检索结果-内蒙古大学图书馆

DUSA-UNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Song, Jie Sun, Yue Cai, Ziyun Xiao, Liang Huang, Yawen Zheng, Yefeng Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense Nanjing210094 China Tencent YouTu Lab Jarvis Research Center Shenzhen518057 China

The challenges of road network segmentation demand an algorithm capable of adapting to the sparse and irregular shapes, as well as the diverse context, which often leads traditional encoding-decoding methods and simple Transformer embeddings to failure. We introduce a computationally efficient and powerful framework for elegant road-aware segmentation. Our method, called DUSA-UNet, effectively encodes fine-grained local road connectivity and holistic global topological semantics while decoding multiscale road network information. DUSA-UNet offers a novel alternative to the U-Net architecture by integrating connectivity attention, which can exploit intra-road interactions across multi-level sampling features with reduced computational complexity. This local interaction serves as valuable prior information for learning global interactions between road networks and the background through another integrality attention mechanism. The two forms of sparse attention are arranged alternatively and complementarily, and trained jointly, resulting in performance improvements without significant increases in computational complexity. Extensive experiments on various datasets with different resolutions, including Massachusetts, DeepGlobe, SpaceNet, and Large-Scale remote sensing images, demonstrate that DUSA-UNet outperforms state-of-the-art techniques. Our approach represents a significant advancement in the field of road network extraction, providing a computationally feasible solution that achieves high-quality segmentation results. © 1980-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

The Positive Impact of Artificial Intelligence on Education

The Positive Impact of Artificial Intelligence on Education

引用

Global Aeronautical engineering and Satellite Technology (GAST), International Conference on

作者： Abdelali El Gourari Mustapha Raoufi Mohammed Skouri Abdelghani Ait Ben Braim Mustapha Ezzini Yassine Ait Lahsen Samira Achki Laboratory of Physics High Energy and Astrophysics Faculty of Science Semlalia Cadi Ayyad University Marrakech Morocco Laboratory of Materials Energy and Environment Faculty of Sciences Semlalia Cadi Ayyad University Marrakech Morocco Fluid Mechanics and EnergeticLaboratory Cadi Ayyad UniversityFaculty of Sciences Semlalia Marrakesh Morocco Laboratory of Computer Systems Engineering Faculty of Sciences Semlalia Cadi Ayyad University Marrakech Morocco Computer Science Department FSTG Marrakech Morocco

ISBN: (数字)9798350371598

ISBN: (纸本)9798350371604

Those interested in artificial intelligence technologies, especially supervised and unsupervised learning in education, know they need considerable data for well-modeled training and high-quality accuracy. However, data access is not easy as it drains time and effort. So, in this paper, we will talk about the impact of artificial intelligence on education in general and how it will affect teachers' role in the future. We will also create an algorithm that will integrate several algorithms sequentially that will add value to this paper and contribute significantly to solving most of the problems that exist in education. Since the reinforcement learning (RL) algorithm is based on trial and error during training, it stores all the good events done in a considerable buffer. Once the RL model is ready, we will collect enough data to be used to train one of the algorithms mentioned earlier (supervised learning and unsupervised learning).

关键词： Training Satellites Supervised learning Focusing Reinforcement learning Learning (artificial intelligence) Data models

来源：评论

学校读者我要写书评

暂无评论

A Battery Capacity Prediction Method Applying to On-Service Vehicles Using Charging Data and Decomposition Framework

SSRN

引用

SSRN 2024年

作者： Zhao, Xinwei Liu, Yonggui Xiao, Bin Key Laboratory of Autonomous Systems and Network Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou510641 China School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Information Engineering School Guangzhou Vocational College of Technology & Business Guangzhou511442 China

Lithium-ion batteries are valuable as the primary power source for electric vehicles (EVs). However, their capacity degradation and reliability directly affect driving of on-service EVs, accurately forecasting battery capacity is still a tricky challenge due to complex battery systems and limitations of computing power. To overcome such barriers, a concise battery capacity prediction method is proposed based on charging data and decomposition framework in this paper. First, charging hot-spot intervals are counted to provide a reliable foundation for screening high-quality and low-quantity data. Then, the seasonal-trend decomposition method with independent analysis is designed and applied to extract significant correlation features associated with capacity degradation. Subsequently, a temporal convolution network with the decomposed mode is developed to forecast battery capacity, in conjunction with the use of decoupling mechanism to rectify the analytical interference and misinformation caused by data mixing. Finally, experiment results demonstrate that the proposed method can accurately predict capacity of on-service EVs. Furthermore, this approach alleviates the computational burden without compromising prediction accuracy. © 2024, The Authors. All rights reserved.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Learning Reduced-Order Linear Parameter-Varying Models of Nonlinear systems

arXiv

引用

arXiv 2023年

作者： Koelewijn, Patrick J.W. Singh, Rajiv Seiler, Peter Tóth, Roland Sioux Technologies B.V. Eindhoven Netherlands Control Systems Group Eindhoven University of Technology Eindhoven Netherlands The MathWorks Inc. Natick United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

In this paper, we consider the learning of a Reduced-Order Linear Parameter-Varying Model (ROLPVM) of a nonlinear dynamical system based on data. This is achieved by a two-step procedure. In the first step, we learn a projection to a lower dimensional state-space. In step two, an LPV model is learned on the reduced-order state-space using a novel, efficient parameterization in terms of neural networks. The improved modeling accuracy of the method compared to an existing method is demonstrated by simulation examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Sparse State Preparation via Quantum Walks

arXiv

引用

arXiv 2024年

作者： Gonzales, Alvin Herrman, Rebekah Campbell, Colin Gaidai, Igor Liu, Ji Tomesh, Teague Saleem, Zain H. Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States Department of Industrial and Systems Engineering University of Tennessee Knoxville KnoxvilleTN37996 United States Infleqtion ChicagoIL60604 United States

Continuous-time quantum walks (CTQWs) on dynamic graphs, referred to as dynamic CTQWs, are a recently introduced universal model of computation that offers a new paradigm in which to envision quantum algorithms. In this work we develop a mapping from dynamic CTQWs to the gate model of computation in the form of an algorithm to convert arbitrary single-edge walks and single self-loop walks, which are the fundamental building blocks of dynamic CTQWs, to their circuit model counterparts. We use this mapping to introduce an efficient sparse quantum state preparation framework based on dynamic CTQWs. Our approach utilizes global information about the target state, relates state preparation to finding the optimal path in a graph, and leads to optimizations in the reduction of controls that are not as obvious in other approaches. Interestingly, classical optimization problems such as the minimal hitting set, minimum spanning tree, and shortest Hamiltonian path problems arise in our framework. We test our methods against the state-of-the-art ancilla free sparse state preparation method and a uniformly controlled rotation method, which is used by Qiskit, and find ours requires fewer CX gates when the target state has a polynomial number of non-zero amplitudes. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Sleep Control in 5G and Beyond Radio Access Networks: An Overview

Deep Reinforcement Learning for Sleep Control in 5G and Beyo...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Nessrine Trabelsi Rihab Maaloul Lamia Chaari Fourati Wael Jaafar Laboratory of Signals systeMs aRtificial intelligence and neTworkS – Digital Research Center of Sfax Sfax Tunisia Higher Institute of Computer Science of Mahdia (ISIMa) University of Monastir Tunisia Higher Institute of Computer Science and Multimedia in Sfax (ISIMS) University of Sfax Tunisia Department of Software and IT Engineering École de technologies supérieure (ÉTS) Montreal Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The advent of 5G and beyond networks is envisioned to support lower latency, higher data rates, and wider connectivity than previous cellular network generations. However, given the denser deployment of base stations (BSs) to accommodate such improvements, this results inevitably in a significant and unsustainable increase in the network’s energy consumption. Sleep Control (SC), which allows switching off some BS hardware components during light-traffic time, is considered a viable solution for greener and more energy-efficient Radio Access Networks (RAN). However, the optimization of SC is a highly challenging large-scale network combinatorial problem that depends on dynamic wireless channel conditions and varying traffic demands with stringent Quality-of-Service (QoS) requirements. Driven by the benefits and efficiency of Deep Reinforcement Learning (DRL), which has been successfully applied to multiple wireless network optimization problems, this paper investigates DRL approaches addressing sleep control in 5G and beyond RAN. To this end, we propose a taxonomy to classify the related literature. Then, we provide an overview of the different components of the Markov Decision Process (MDP) modeling the sequential decision-making of sleep control and the applied DRL algorithms. Finally, we highlight the main challenges in existing works and suggest novel strategies to address them.

关键词： 5G mobile communication Wireless networks Taxonomy Decision making Quality of service Switches Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

arXiv

引用

arXiv 2024年

作者： Yang, Haoxin Xu, Xuemiao Xu, Cheng Zhang, Huaidong Qin, Jing Wang, Yi Heng, Pheng-Ann He, Shengfeng The School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology State Key Laboratory of Subtropical Building and Urban Science China The Centre for Smart Health The Hong Kong Polytechnic University Hong Kong The School of Future Technology South China University of Technology Guangzhou China The School of Computer Science and Network Security Dongguan University of Technology Dongguan China The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The School of Computing and Information Systems Singapore Management University Singapore

Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent manipulation in pre-trained GANs can lead to changes in ID-irrelevant attributes, adversely affecting data utility due to GAN inversion inaccuracies. This paper introduces G2Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility. We utilize a 3D face model to extract geometric information from the input face, integrating it with a pre-trained GAN-based decoder. This synergy of generative and geometric priors allows the decoder to produce realistic anonymized faces with consistent geometry. Moreover, multi-scale facial features are extracted from the original face and combined with the decoder using our novel identity-aware feature fusion blocks (IFF). This integration enables precise blending of the generated facial patterns with the original ID-irrelevant features, resulting in accurate identity manipulation. Extensive experiments demonstrate that our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility. Code is available at https://***/Harxis/G2Face. Copyright © 2024, The Authors. All rights reserved.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

BlzFS: Crash Consistent Log-structured File System Based on Byte-loggable Zone for ZNS SSD

BlzFS: Crash Consistent Log-structured File System Based on ...

引用

IEEE International Conference on computer Design: VLSI in computers and Processors, (ICCD)

作者： Wenjie Qi Zhipeng Tan Ziyue Zhang Jing Zhang Chao Yu Ying Yuan Shikai Tan Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science & Technology Huazhong University of Science & Technology Guangdong Oppo Mobile Telecommunications Corp. Ltd

Emerging Zoned Namespace (ZNS) SSDs provide hosts with fine-grained, performance-predictable storage management. The ZNS SSD divides its address space into zones, and each zone must be written sequentially and cannot be overwritten. However, the write constraint results in frequent small modifications of file metadata to record the latest logical block addresses of the updated data blocks, increasing the overhead of fsync() system call. We comprehensively analyze the metadata overhead of fsync on a real ZNS SSD and find that (1) the update size of most metadata blocks (e.g., tens of bytes) is far less than the IO unit of the zone (e.g., 4 KiB), and frequent fsyncs cause severe metadata write amplification; (2) metadata block IOs significantly increase the fsync latency, decreasing the throughput of *** reduce the metadata overhead of fsync, we build the byte-loggable zone based on the persistent write cache of the opened zone, a novel extension of ZNS, which can be appended at byte granularity instead of block. Based on the byte-loggable zone, we present BlzFS, a high-performance and crash-consistent file system for ZNS SSD. Firstly, BlzFS maintains the update ranges of the metadata block by the update bitmap. Secondly, BlzFS ensures the persistence and consistency of metadata by logging the partial updates of metadata blocks to the device’s byte-loggable zone. Finally, BlzFS restores metadata consistency by replaying the metadata update log and scanning the list of recent allocated metadata blocks. In the evaluation, BlzFS shows a 33.5%∼96.1% reduction in metadata write traffic and a 1.37×∼1.91× throughput improvement compared with the original ZNS storage system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

H observer-based control for fuzzy Hadamard fractional-order systems

引用

Computational and Applied Mathematics 2025年第4期44卷 1-14页

作者： Rhaima, Mohamed Gassara, Hamdi Mchiri, Lassaad El Hajjaji, Ahmed Ben Makhlouf, Abdellatif Department of Statistics and Operations Research College of Science King Saud University Riyadh Saudi Arabia Laboratory of Sciences Techniques of Automatic Control and Computer Engineering National School of Engineering of Sfax University of Sfax Sfax Tunisia Panthéon-Assas University Paris II Paris France Modeling Information and Systems Laboratory University of Picardie Jules Verne UFR of Sciences Amiens France Department of Mathematics Faculty of Sciences Sfax University Sfax Tunisia

While the $$H_\infty $$ observer-based control has found widespread application in the literature for integer-order systems, researchers have shown less interest in addressing the same issue within the fractional-order framework. In this context, this study delves into the application of $$H_\infty $$ observer-based control for the Hadamard fractional-order system (HFOS) described by the Takagi–Sugeno fuzzy models (TSFM). Using Lyapunov approach and by employing a matrix decoupling technique, LMI based conditions ensuring the existence of an observer and controller, are proposed. To minimize the impact of disturbances on the controlled output, $$H_\infty $$ optimization technique is used. The validity of our approach is substantiated through an example, underscoring the robustness and reliability of our proposed findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image segmentation with spatiotemporal relationship-guided graph convolution network

引用

Computing 2025年第7期107卷 1-26页

作者： You, Hongfeng Yu, Long Lin, Jianchu Chen, Xiaobing Wang, Wenhao Yu, Kun Wang, Jiacheng Huaiyin Institute of Technology Huaian China Key Laboratory of Software Engineering Technology Xinjiang University Urumuqi China Jiangsu Key Lab of Image and Video Understanding for Social Security and Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

The size of the receptive field limits traditional deep convolutional networks and needs help to fully capture the detailed semantic information of targets in complex remote sensing images. At the same time, the attributes of boundary pixels are ambiguous due to many external factors, such as illumination and imaging technology. To solve these problems, we propose a spatiotemporal relationship-guided graph convolutional network for image segmentation. We aim to explore the global and contextual semantics of targets in images and judge the attribute information of boundary pixels. On the one hand, a particular contextual attention module is embedded in the feature extractor to improve the feature extractor’s global and local detail representation. On the other hand, the graph convolution layer, enhanced by the recursive network, aggregates the high-level and low-level features of nodes to strengthen the interactivity between semantic information at different levels. At the same time, long-term dependencies are established between boundary pixels and target center pixels to constrain boundary pixels and improve their attribute decision-making ability. It is worth noting that we designed a weighted loss function to supervise, adjust, and optimize different modules separately. Finally, experimental results on the indian driving dataset, uestc all-day scenery datasets and deepglobe land cover classification challenge datasets show that the proposed framework is robust and has good segmentation performance, with F1 of 89.03%, 98.38% and 85.46%, respectively.

关键词：

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：