检索结果-内蒙古大学图书馆

Energy Efficient Behavior Modelling for Demand Side Recommender System in Solar Microgrid Applications Using Multi Agent Reinforcement Learning Model

SSRN

引用

SSRN 2022年

作者： Onile, Abiodun Emmanuel Belikov, Juri Levron, Yoash Petlenkov, Eduard Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia The Andrew and Erna Viterbi Faculty of Electrical Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Computer Systems Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia

Electricity consumers are often faced with challenges relating the choice of optimal energy saving plan, increasing integration of transient’s renewable sources of energy promises tantalizing solution which also constitutes emerging stability challenges for the electricity Grid. Demand side management using Battery storage as grid balancing measures are crucial towards extending physical limits of existing electricity grid. On the one hand, battery storage is assuming a critical role in decarbonization efforts partly due to its tendencies to store excess electricity obtained via renewable energy sources thus enabling unlimited potentials for seasonal storage. On the other hand, while solving the identified problem, other problems relating consumer behavior towards adoption of energy/battery efficiency technologies, consumers comfort-feedback and control loop integration exist. In this study, we presented electricity energy storage (EES) technologies which are embedded into the grid and further enhanced with the use of Reinforcement learning control and recommendation system technologies for improving the grid management, the grid reliability and sustainability, mitigated operational issues, improved BESS utilization and attain self-consumption goals. The result of the study shows that operating the BESS using the multi-agent RL control strategy achieved a maximum peak load reduction of about 24.5% alongside 94% comfort improvements in certain loads. © 2022, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Unified resilience model using deep learning for assessing power system performance

引用

Heliyon 2025年第4期11卷 e42802页

作者： Artemchuk, Volodymyr Garbuz, Iurii Jamil Alsayaydeh, Jamil Abedalrahim Shkarupylo, Vadym Oliinyk, Andrii Bin Yusof, Mohd Faizal Herawan, Safarudin Gazali Department of Mathematical and Econometric Modelling G.E. Pukhov Institute for Modelling in Energy Engineering of the NAS of Ukraine Kyiv Ukraine Department of Environmental Protection Technologies and Radiation Safety Center for Information-analytical and Technical Support of Nuclear Power Facilities Monitoring of the NAS of Ukraine Kyiv Ukraine Department of Іnformation Systems in Economics Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Department of Computerized Control System National Aviation University Kyiv Ukraine Department of Engineering Technology Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK) Universiti Teknikal Malaysia Melaka (UTeM) Melaka 76100 Malaysia Department of Computer Systems Networks and Cybersecurity of the National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Department of Software Tools Faculty of Computer Science and Technology Zaporizhzhia Polytechnic National University Zaporizhzhia Ukraine Research Section Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia

Energy resilience in renewable energy sources dissemination components such as batteries and inverters is crucial for achieving high operational fidelity. Resilience factors play a vital role in determining the performance of power systems, regardless of their operating environment and interruptions. This article introduces a Unified Resilience Model (URM) using Deep Learning (DL) to enhance power system performance. The proposed model analyzes environmental factors impacting the resilience of batteries and energy storage devices. This deep learning approach trains performance-impacting factors using previously known low resilience drain data. The learning output is utilized to augment various strengthening factors, thereby improving resilience. Drain mitigation and performance improvements are combined for direct impact verification. This process validates the model's fidelity in enhancing power system performance, with a specific focus on the impact of weather factors. © 2025 The Authors

关键词： Deep learning Energy resilience Fidelity Weather impact

来源：评论

学校读者我要写书评

暂无评论

BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhou, Tong Ding, Chen Jing, Changhong Liu, Feng Hung, Kevin Pham, Hieu Mahmud, Mufti Lyu, Zhihan Qiao, Sibo Wang, Shuqiang Tsang, Kim-Fung Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100864 China Stevens Institute of Technology Department of Systems and Enterprises United States Hong Kong Metropolitan University School of Science and Technology Hong Kong Hong Kong VinUniversity College of Engineering and Computer Science VinUni-Illinois Smart Health Center Viet Nam King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Uppsala University Department of Game Design Faculty of Arts Sweden Tiangong University School of Software Tianjin300387 China

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pl-Densenet: Enhancing Disease Classification in Pear Leaves Using Deep Learning

SSRN

引用

SSRN 2023年

作者： Gulzar, Yonis Ünal, Zeynep Ayoub, Shahnawaz Wani, Sharyar Mir, Mohammad Shuaib Soomro, Arjumand Bano Department of Management Information Systems College of Business Administration King Faisal University Al-Ahsa31982 Saudi Arabia Department of Biosystem Engineering Niğde Ömer Halisdemir University Central Campus Türkiye Niğde51240 Turkey Mirzapur Pole U.P. Saharanpur247121 India Department of Computer Science Kulliyyah of Information and Communication Technology International Islamic University Malaysia Kuala Lumpur53100 Malaysia Department of Software Engineering Faculty of Engineering and Technology University of Sindh Sindh Pakistan

Over the past two decades, climate changes have negatively impacted agriculture. It hasn’t left any stage of production unaffected. These noticeable changes have left formers no choice but to adopt new technological measures to tackle such changes. Deep learning has played a great role in improving decision-making in agriculture. This research introduces a novel deep learning model, PL-DenseNet, designed to accurately identify various disease types present in pear leaves. The PL-DenseNet model is an adaptation of the original DenseNet architecture, incorporating significant modifications to enhance its disease classification capabilities. The modifications involve replacing the classification layer of the DenseNet with three additional layers: Global Average Pooling 2D, Batch Normalization, and Dropout layers. Moreover, the final layer of the PL-DenseNet model comprises four nodes dedicated to classifying pear leaf diseases. The integration of these modifications aims to improve disease identification accuracy and enhance overall classification performance within the context of pear leaf diseases. The PL-DenseNet model also incorporated transfer learning and data augmentation to increase the variety and quantity of training data. The model's performance was evaluated on the DiaMOS Plant dataset, which comprises four different pear leaf diseases under real field conditions with varying brightness, disease similarity, complex background, and multiple leaves. Experimental evaluation reveals that the proposed PL-DenseNet model achieves notable advancements compared to the baseline model. It demonstrates higher accuracy (99.18%), precision (98.83), recall (99.06), and F1-score (93.58). Additionally, the proposed model surpasses other state-of-the-art models, including EfficientNetB0, InceptionV2, MobileNetV2, ResNet50, and VGG16, underscoring its superior performance in disease classification. Moreover, this research demonstrates how transfer learning and data augmentati

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Quantum-optimal Frequency Estimation of Stochastic AC Fields

arXiv

引用

arXiv 2024年

作者： Dey, Anirban Mouradian, Sara Lupo, Cosmo Huang, Zixin School of Mathematical and Physical Sciences Macquarie University NSW2109 Australia ARC Centre of Excellence for Engineered Quantum Systems Macquarie University NSW2109 Australia Department of Electrical and Computer Engineering University of Washington 98195 United States Dipartimento Interateneo di Fisica Politecnico di Bari Bari70126 Italy Dipartimento Interateneo di Fisica Università di Bari Bari70126 Italy INFN Sezione di Bari Bari70126 Italy Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia

Classically, measurement bandwidth limits the achievable frequency resolution of stochastic time-dependent fields. We frame the problem of frequency measurement as the estimation of the noise parameter of a dephasing quantum channel. Using this framework, we find an exact upper bound for estimating frequency centroids and separations. In particular, given two closely separated frequencies with separation ωr, the quantum Fisher information (QFI) upper bound is approximately 2/ωr2, inversely proportional to the separation parameter. We show that this is achievable with a superposition of Dicke states, and show that GHZ states improve precision over unentangled states, achieving Heisenberg scaling in the low-bandwidth limit. This work established a robust framework for stochastic AC signal sensing and can be extended to an arbitrary number of frequencies. Copyright © 2024, The Authors. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Short-time simulation of quantum dynamics by Pauli measurements

arXiv

引用

arXiv 2024年

作者： Faehrmann, Paul K. Eisert, Jens Kieferová, Mária Kueng, Richard Dahlem Center for Complex Quantum Systems Freie Universität Berlin Berlin14195 Germany Institute for Integrated Circuits and Quantum Computing Johannes Kepler University Linz Austria Helmholtz-Zentrum Berlin für Materialien und Energie Hahn-Meitner-Platz 1 Berlin14109 Germany Fraunhofer Heinrich Hertz Institute Berlin10587 Germany Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology SydneyNSW2007 Australia

Simulating the dynamics of complex quantum systems is a central application of quantum devices. Here, we propose leveraging the power of measurements to simulate short-time quantum dynamics of physically prepared quantum states in classical post-processing using a truncated Taylor series approach. While limited to short simulation times, our hybrid quantum-classical method is equipped with rigorous error bounds. It is extendable to estimate low-order Taylor approximations of smooth, time-dependent functions of tractable linear combinations of measurable operators. These insights can be made use of in the context of Hamiltonian learning and device verification, short-time imaginary time evolution, or the application of intractable operations to sub-universal quantum simulators in classical post-processing. © 2024, CC BY.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

FeSiCr添加对羰基铁磁粉心磁性能与温度稳定性的影响

引用

磁性材料及器件 2024年

作者：王雨孙小龙杨陆董鑫武文杰陈劲松邬传健曾涛李子鸣西南应用磁学研究所四川省磁性材料工程技术研究中心电子科技大学材料与能源学院 Faculty of Software Engineering and Computer Systems， ITMO University

以羰基铁粉为基体添加不同比例的FeSiCr软磁粉末，添加固定比例的酚醛树脂进行有机绝缘包覆，然后将其制备成羰基铁/FeSiCr复合磁粉心材料。研究了FeSiCr粉末添加量对磁粉心材料微观形貌、致密性、技术磁化性能、高频软磁性能以及磁导... 详细信息

以羰基铁粉为基体添加不同比例的FeSiCr软磁粉末，添加固定比例的酚醛树脂进行有机绝缘包覆，然后将其制备成羰基铁/FeSiCr复合磁粉心材料。研究了FeSiCr粉末添加量对磁粉心材料微观形貌、致密性、技术磁化性能、高频软磁性能以及磁导率温度稳定性等性能的影响。结果表明，羰基铁/FeSiCr复合磁粉心的密度、比饱和磁化强度和磁导率温度系数随着FeSiCr粉末添加添加量提升发生了显著改善，而高频磁导率、矫顽力以及Q值未随FeSiCr粉末添加得到优化。当FeSiCr为25%时，羰基铁/FeSiCr复合磁粉心综合性能最优，此时复合磁粉心磁导率为12.5(@1 MHz)、比饱和磁化强度为196.17 emu/g、Q最大值为176.64(@3 MHz)以及磁导率温度系数为72.95 ppm/℃。

关键词：羰基铁粉 FeSiCr粉添加复合磁粉心高频软磁性能磁导率温度系数

来源：评论

学校读者我要写书评

暂无评论

Designing planar cubic B-spline curves with monotonic curvature for curve interpolation

引用

Computational Visual Media 2020年第3期6卷 349-354页

作者： Aizeng Wang Chuan He Fei Hou Zhanchuan Cai Gang Zhao School of Mechanical Engineering&Automation Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology&Systems Beihang UniversityBeijing 100191China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

Monotonic curvature plays an important role in industrial design and styling of curves with aesthetic shapes,e.g.,in automobile and aircraft design[1].Used in conventional parametric CAD/CAM systems,general B-splines are not adequate for aesthetic *** for the straight line and circle,monotonic curvature distribution,associated with pleasing shape,is very difficult to achieve.

关键词： curvature monotonic curves

来源：评论

学校读者我要写书评

暂无评论

Image-to-Image Translation Based Face Photo De-Meshing Using Gans

SSRN

引用

SSRN 2023年

作者： Jabbar, Abdul Assam, Muhammad Shloul, Tamara Al Hameed, Hala Abdel Al-Kahtani, Noor Alkahtani, Hend Khalid Ghamry, Nivin A. Tag El Din Bro, Wahii Elsayed M. Amin, Muhammad Shoib College of Computer Science and Technology Zhejiang University Hangzhou310027 China School of Software Engineering East China Normal University Shanghai200050 China Liwa College of Technology College of Business administration United Arab Emirates Khaybar Applied College Taibah University Saudi Arabia Department of Health Information Management and Technology College of Public Health Imam Abdulrahman Bin Faisal University Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia Faculty of Computers and Artificial intelligence Cairo University Giza Egypt Faculty of Engineering and Technology Future University New Cairo11835 Egypt

Most of the existing face photo de-meshing methods have accomplished promising results;there are certain quality problems with these methods like the inpainted regions would appear blurry and unpleasant boundaries becoming visible. Such artifacts cause generated face photos unreal. Therefore, we propose an effective image-to-image translation framework called Face De-meshing Using Generative Adversarial Networks (De-mesh GANs). The De-mesh GANs is a two-stage model: (i) binary mask generating module, is a three convolution layers-based encoder-decoder network architecture that automatically generates a binary mask for the meshed region, and (ii) face photo de-meshing module, is a GANs-based network that eliminates the mesh mask and synthesizes the meshed area. An arrangement of careful losses (reconstruction loss, adversarial loss, and perceptual loss) is used to reassure the better quality of the de-mesh face photos. To facilitate the training of the proposed model, we have designed a dataset of clean/corrupted photo pairs using the CelebA dataset. Qualitative and quantitative evaluations of the De-mesh GANs on real-world corrupted face photo images show better performance than the previously proposed face photo de-meshing models. Furthermore, we also offer the ablation study for performance assessment of the additional network i.e., perceptual network. © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SS-SFR: Synthetic Scenes Spatial Frequency Response on Virtual KITTI and Degraded Automotive Simulations for Object Detection

arXiv

引用

arXiv 2024年

作者： Jakab, Daniel Braun, Alexander Agnew, Cathaoir Mohandas, Reenu Deegan, Brian Michael Molloy, Dara Ward, Enda Scanlan, Anthony Eising, Ciarán Dept. of Electronic and Computer Engineering University of Limerick Co. Limerick CastletroyV94 T9PX Ireland Faculty of Electrical Engineering & Information Technology University of Applied Sciences Düsseldorf40476 Germany Dept. of Electrical and Electronic Engineering University of Galway GalwayH91 TK33 Ireland Valeo Vision Systems Tuam GalwayDY1 22DJ Ireland Lero the Science Foundation Ireland Research Centre for Software University of Limerick LimerickV94 T9PX Ireland

Automotive simulation can potentially compensate for a lack of training data in computer vision applications. However, there has been little to no image quality evaluation of automotive simulation and the impact of optical degradations on simulation is little explored. In this work, we investigate Virtual KITTI and the impact of applying variations of Gaussian blur on image sharpness. Furthermore, we consider object detection, a common computer vision application on three different state-of-the-art models, thus allowing us to characterize the relationship between object detection and sharpness. It was found that while image sharpness (MTF50) degrades from an average of 0.245cy/px to approximately 0.119cy/px;object detection performance stays largely robust within 0.58%(Faster RCNN), 1.45%(YOLOF) and 1.93%(DETR) across all respective held-out test sets. © 2024, CC BY.

关键词： Automobile simulators

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：