检索结果-内蒙古大学图书馆

Sequence-Aware Online Container Scheduling with Reinforcement Learning in Parked Vehicle Edge computing

IEEE Transactions on Vehicular Technology 2025年

作者： Wu, Jianqiu Guo, Jianxiong Tang, Zhiqing Luo, Chuanwen Wang, Tian Jia, Weijia Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing100083 China

intelligent vehicles, often parked for long periods, are ideally suited to serve as computational nodes to expand the Mobile Edge computing (MEC) infrastructure, with containerization significantly enhancing the system's load balancing, self-healing, resource isolation, and security. However, fluctuations in task demand and frequent container image downloads during peak hours create high loads on containerized nodes, as multiple mobile devices offload tasks simultaneously, leading to significant processing delays. Many existing studies make the simplified assumption of predefined patterns of task arrivals, which overlooks this issue and makes suboptimal decisions. In this paper, we consider a Parked Vehicles (PVs)-extended MEC scenario, where multiple devices request services on PVs functioning as edge servers, all controlled by a central base station. Task arrivals follow observed patterns based on long-term trends, such as peak and off-peak periods, resembling realistic arrival patterns rather than predefined ones. To optimize task offloading by identifying these patterns, we propose the Sequence-Aware Task Scheduling (SATS) algorithm, which is a policy gradient-based deep reinforcement learning approach that integrates Transformer and LSTM architectures to capture patterns in time-series task arrivals and relationships between nodes in a collaborative and containerized environment, thereby enhancing the efficiency of online task scheduling. The primary objective of SATS is to optimize the task offloading policy and minimize delay and energy consumption for all devices and PVs. Extensive numerical comparisons against baselines demonstrate the effectiveness and advantages of our algorithm. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-CRIME and XD-VIOLENCE datasets, demonstrating its effectiveness in OVVAD. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The role of membrane characteristics in improving vacuum membrane distillation efficiency: A lattice Boltzmann study

引用

Desalination 2025年 612卷

作者： Zhang, Hongxuan Gong, Dian Zhou, Yiling Qin, Zhangrong Wen, Binghai Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China CAS Key Laboratory of Low-Carbon Conversion Science and Engineering Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai201210 China PetroChina Shanghai Advanced Materials Research Institute Co.Ltd Shanghai201210 China

With increasing water scarcity, membrane distillation technology has gained widespread attention as an innovative method for seawater desalination. However, existing studies often overlook the influence of membrane characteristics on mass transfer efficiency. This study, based on the lattice Boltzmann method, proposes a model for a novel Poly(tetraethynylpyrene) membrane material to reveal the influence of membrane characteristics on the performance of vacuum membrane distillation. The model considers factors such as porosity, tortuosity, membrane thickness, pore size, membrane surface wettability, temperature difference and vacuum pressure on the permeate flux. The results show that the permeate flux increases linearly with both the increase in porosity and the decrease in vacuum pressure, while it decreases exponentially with the tortuosity factor. The results show that the permeate flux increases linearly with the porosity and decreases exponentially with the tortuosity factor. There is an optimal membrane thickness (2 μm) beyond which the permeate flux decreases exponentially. In addition, the permeate flux increases exponentially with increasing temperature difference and pore size. Further analysis of the effect of membrane surface wettability shows that permeate flux increases with increasing hydrophobicity. Finally, the feed temperature and the tortuosity factor have the most significant effect on the permeate flux, followed by the membrane thickness, the pore size and finally the vacuum pressure, which has the least significant effect. The model can be further extended to study other configurations of membrane distillation technologies. © 2025

关键词： Pore size

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

IEEE International Symposium on Biomedical Imaging

作者： Fan Yang S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment.

关键词： Training Measurement Adaptation models Three-dimensional displays Smoothing methods Head Kernel Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Learning Comprehensive Representation via Selective Activation and Dual-Level Orthogonality for Pedestrian Attribute Recognition

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Zhao, Jianqiang Ministry of Education Engineering Research Center of Big Data Intelligence China Ai Research Center Sdic Intelligence Xiamen Information Co. Ltd Xiamen China Xiamen Meiya Pico Information Security Research Institute Co. Ltd Xiamen China Institute of Automation Beijing China Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou China University of Technology Sydney School of Electrical and Data Engineering Ultimo Australia

Multi-label Pedestrian Attribute Recognition (PAR) involves identifying a series of semantic attributes in person images. Existing PAR solutions typically rely on CNN as the backbone network to extract pedestrian features. Unfortunately, CNNs process only one adjacent region at a time, resulting in the disappearance of long-range relations between different attribute-specific regions. To address this limitation, we adopt the Vision Transformer (ViT) instead of CNN as the backbone for PAR, aiming to build long-range relations and extract more robust features. However, PAR suffers from an inherent attribute imbalance issue, causing ViT to naturally focus more on attributes that appear frequently in the training set and ignore some pedestrian attributes that appear less. The native features extracted by ViT are not able to tolerate the imbalance attribute distribution issue. To tackle this issue, we propose a novel component and a dual-level loss: the Selective Feature Activation Method (SFAM), the Orthogonal Feature Activation Loss (OFALoss), and Orthogonal Weight Regularization Loss (OWRLoss). SFAM smartly suppresses the more informative attribute-specific features, thus compelling the PAR model to pay greater attention to attribute-specific regions that are often overlooked. The proposed OFALoss enforces an orthogonal constraint on the original feature extracted by ViT and the suppressed features from SFAM, promoting the comprehensiveness of feature representation in each attribute-specific region. Furthermore, OWRLoss is employed for decreasing correlations among entries of the last shared classification layer, which can alleviate the highly correlated of weight vectors caused by non-uniform distribution. This can prevent excessive mutual interference among different attributes during attribute recognition. Our model-agnostic approach is plug-and-play, requiring no additional training parameters in the training process. We conduct experiments on several benchmark P

关键词： Dual-Level Orthogonal Regularization Pedestrian Attribute Recognition Selective Feature Activation

来源：评论

学校读者我要写书评

暂无评论

Influence of Membrane Characteristics on Efficiency of Vacuum Membrane Distillation: a Lattice Boltzmann Study

arXiv

引用

arXiv 2025年

With increasing water scarcity, membrane distillation technology has gained widespread attention as an innovative method for seawater desalination. However, existing studies often overlook the influence of membrane characteristics on mass transfer efficiency. This study, based on the lattice Boltzmann method, proposes a model for a novel Poly(tetraethynylpyrene) membrane material to reveal the influence of membrane characteristics on the performance of vacuum membrane distillation. The model considers the factors such as porosity, tortuosity, membrane thickness, pore size, membrane surface wettability and temperature difference on the permeate flux. The results show that the permeate flux increases linearly with the porosity and decreases exponentially with the tortuosity factor. There is an optimal membrane thickness range (2 m) beyond which the permeate flux decreases exponentially. In addition, the permeate flux increases exponentially with increasing temperature difference and pore size. Further analysis of the effect of membrane surface wettability shows that permeate flux increases with increasing hydrophobicity. Finally, the feed temperature and tortuosity factor have the largest effect on permeate flux, followed by membrane thickness and, subsequently, pore size. The model can be further extended to study other configurations of membrane distillation technologies. Copyright © 2025, The Authors. All rights reserved.

关键词： Wetting

来源：评论

学校读者我要写书评

暂无评论

In-situ synthesized SiC/TiC/SiTiOC hybrid nanofiber mats for broad-range temperature microwave absorption

引用

Science China Technological Sciences 2025年第6期68.0卷 1-14页

作者： Huo, Yashan Qian, Yuetong Zhao, Minshan Zhang, Lei Tan, Yujia He, Zhihui Miao, Peng Zhang, Fuchun Cui, Wei Che, Renchao School of Physics and Electronic Information Yan’an University Yan’an 716000 China Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative Materials Academy for Engineering & Technology Advanced Coatings Research Center of Ministry of Education of China Fudan University Shanghai 200438 China School of Materials and Chemical Engineering Xi’an Technological University Xi’an 710021 China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan’an 716000 China School of Materials Science & Engineering Tongji University Shanghai 201804 China College of Physics Donghua University Shanghai 201620 China

Efficient, temperature-insensitive electromagnetic attenuation materials are critical for high microwave absorption at high temperatures. This study presents SiC/TiC/SiTiOC hybrid nanofiber mats constructed using an in-situ synthesis method;these mats incorporate SiC/TiC as the microwave loss unit and SiTiOC as the antioxidant unit, offering an innovative approach to high-temperature microwave absorption. The introduction of high-conductivity TiC not only optimizes the dielectric constant and impedance matching of the material but also enhances its thermal cycling stability. This design ensures steady electromagnetic attenuation, enabling the hybrid nanofiber mats to maintain robust absorption performance in the X-band, even at high temperatures. At 873 K, the material demonstrates an effective absorption bandwidth of 3.6 GHz and a minimum reflection loss of −45.55 dB. Compared to single-system absorbers, such as SiC/C nanofiber materials, with a single system, the multi-component SiC/TiC/SiTiOC hybrid nanofiber mats deliver reliable absorption performance in the temperature range of 293–873 K. This study confirms that highly conductive titanium-based ceramic materials used for dielectric property regulation effectively address the challenges of poor temperature stability and limited reusability in high-temperature carbon-ceramic absorbing materials, providing valuable insights and guidance for designing efficient microwave absorbers that can operate across a wide temperature range. © Science China Press 2025.

关键词： dielectric properties electrospinning high-temperature microwave absorption SiC/TiC/SiTiOC hybrid nanofiber mats thermal stability

来源：评论

学校读者我要写书评

暂无评论

Rate-Splitting Multiple Access Enabled Green Probabilistic Semantic Communication over Wireless Networks

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Xu, Ruopeng Yang, Zhaohui Mao, Yijie Huang, Chongwen Yang, Qianqian Xu, Lexi Xu, Wei Zhang, Zhaoyang Zhejiang University College of Information Science and Electronic Engineering China Hangzhou310027 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China Zhejiang Prov. Key Lab. of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China China United Network Communications Corporation Research Institute Beijing100048 China Southeast University National Mobile Communications Research Laboratory Nanjing211189 China

In this paper, we propose a multi-user green probabilistic semantic communication (PSC) system for semantic communication (SemCom) facilitated by probabilistic knowledge graphs (PKGs), which are knowledge graphs (KGs) integrated with probability to represent semantic information. In the considered model, semantic information of different users is represented by PKGs. On this basis, we design a semantic compression model for multi-user downlink task-oriented SemCom, utilizing the semantic compression ratio (SCR) as a parameter to connect the computation and communication processes of information transmission. Utilizing rate-splitting multiple access (RSMA) technology, the transmitted messages are splitted into shared and private ones. Considering the limited wireless resources and constraint in semantic communication, an optimization problem with the goal of minimizing system energy consumption comprehensively considering the computation and communication process is formulated. In order to address the optimization problem, we propose an alternating optimization algorithm that tackles sub-problems of power allocation and beamforming design with successive convex approximation (SCA) method, semantic compression ratio optimization with variable substitution method, and computation capacity allocation with obtaining closed-form optimal solution. Simulation results verify the effectiveness of the proposed algorithm. © 2017 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

arXiv

引用

arXiv 2025年

作者： Jiang, Kaixun Chen, Zhaoyu Fu, Jiyuan Hong, Lingyi Li, Jinglun Zhang, Wenqiang Shanghai Engineering Research Center of AI Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

—Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models’ adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against state-of-the-art black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Moreover, our method can be applied as a flexible defense plugin for video recognition models. Our code is available at https://***/deep-kaix

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Quantum neural compressive sensing for ghost imaging

arXiv

引用

arXiv 2025年

作者： Zhai, Xinliang Xiao, Tailong Huang, Jingzheng Fan, Jianping Zeng, Guihua State Key Laboratory of Advanced Optical Communication Systems and Networks Institute for Quantum Sensing and Information Processing Shanghai Jiao Tong University Shanghai200240 China Hefei National Laboratory Hefei230088 China Shanghai Research Center for Quantum Sciences Shanghai201315 China AI Lab Lenovo Research Beijing100094 China

Demonstrating the utility of quantum algorithms is a long-standing challenge, where quantum machine learning becomes one of the most promising candidate that can be resorted to. In this study, we investigate a quantum neural compressive sensing algorithm for ghost imaging to showcase its utility. The algorithm utilizes the variational quantum circuits to reparameterize the inverse problem of ghost imaging and uses the inductive bias of the physical forward model to perform optimization. To validate the algorithm’s effectiveness, we conduct optical ghost imaging experiments, capturing signals from objects at different physical sampling rates and detection signal-to-noise ratios. The experimental results show that our proposed algorithm surpasses conventional methods in both visual appearance and quantitative metrics, achieving state-of-the-art performance. Importantly, we observe that the quantum neural network, guided by prior knowledge of physics, effectively overcomes the challenge of barren plateau in the optimization process. The proposed algorithm demonstrates robustness against various quantum noise levels, making it suitable for near-term quantum devices. Our study leverages physical inductive bias guided variational quantum algorithm, underscoring the potential of quantum computation in tackling a broad range of optimization and inverse problems. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

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：