检索结果-内蒙古大学图书馆

Application-Oriented Cloud Workload Prediction:A Survey and New Perspectives

Tsinghua Science and Technology 2025年第1期30卷 34-54页

作者： Binbin Feng Zhijun Ding Key Laboratory of Embedded System and Service Computing Ministry of EducationDepartment of Computer Science and TechnologyTongji UniversityShanghai 201804China Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji UniversityDepartment of Computer Science and TechnologyTongji UniversityShanghai 201804China Shanghai Artificial Intelligence Laboratory Shanghai 200232China

Workload prediction is critical in enabling proactive resource management of cloud *** workload prediction is valuable for cloud users and providers as it can effectively guide many practices,such as performance assurance,cost reduction,and energy consumption ***,cloud workload prediction is highly challenging due to the complexity and dynamics of workloads,and various solutions have been proposed to enhance the prediction *** paper aims to provide an in-depth understanding and categorization of existing solutions through extensive literature *** existing surveys,for the first time,we comprehensively sort out and analyze the development landscape of workload prediction from a new perspective,i.e.,application-oriented rather than prediction methodologies per ***,we first introduce the basic features of workload prediction,and then analyze and categorize existing efforts based on two significant characteristics of cloud applications:variability and ***,we also investigate how workload prediction is applied to resource ***,open research opportunities in workload prediction are highlighted to foster further advancements.

关键词： cloud computing workload prediction resource management artificial intelligence for IT operations(AIOps)

来源：评论

学校读者我要写书评

暂无评论

3DGCformer: 3-Dimensional Graph Convolutional transformer for multi-step origin–destination matrix forecasting

引用

Applied Intelligence 2025年第6期55卷 1-18页

作者： Huang, Yiou Deng, Hao Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

Forecasting Human mobility is of great significance in the simulation and control of infectious diseases like COVID-19. To get a clear picture of potential future outbreaks, it is necessary to forecast multi-step Origin–Destination (OD) matrices for a relatively long period in the future. However, multi-step Origin–Destination Matrix Forecasting (ODMF) is a non-trivial problem. First, previous ODMF models only forecast the OD matrix for the next time-step, and they cannot perform well on long-term multi-step forecasts due to error accumulation. Second, many ODMF methods capture spatial and temporal dependencies with separate modules, which is insufficient to model spatio-temporal correlations in the time-varying OD matrix sequence. To address the challenges in multi-step ODMF, we propose 3-Dimensional Graph Convolutional Transformer (3DGCformer). As an enhancement of the original 3DGCN, we propose a novel Origin–Destination Feature Propagation (ODFP) rule between 3DGCN layers and integrate 2 3DGCNs with different spatio-temporal graphs and corresponding feature propagation rules to model the formation of OD flows in a more comprehensive way. For multi-step forecasts, 3DGCformer uses Transformer to capture long-term global temporal dependency, and adapt its decoder using labeled tokens to avoid error accumulation and improve time efficiency. To avoid information loss as the number of regions increases, we propose a patch embedding approach to convert data from 3DGCNs to the Transformer module. We perform extensive experiments on 4 real-world human mobility datasets, and the results show that our proposed model outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Low-Light Image Enhancement Based on Explicit Denoising and Knowledge Distillation

引用

computers, Materials & Continua 2025年第2期82卷 2537-2554页

作者： Wenkai Zhang Hao Zhang Xianming Liu Xiaoyu Guo Xinzhe Wang Shuiwang Li College of Computer Science and Engineering Guilin University of TechnologyGuilin541006China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of TechnologyGuilin541004China

Under low-illumination conditions, the quality of image signals deteriorates significantly, typically characterized by a peak signal-to-noise ratio (PSNR) below 10 dB, which severely limits the usability of the images. Supervised methods, which utilize paired high-low light images as training sets, can enhance the PSNR to around 20 dB, significantly improving image quality. However, such data is challenging to obtain. In recent years, unsupervised low-light image enhancement (LIE) methods based on the Retinex framework have been proposed, but they generally lag behind supervised methods by 5–10 dB in performance. In this paper, we introduce the Denoising-Distilled Retine (DDR) method, an unsupervised approach that integrates denoising priors into a Retinex-based training framework. By explicitly incorporating denoising, the DDR method effectively addresses the challenges of noise and artifacts in low-light images, thereby enhancing the performance of the Retinex framework. The model achieved a PSNR of 19.82 dB on the LOL dataset, which is comparable to the performance of supervised methods. Furthermore, by applying knowledge distillation, the DDR method optimizes the model for real-time processing of low-light images, achieving a processing speed of 199.7 fps without incurring additional computational costs. While the DDR method has demonstrated superior performance in terms of image quality and processing speed, there is still room for improvement in terms of robustness across different color spaces and under highly resource-constrained conditions. Future research will focus on enhancing the model’s generalizability and adaptability to address these challenges. Our rigorous testing on public datasets further substantiates the DDR method’s state-of-the-art performance in both image quality and processing speed.

关键词： Deep learning low-light image enhancement real-time processing knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

PPDO:a privacy-preservation-aware delay optimization task-offloading algorithm for collaborative edge computing

引用

Frontiers of Information Technology & Electronic Engineering 2025年第1期26卷 27-41页

作者： Chao JING Jianwu XU College of Computer Science and Engineering Guilin University of TechnologyGuilin 541004China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin 541004China

Although collaborative edge computing(CEC)systems are beneficial in enhancing the performance of mobile edge computing(MEC),the issue of user privacy leakage becomes prominent during task *** address this issue,we design a privacy-preservation-aware delay optimization task-offloading algorithm(PPDO)in a CEC *** considering location and usage pattern privacy protection,we establish a privacy task model to interfere with the edge server and ensure user *** address the extra delay arising from privacy protection,we subsequently leverage a Markov decision processing(MDP)policy-iteration-based algorithm to minimize delays without compromising *** simultaneously accelerate the MDP operation,we develop an extension that improves the PPDO by optimizing the action ***,a comprehensive simulation was conducted using the edge user allocation(EUA)*** results demonstrated that PPDO achieves an optimal trade-off between privacy protection and delay with a minimum delay compared with existing ***,we examined the advantages and disadvantages of improving PPDO.

关键词： Collaborative edge computing Task offloading Privacy protection Markov decision process

来源：评论

学校读者我要写书评

暂无评论

UAV-Mounted Intelligent Reflecting Surface in Maritime Wireless Powered Communication Network

引用

China Communications 2025年第3期22卷 254-269页

作者： Liu Yuan Han Fengxia Zhao Shengjie School of Information Science and Electrical Engineering Shandong Jiaotong UniversityJinan 250357China College of Electronic and Information Engineering Tongji UniversityShanghai 201804China School of Software Engineering Tongji UniversityShanghai 201804China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of EducationShanghai 200003China Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 201804China

Intelligent reflecting surface(IRS)assisted with the wireless powered communication network(WPCN)can enhance the desired signal energy and carry out the power-sustaining problem in ocean monitoring *** this paper,we investigate a reliable communication structure where multiple buoys transmit data to a base station(BS)with the help of the unmanned aerial vehicle(UAV)-mounted IRS and harvest energy from the base station *** organically combine WPCN with maritime data collection scenario,a scheduling protocol that employs the time division multiple access(TDMA)is proposed to serve multiple buoys for uplink data ***,we compare the full-duplex(FD)and half-duplex(HD)mechanisms in the maritime data collection system to illustrate different performances under these two *** maximize the fair energy efficiency under the energy harvesting constraints,a joint optimization problem on user association,BS transmit power,UAV’s trajectory and IRS’s phase shift is *** solve the non-convex problem,the original problem is decoupled into several subproblems,and successive convex optimization and block coordinate descent(BCD)methods are employed obtain the near-optimal solutions *** results demonstrate that the UAV-mounted IRS can significantly improve energy efficiency in our considered system.

关键词： full-duplex IRS joint optimization TDMA UAV WPCN

来源：评论

学校读者我要写书评

暂无评论

Personalized Medical Federated Learning Based on Mutual Knowledge Distillation in Object Heterogeneous Environment 1st

Personalized Medical Federated Learning Based on Mutual Kno...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Ni, Lina Song, Chenglin Zhao, Hanmo Tang, Yuncan Ma, Yunshen Zhang, Jinquan College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Tongji University Shanghai201804 China

ISBN: (纸本)9789819794119

Federated Learning (FL), hailed as a potent approach in merging medical expertise, promises to elevate collaborative efforts among healthcare institutions while safeguarding the privacy and security of sensitive medical data, thereby energizing the trajectory of intelligent healthcare advancements. However, the diversity in training objectives across medical institutions can diminish their active participation in a unified federated training process. To address this issue of waning enthusiasm due to diverse training goals, in this paper, we propose Personalized Medical Federated Learning method based on Mutual Distillation Knowledge (pFedMKD). Specifically, we propose a similarity-based mutual distillation model selection algorithm that reduces interference among medical institutions with notably diverse data distributions. Moreover, we develop a server-side local model update method leveraging mutual knowledge distillation, enabling each local model to gain beneficial insights for personalization from analogous models. Additionally, we formulate a personalized model update method utilizing knowledge distillation from specifically labeled samples, thereby improving the performance of personalized models. Experimental results demonstrate that compared to the baseline algorithm, pFedMKD can more effectively address the target heterogeneity problem among different medical institutions, enabling each institution to achieve higher personalized performance in federated learning tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning Based on Device Performance in a Heterogeneous Environment of Medical Computing Devices 1st

Adaptive Federated Learning Based on Device Performance in...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Zhang, Jinquan Wang, Chongbo Yang, Rendong Tang, Yuncan Ma, Yunshen Ni, Lina College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Tongji University Shanghai201804 China

ISBN: (纸本)9789819794119

Federated Learning (FL), as one of the effective methods to solve the problem of medical data silos, can promote mutual cooperation among medical institutions under the premise of safeguarding the privacy and security of medical data, and effectively promote the development of intelligent medical treatment. However, the characteristics of medical data with multiple sources and heterogeneity bring certain challenges to the application of federated learning in the medical field. Due to the wide range of medical data sources, some medical institutions are unable to complete the federated learning training task on time due to the limitation of device performance, which leads to the failure of federated learning training. To address the problem of heterogeneity of computing devices among medical institutions that may cause some clients to fall behind, we propose an Adaptive Federated Learning based on Device Performance (AFedDP) method. Specifically, we design an adaptive local model training method to reduce the computational burden of medical institutions with poor equipment performance in the local model training process by adaptively constructing a local training model. Additionally, we propose a hierarchical model aggregation algorithm based on dynamic weight. This allows the heterogeneous adaptive local model to actively participate in the global model aggregation, making full use of the local data of each medical institution and improving the performance of the global model. Finally, we design an aggregation weight update algorithm based on momentum optimization to enhance the stability of global model aggregation. This algorithm updates contribution and aggregation weight with the idea of momentum optimization. Simulation experiments demonstrate that AFedDP achieves higher accuracy compared to the baseline algorithm. AFedDP can better address the issue of some devices being unable to participate in federated training properly. © The Author(s), under exclusive lic

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Memetic Algorithm Based Feature Weighting for Metabolomics Data Classification

引用

Chinese Journal of Electronics 2025年第4期23卷 706-711页

作者： Jiarui Zhou Zexuan Zhu Zhen Ji College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China Shenzhen City Key Laboratory of Embedded System Design College of Computer Science and Software Engineering Shenzhen University Shenzhen China

A metaheuristic chain based memetic algorithm namely MCMA is proposed for the classification of metabolomics data. MCMA regards both global evolution and local search as equivalent elemental metaheuristics, and searches with a chain of metaheuristics performed alternatively on the target problem. A hidden Markov model based scheduling mechanism is employed in MCMA for the selection of metaheuristics. By using MCMA for optimizing the linkage weight vector, a feature weighting algorithm for metabolomics data is formed to identify relevant metabolite features and reveal their exact relationships with the given physiological states. An extreme learning machine based classifier is utilized in predicting the physiological states according to the weighted metabolite features. Experimental results on real metabolomics data of clinical liver transplantation demonstrate that the proposed feature weighting and classification method obtains better performance than the other compared algorithms.

关键词： Memetics Metabolomics Metaheuristics Urban areas Liver Prediction algorithms Search problems Physiology Vectors Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multivariate Time Series Anomaly Detection by Feature Decoupling in Federated Learning Scenarios

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： He, Yifan Ding, Xi Tang, Yateng Guan, Jihong Zhou, Shuigeng Fudan University School of Computer Science Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Tencent Weixin Group Guangzhou510308 China Tongji University Department of Computer Science and Technology Shanghai201804 China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai200092 China

Anomalies are usually regarded as data errors or novel patterns previously unseen, which are quite different from most observed data. Accurate detection of anomalies is crucial in various application scenarios. This paper focuses on unsupervised anomaly detection from Multivariate Time Series (MTS), as real-world data collected from sources such as wearable devices, medical equipment and industrial machines typically manifest as MTS and are often unlabeled. Anomaly detection in MTS represents a data-driven challenge that traditionally requires substantial centralized data for training models. However, in practice, data are frequently distributed among multiple institutions, with privacy concerns restricting unrestricted access. To address these issues, we introduce Feature Decoupling Federated Learning (FDFL), an approach designed to collaboratively train a representation learning network over multiple clients for unsupervised anomaly detection in MTS. Unlike previous methods that simply integrate MTS anomaly detection algorithms with federated learning strategies, FDFL specifically addresses heterogeneity among clients by decoupling the representation network into shared and private branches through a contrastive learning mechanism. This method aggregates shared parameters during each federated round while maintaining client-specific private parameters locally. Additionally, we develop a self-attention block that integrates the representations derived from both shared and private parameters to reconstruct MTS and identify anomalies based on reconstruction errors. Extensive experiments conducted on three publicly available datasets demonstrate that FDFL outperforms existing algorithms in most cases, highlighting the effectiveness and superiority of our proposed method in MTS anomaly detection. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A two-way dynamic adaptive pricing resource allocation model based on combinatorial double auctions in computational network

引用

computer Communications 2025年 238卷

作者： Xu, Yanjun Tian, Chunqi Wang, Wei Bai, Lizhi Xia, Xuhui School of Computer Science and Technology Tongji University Shanghai China School of Data Science and Engineering East China Normal University Shanghai China Embedded System and Service Computing Key Laboratory of Ministry of Education China

Efficient resource allocation in computing networks is essential for managing fluctuating demands and optimizing system performance. Traditional auction and pricing models often fail to adapt to diverse demands and supply–demand fluctuations, resulting in inefficiencies. This paper proposes a bidirectional price-adaptive bundled resource auction model that considers not only the autonomous adjustment of sellers’ quotations in response to supply–demand fluctuations but also the impact of these fluctuations on buyers’ willingness to pay and bidding behavior. The model integrates Combinatorial Double Auction (CDA) mechanism and Genetic Algorithm (GA), constructing a bundled resource auction mechanism that accommodates diverse resource demands and an adaptive pricing strategy that dynamically responds to real-time supply–demand variations. This approach enhances resource allocation accuracy in dynamic and competitive computing network environments. Furthermore, a reserve price mechanism and a delay compensation strategy are introduced to ensure that the proposed mechanism satisfies individual rationality, budget balance, and incentive compatibility while maintaining computational efficiency. Simulation results demonstrate that, compared to traditional methods, the proposed model not only improves allocation efficiency and enhances resource utilization but also helps reduce operational costs. Specifically, resource allocation dispersion decreases by 4.26%, while service providers’ revenue increases by 7.47%. This study provides a scalable and adaptive solution for dynamic resource allocation in cloud and edge computing platforms. It contributes significantly to the development of resource management and flexible pricing strategies in markets characterized by diverse demands and fluctuating conditions. © 2025

关键词： Budget control

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：