and extrinsic variation sources on the performance and variability of 2D-layered TFTs. It is found that : i) High trap density exacerbates device variability by amplifying localized energy barriers and enhancing barrier interference; ii) The device variability reaches peak value for intermediate numbers of grains, while increased numbers of grains reduce overall variability due to statistical averaging effects, highlighting the importance of considering both the quantity of grain boundaries and their spatial distribution as key variability sources; iii) interlayer interactions in multilayer structures further exaggerate the device variability, particularly for the on-current. This demands precise control of grain alignment and distribution. These findings emphasize the importance of grain engineering strategies, such as optimizing grain size, reducing defect density, and improving interlayer uniformity, to suppress variability and enhance device performance in large-scale 2D-layered TFT applications.

关键词： Performance evaluation Grain size Grain boundaries Graphical models Fluctuations Interference Reliability engineering Nonhomogeneous media Thin film transistors Physics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Federated Transfer Learning Approach for Multi-UAV systems

An Efficient Federated Transfer Learning Approach for Multi-...

引用

National Conference on Communications (NCC)

作者： Vedang Bhupesh Shenvi Nadkarni Sandeep Joshi L. Rajya Lakshmi Department of Computer Science and Information Systems Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Pilani Rajasthan India

ISBN: (数字)9798331536015

ISBN: (纸本)9798331536022

Recent advances in multi-unmanned aerial vehicle (UAV) based federated learning do not take into consideration the massive computational requirements of modern deep learning models on mobile UAV s. Additionally, there has been significant progress that shows that the information transmitted between the federated agent and the central hub can be attacked to undermine the privacy of the data. We propose a novel multi-UAV-based federated transfer learning system that drastically reduces the computational burden overall, shifts it from UAV s to the ground fusion center, and reduces the bandwidth requirements while enhancing its secure nature. The proposed system makes multi-UAV learning significantly fast, reliable, power efficient, and practically feasible. Furthermore, we provide simulation and experimental results to demonstrate the effectiveness of the proposed system.

关键词： Deep learning Image segmentation Data privacy Federated learning Power supplies Transfer learning Object detection Autonomous aerial vehicles Data models Reliability

来源：评论

学校读者我要写书评

暂无评论

Sensitivity of DC Network Representation for GIC Analysis

Sensitivity of DC Network Representation for GIC Analysis

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Aniruddh Mishra Arthur K. Barnes Jose E. Tabarez Adam Mate Department of Electrical and Computer Engineering University of Texas at Austin Austin TX Information Systems and Modeling Group Los Alamos National Laboratory Los Alamos NM

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

Geomagnetic disturbances are a threat to the reliability and security of our national critical energy infrastructures. These events specifically result in geomagnetically induced currents, which can cause damage to transformers due to magnetic saturation. In order to mitigate these effects, blocker devices must be placed in optimal locations. Finding this placement requires a dc representation of the ac transmission lines, which this paper discusses. Different decisions in this process, including the method of representing the blocking devices, result in significant variations to the power loss calculations. To analyze these effects, we conclude the paper by comparing the losses on a sample network with different modeling implementations.

关键词： Analytical models Sensitivity Substations Power transmission lines Windings Circuit faults Security Reliability Electric fields Saturation magnetization

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：