检索结果-内蒙古大学图书馆

XRL-SHAP-Cache:an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks

引用

Science China(information Sciences) 2024年第7期67卷 46-71页

作者： Xiaolong XU Fan WU Muhammad BILAL Xiaoyu XIA Wanchun DOU Lina YAO Weiyi ZHONG School of Software Nanjing University of Information Science and Technology School of Computing and Communications Lancaster University School of Computing Technologies Royal Melbourne Institute of Technology State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering University of New South Wales Data 61 Commonwealth Scientific and Industrial Research Organization School of Computer Science Qufu Normal University

Content delivery networks(CDNs) play a pivotal role in the modern internet infrastructure by enabling efficient content delivery across diverse geographical regions. As an essential component of CDNs, the edge caching scheme directly influences the user experience by determining the caching and eviction of content on edge servers. With the emergence of 5G technology, traditional caching schemes have faced challenges in adapting to increasingly complex and dynamic network environments. Consequently, deep reinforcement learning(DRL) offers a promising solution for intelligent zero-touch network governance. However, the blackbox nature of DRL models poses challenges in understanding and making trusting decisions. In this paper,we propose an explainable reinforcement learning(XRL)-based intelligent edge service caching approach,namely XRL-SHAP-Cache, which combines DRL with an explainable artificial intelligence(XAI) technique for cache management in CDNs. Instead of focusing solely on achieving performance gains, this study introduces a novel paradigm for providing interpretable caching strategies, thereby establishing a foundation for future transparent and trustworthy edge caching solutions. Specifically, a multi-level cache scheduling framework for CDNs was formulated theoretically, with the D3QN-based caching scheme serving as the targeted interpretable model. Subsequently, by integrating Deep-SHAP into our framework, the contribution of each state input feature to the agent's Q-value output was calculated, thereby providing valuable insights into the decision-making process. The proposed XRL-SHAP-Cache approach was evaluated through extensive experiments to demonstrate the behavior of the scheduling agent in the face of different environmental *** results demonstrate its strong explainability under various real-life scenarios while maintaining superior performance compared to traditional caching schemes in terms of cache hit ratio, quality of service(QoS),a

关键词： deep reinforcement learning (DRL) explainable artificial intelligence (XAI) multi-level cache content delivery network (CDN) D3QN algorithm Deep-SHAP

来源：评论

学校读者我要写书评

暂无评论

Computing Flow Experience Based on Physiological Signals: A Systematic Literature Review

Computing Flow Experience Based on Physiological Signals: A ...

引用

2025 CHI Conference on Human Factors in Computing systems, CHI EA 2025

作者： Hong, Yichen Zhou, Chao Liu, Zelu Zifeng, Ni Liu, Juan Li, Xiangxian Yang, Chenglei Bian, Yulong Shandong University Weihai China Human Computer Interaction Technology and Intelligent Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China Shandong University School of Mechanical Electrical & Information Engineering Weihai China Shandong University Jinan China School of Software Shandong University Jinan China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application Shandong University Shandong Weihai China Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application China

ISBN: (纸本)9798400713958

Flow experience is a key user experience in human-computer interaction (HCI). Compared with traditional subjective measurements, physiological signal-based methods (i.e. physiological computation of flow experience) can measure flow experience in a more objective and real-time way without interrupting the ongoing activity of the user. Despite scattered studies, a systematic review of research in this field is absent. Synthesizing key aspects of this field, including the conceptualization of flow experience, prevalent theoretical models, foundational research steps for experiment, computerized tasks for inducing flow, commonly used physiological signals, methods for analyzing flow state, and application in HCI. Finally, we discuss the potential of this field to propel HCI and user experience evaluation technologies, while projecting future research avenues. This paper is expected to help researchers grasp existing work in physiological signal-based flow computing and inspire subsequent explorations. © 2025 Copyright held by the owner/author(s).

关键词： Flow simulation

来源：评论

学校读者我要写书评

暂无评论

GroPipe: A Grouped Pipeline Hybrid Parallel Method for Accelerating DCNNs Training

引用

IEEE Transactions on computers 2025年第7期74卷 2487-2500页

作者： Liu, Bin Ma, Yongyao Hu, Zijian Ji, Zeyu He, Zhenli Li, Keqin Northwest A&F University College of Information Engineering Shaanxi Yangling712100 China Shaanxi Engineering Research Center of Agricultural Information Intelligent Perception and Analysis Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs China Yunnan University Yunnan Key Laboratory of Software Engineering Kunming650091 China Yunnan University School of Software Kunming650091 China State University of New York Department of Computer Science New PaltzNY12561 United States

Training large Deep Convolutional Neural Networks (DCNNs) with increasingly large datasets to improve model accuracy has become extremely time-consuming. Distributed training methods, such as data parallelism (DP) and pipeline model parallelism (PMP), offer potential solutions but face challenges like load imbalance and significant communication overhead. This paper introduces GroPipe, a novel architecture that synergistically integrates PMP and DP, markedly improving training speeds. GroPipe employs an automatic model partitioning algorithm based on a performance projection technique, ensuring load balance and facilitating quantitative performance evaluation in PMP. Additionally, it adopts a group-based delayed asynchronous communication strategy to efficiently reduce communication overhead in DP. Using the ResNet and VGG models with the ImageNet dataset, extensive experiments are performed on an 8-GPU server and demonstrate GroPipe’s effectiveness. GroPipe achieves substantial improvements in time to accuracy, showing an average improvement of 42.2% and 14.0% on the ResNet series, and 79.2% and 43.9% on the VGG series, without compromising Top-1 accuracy. © 1968-2012 IEEE.

关键词： Training Computational Modeling Parallel Processing Load Modeling Pipelines Data Models computers Memory Management Asynchronous Communication Resource Management Delayed Asynchronous Communication Deep Convolutional Neural Networks Hybrid Parallelism Pipelined Model Parallelism Deep Convolutional Neural Network Training Methods Training Speed Load Balancing Image Net Dataset Parallel Data Communication Overhead Partition Model Partitioning Algorithm Top 1 Accuracy Pipeline Model Load Imbalance Learning Rate Training Time Resource Utilization Parallelization Model Convergence Memory Usage Training Efficiency Balanced Distribution Backward Pass Multiple GP Us Forward Pass Multiple Partitions Vertical Dimension Parallel Efficiency VGG 19 Model Throughput Experiments Parallel Training Idle Time

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Deep Learning Model for Real-Time Routin 16

A Conceptual Deep Learning Model for Real-Time Routin

引用

16th IEEE International Conference on Signal-Image Technology and Internet-Based systems, SITIS 2022

作者： Ikidid, Abdelouafi Fazziki, Abdelaziz El Sadgal, Mohammed Ghazouani, Mohamed El Ichahane, My Youssef Cadi Ayyad University Computer Systems Engineering Laboratory Computer Science Dept Marrakesh Morocco Chouaib Doukkali University Polydisciplinary Faculty of Sidi Bennour El Jadida Morocco Chouaib Doukkali University Information Technologiy Laboratory El Jadida Morocco

ISBN: (纸本)9781665464956

Urban congestion has been a known problem since the first urban revolution throughout the world. Today's major metropolises are synonymous with traffic congestion and complicated urban circulation. This paper introduces a traffic management system based on agent technology and deep learning model. It acts on the phase layouts constituted of sequences and length to reduce average delay time, maximize intersection throughput, and suggest a routing planning scheme to avoid congested intersection. In the optimization model, lights of each intersection are controlled by a group of agents. The system uptake the ability of the agent to communicate, coordinate and collaborate, to decompose the routing process into decentralized architecture. The proposed model was instantiated in the ANYLOGIC simulator. © 2022 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Implementation of Malaria Detection Using MobileNetV2 Pretrained Model for Improved Deep Learning Based Diagnostics

Implementation of Malaria Detection Using MobileNetV2 Pretra...

引用

International Conference on Computing, engineering, and Design (ICCED)

作者： Rahmat Hidayat Achmad Solichin Adhitia Erfina Sudin Saepudin Muhamad Muslih Mohd Zainuri Saringat Master of Computer Science Budi Luhur University Jakarta Indonesia Information Systems Study Program Nusa Putra University Sukabumi Indonesia Department of Software Engineering Faculty of Computer Science and Information Technology Tun Hussein Onn Malaysia University

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

The Plasmodium parasite, which causes malaria, is an acute fever illness that infects people when a female Anopheles mosquito bites them. It is predicted that malaria would claim 619,000 lives in 2021, with 96% of those deaths occurring in the African continent. We can achieve this by using a microscope to examine thick and thin blood smears. The proficiency of a microscope examiner is crucial for doing microscopic examinations. Consider how time-consuming, ineffective, and costly it would be to examine thousands of malaria cases. Consequently, Creating an automated method for detecting malaria parasites is the aim of this study. We employ a MobileNetV2 pretrained model with CNN technology. Because it has been trained on dozens or even millions of data points, this pretrained model is incredibly light but dependable. There are two main benefits of automatic malaria parasite detection: firstly, it can offer a more accurate diagnosis, particularly in locations with limited resources; secondly, it lowers diagnostic expenses. The optimizer utilizes Adam Weight, the criteria uses NLLLoss, and the model is trained using 32 for batch_size. In the fourteenth epoch, we obtained the maximum accuracy score of 96.26% based on the training data. The outcomes of the predictions demonstrate how excellent this score is. EfficienceNet, DenseNet, AlexNet, and other pretrained models are among the alternatives that scientists are advised to try training with.

关键词： Training Adaptation models Accuracy Costs Malaria Microscopy Data visualization Training data Cost function Data models

来源：评论

学校读者我要写书评

暂无评论

Using Lock-Free Design for Throughput-Optimized Cache Eviction

引用

Proceedings of the ACM on Measurement and Analysis of Computing systems 2025年第2期9卷 1-28页

作者： Dong, Chao Wang, Fang Jiang, Hong Feng, Dan Huazhong University of Science and Technology Key Laboratory of Information Storage System Wuhan National Laboratory for Optoelectronics Engineering Research Center of data storage systems and Technology School of Computer Science and Technology Ministry of Education of China Hubei Wuhan China University of Texas at Arlington Department of Computer Science and Engineering ArlingtonTX United States

In large-scale information systems, storage device performance continues to improve while workloads expand in size and access characteristics. This growth puts tremendous pressure on caches and storage hierarchy in terms of concurrent throughput. However, existing cache eviction policies often struggle to provide adequate concurrent throughput due to their reliance on coarse-grained locking mechanisms and complex data structures. This paper presents a practical approach to cache eviction algorithm design, called Mobius, that optimizes the concurrent throughput of caches and reduces cache operation latency by utilizing lock-free data structures, while maintaining comparable hit ratios. Mobius includes two key designs. First, Mobius employs two lock-free FIFO queues to manage cache items, ensuring that all cache operations are executed efficiently in parallel. Second, Mobius integrates a consecutive detection mechanism that merges multiple modifications during eviction into a single operation, thereby reducing data races. Extensive evaluations using both synthetic and real-world workloads from high-concurrency clusters demonstrate that Mobius achieves a concurrent-throughput improvement ranging from 1.2× to 8.5× over state-of-the-art methods, while also maintaining lower latency and comparable cache hit ratios. The implementation of Mobius in CacheLib and RocksDB highlights its effectiveness in enhancing cache performance in practical scenarios. © 2025 ACM.

关键词： Keyways

来源：评论

学校读者我要写书评

暂无评论

Polarization-controlled dual resonant lattice Kerker effects

引用

Nano Research 2023年第2期16卷 3195-3200页

作者： Lei Xiong Xueqian Zhao Xiang Du Shuai Chen Yuanfu Lu Hongwei Ding Guangyuan Li School of Information Science and Engineering Yunnan UniversityKunming 650500China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China School of Computer Electronic and InformationGuangxi UniversityNanning 530004China College of Physics and Electronic Technology Anhui Normal UniversityWuhu 241000China Tianjin H-Chip Technology Group Corporation Tianjin 300467China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhen 518055China

The generalized Kerker effects have attracted increasing interests in recent years due to their abilities to manipulate the far-field properties of ***,the dual-polarized generalized Kerker effect enabling different tailoring of orthogonally-polarized electromagnetic waves has not yet been ***,we demonstrate polarization-controlled dual resonant lattice Kerker effects in periodic silicon *** varying the incident angle,the electric dipole and magnetic dipole surface lattice resonances can spectrally overlap,causing zero reflectance and unitary transmittance,i.e.,the resonant lattice Kerker *** incident angle for achieving this effect can be tuned differently for s-and p-polarizations over large regions by varying the nanodisk size or the lattice *** proposed dual-polarized resonant lattice Kerker effects open up avenues for polarization-controlled manipulation of the phase and wavefront of light with metasurfaces.

关键词： Kerker effect surface lattice resonances dual-polarized silicon metasurface

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Moving Object Segmentation:Recent Progress and Research Prospects

引用

Machine Intelligence Research 2023年第3期20卷 335-369页

作者： Rui Jiang Ruixiang Zhu Hu Su Yinlin Li Yuan Xie Wei Zou College of Information Engineering Shanghai Maritime UniversityShanghai201306China School of Computer Science and Technology East China Normal UniversityShanghai200062China Research Center of Precision Sensing and Control Institute of AutomationChinese Academy of SciencesBeijing100190China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing100190China

Moving object segmentation(MOS),aiming at segmenting moving objects from video frames,is an important and challenging task in computer vision and with various *** the development of deep learning(DL),MOS has also entered the era of deep models toward spatiotemporal feature *** paper aims to provide the latest review of recent DL-based MOS methods proposed during the past three ***,we present a more up-to-date categorization based on model characteristics,then compare and discuss each category from feature learning(FL),and model training and evaluation *** FL,the methods reviewed are divided into three types:spatial FL,temporal FL,and spatiotemporal FL,then analyzed from input and model architectures aspects,three input types,and four typical preprocessing subnetworks are *** terms of training,we discuss ideas for enhancing model *** terms of evaluation,based on a previous categorization of scene dependent evaluation and scene independent evaluation,and combined with whether used videos are recorded with static or moving cameras,we further provide four subdivided evaluation setups and analyze that of reviewed *** also show performance comparisons of some reviewed MOS methods and analyze the advantages and disadvantages of reviewed MOS methods in terms of ***,based on the above comparisons and discussions,we present research prospects and future directions.

关键词： Moving object segmentation(MOS) change detection background subtraction deep learning(DL) video understanding

来源：评论

学校读者我要写书评

暂无评论

Covert Communication in Satellite-Terrestrial systems with a Full-Duplex Receiver

Covert Communication in Satellite-Terrestrial Systems with a...

引用

2024 International Conference on Satellite Internet, SAT-NET 2024

作者： Guo, Zewei Sun, Ranran He, Ji Shen, Yulong Jiang, Xiaohong Future University Hakodate School of Systems Information Science Hakodate041-8655 Japan Hangzhou Institute of Technology Xidian University Hangzhou311200 China Xidian University School of Computer Science and Technology Xi'an710071 China Institute of Systems General Academy of Systems Engineering Academy of Military Sciences Beijing100101 China Xidian University Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

ISBN: (纸本)9798350375176

This paper investigates the covert communication in a satellite-terrestrial system, including a satellite transmitter Alice, a terrestrial full-duplex receiver Bob and a terrestrial warden Willie. To help the covert transmission from Alice, the full-duplex Bob transmits the jamming signal to confuse Willie and also receives the signal from Alice simultaneously. To explore the fundamental covertness in such a system, we first provide theoretical modelings for satellite-terrestrial downlink, and the detection error probability of Willie. Based on these models, we then study the transmit power optimization for covert rate maximization. Finally, we present extensive numerical results to validate our theoretical analysis and to illustrate the impact of various system parameters on the maximum covert rate. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Expression-Aware Masking and Progressive Decoupling for Cross-Database Facial Expression Recognition

Expression-Aware Masking and Progressive Decoupling for Cros...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Tao Zhong Xiaole Xian Zihan Wang Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Cross-database facial expression recognition (CD-FER) has been widely studied due to its promising applicability in real-life situations, while the generalization performance is the main concern in this task. For improving cross-database generalization, current works frequently resort to masked auto encoder (MAE) to learn the expression representation in an unsupervised manner, and disentanglement of expression and domain features. (i) For MAE, current algorithms mainly employ random masking, and leverage the reconstruction of these masked regions to enable networks to learn the expression representation. However, these masked regions are expression-irrelevant, can not well reflect the characteristics of expression, thus are not efficient enough in representation learning. To this end, we propose an expression-aware masking in MAE to improve the learning efficiency of expression representation, by guiding MAE to mask out expression-aware regions during training. (ii) For disentanglement of expression and domain features, current algorithms realize it mainly in the deep layers. However, the coupling of these features in the shallow layers are rarely concerned, which may largely affect the disentanglement performance in deep layers. Thus, we propose a progressive decoupler to disentangle these features block by block, to use the feature disentanglement in shallow layers to facilitate that in deep layers. Extensive quantitative and qualitative results on multiple expression datasets show that our method can largely outperform the state of the arts in terms of cross-database generalization performance.

关键词： Training Representation learning Couplings Face recognition Gesture recognition Task analysis

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：