检索结果-内蒙古大学图书馆

IEEE Annual Joint conference: INFOCOM, IEEE Computer and Communications Societies

作者： Weijie Wu John C.S. Lui Computer Science & Engineering Department Chinese University of Hong Kong Hong Kong China

ISBN: (纸本)9781424499199

Content providers of P2P-Video-on-Demand (P2P-VoD) services aim to provide a high quality, scalable service to users, and at the same time, operate the system with a manageable operating cost. Given the volume-based charging model by ISPs, it is to the best interest of the P2P-VoD content providers to reduce peers' access to the content server so as to reduce the operating cost. In this paper, we address an important open problem: what is the “optimal replication ratio” in a P2P-VoD system such that peers will receive service from each other and at the same time, reduce the traffic to the content server. We address two fundamental problems: (1) what is the optimal replication ratio of a movie given its popularity, and (2) how to achieve the optimal ratios in a distributed and dynamic fashion. We formally show how movie popularities can impact server's workload, and formulate the video replication as an optimization problem. We show that the conventional wisdom of using the proportional replication strategy is non-optimal, and expand the design space to both passive replacement policy and active push policy to achieve the optimal replication ratios. We consider practical implementation issues, evaluate the performance of P2P-VoD systems and show that our algorithms can greatly reduce server's workload and improve streaming quality.

关键词： Motion pictures Servers Bandwidth software Peer to peer computing Algorithm design and analysis optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Application for Network Latency Management in software Defined Networks

Deep Reinforcement Learning Application for Network Latency ...

引用

IEEE Global Communications conference

作者： El Hocine Bouzidi Abdelkader Outtagarts Rami Langar University Paris-Est LIGM-CNRS UMR 8049 UPEM Marne-la-Vallee France Nokia Bell Labs Villarceaux Center - Route de Villejust Nozay France

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

The centralization of network intelligence enabled by software Defined Networking (SDN), and the recent breakthroughs of Machine Learning (ML), paved the way to address a variety of network challenges. Quality-of-Service (QoS)-aware routing is one of the important challenges in SDN-based networks, especially when multiple flows coexist in the same network. Optimizing network performances (i.e., end-to-end delay, throughput) must be achieved in order to enhance the performance of QoS-aware routing. Neural Networks and Reinforcement learning are ML breakthroughs that can tackle this important challenge. To this end, we propose, in this paper, an efficient rules placement algorithm based on Deep Reinforcement Learning (DRL) and traffic prediction. Our proposal aims to dynamically collect the optimal path from the DRL agent and predict future traffic demands using the well-known prediction method LSTM. To do so, we first formulate the flow rules placement as an Integer Linear Program (ILP) that aims to minimize the total network delay. Then, we propose a simple yet efficient heuristic algorithm to solve the formulated ILP problem with low time complexity and high estimation accuracy. The proposed algorithm interacts with the DRL agent to get the optimal path and the traffic prediction module in order to avoid congestion. The obtained results using ONOS controller and OpenvSwitch revealed the efficiency of the proposed approach in decreasing both network latency and packet loss, and rising the network throughput.

关键词： Routing optimization Quality of service Delays Neural networks Prediction algorithms Network topology

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Robust Motion Planning for high DoF Robot Manipulator using Deep MPC

Self-Adaptive Robust Motion Planning for High DoF Robot Mani...

引用

Robotics, Artificial Intelligence and Intelligent Control (RAIIC), International conference on

作者： Ye Zhang Kangtong Mo Fangzhou Shen Xuanzhen Xu Xingyu Zhang Jiayue Yu Chang Yu University of Pittsburgh PA USA University of Illinois Urbana-Champaign IL USA San Jose State University at San Jose CA USA Snap Inc. at Seattle WA USA George Washington University DC USA Warner Bro. Discovery at Culver City CA USA Northeastern University at Boston MA USA

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

In contemporary control theory, self-adaptive methodologies are highly esteemed for their inherent flexibility and robustness in managing modeling uncertainties. Particularly, robust adaptive control stands out owing to its potent capability of leveraging robust optimization algorithms to approximate cost functions and relax the stringent constraints often associated with conventional self-adaptive control paradigms. Deep learning methods, characterized by their extensive layered architecture, offer significantly enhanced approximation prowess. Notwithstanding, the implementation of deep learning is replete with challenges, particularly the phenomena of vanishing and exploding gradients encountered during the training process. This paper introduces a self-adaptive control scheme integrating a deep MPC, governed by an innovative weight update law designed to mitigate the vanishing and exploding gradient predicament by employing the gradient sign exclusively. The proffered controller is a self-adaptive dynamic inversion mechanism, integrating an augmented state observer within an auxiliary estimation circuit to enhance the training phase. This approach enables the deep MPC to learn the entire plant model in real-time and the efficacy of the controller is demonstrated through simulations involving a high-DoF robot manipulator, wherein the controller adeptly learns the nonlinear plant dynamics expeditiously and exhibits commendable performance in the motion planning task.

关键词： Training Deep learning Uncertainty Dynamics Estimation Robustness Planning

来源：评论

学校读者我要写书评

暂无评论

Implementation and optimization of a data protecting model on the Sunway TaihuLight supercomputer with heterogeneous many-core processors

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2019年第21期31卷

作者： Chen, Yuedan Li, Kenli Fei, Xiongwei Quan, Zhe Li, Keqin Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China Natl Supercomp Ctr Changsha Changsha 410082 Hunan Peoples R China SUNY New York Dept Comp Sci New York NY 12561 USA

With the rapid development of information technology, the security of massive amounts of digital data has attracted huge attention in recent years. The Advanced Encryption Standard (AES) algorithm and the Security Hash Algorithm 3 (SHA3) are extensively used as cryptographic algorithms for protecting the security of information. The Sunway TaihuLight, with massive heterogeneous many-core SW26010 processors, has the peak performance of over 100 PFlops. To achieve high efficiency of data encryption/decryption and guarantee the data integrity for large-scale applications, this paper proposes a fast and secure data protecting model using the parallel AES algorithm and the SHA3 on the Sunway TaihuLight. According to the particular computing architecture and memory hierarchy of the Sunway TaihuLight, we propose a fine-grained software design for the data protecting model to fully exploit the parallelism and properly arranges the data on the Sunway. Furthermore, we propose optimization strategies for the parallel AES algorithm of the data protecting model. It is proved that our data protecting model has high security, good scalability, and excellent encryption/decryption efficiency on the Sunway. Our data protecting model achieves a high throughput of 269.95 Gbits/s, and the optimized parallel AES algorithm achieves 511.28 Gbits/s on the Sunway.

关键词： advanced encryption standard (AES) heterogeneous many-core processor parallelism security hash algorithm 3 (SHA3) Sunway TaihuLight supercomputer

来源：评论

学校读者我要写书评

暂无评论

A Low-light Image Enhancement Method Balancing Brightness Boosting and Noise Smoothing 22

A Low-light Image Enhancement Method Balancing Brightness Bo...

引用

Proceedings of the 2022 6th International conference on Computer Science and Artificial Intelligence

作者： Zekun Cui Weikang Wang Ziwei Xu Chao Wang College of Software Nankai University China

ISBN: (纸本)9781450397773

Images captured in low-light or uneven lighting environments need to use low-light image enhancement techniques to boost brightness and contrast for high-quality improved results. Some existing low-light image enhancement methods over-enhance the image and ignore the noise processing. While other methods do smooth the noise, the brightness and contrast of the result image are not significantly improved. Based on JED, we improve and introduce a low-light image enhancement method balancing brightness boosting and noise smoothing. We simplify and improve the optimization functions for estimating illumination and reflectance map. After that, a Gamma matrix is proposed for illumination correction, and we conduct multi-scale detail enhancement on the reflectance map. Finally, we get the enhanced result image by the Retinex model. Our method can boost the brightness and contrast of the image while effectively smoothing the noise and preserving the details; that is, a balance is achieved between brightness improvement and noise smoothing. The final comparative experiment results show that the proposed method has better performance on qualitative and quantitative evaluations than some classic low-light image enhancement algorithms.

关键词： low-light image enhancement image enhancement Retinex theory image restoration

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Dynamic Demand in Shared Bicycle Scheduling Problem

Deep Reinforcement Learning for Dynamic Demand in Shared Bic...

引用

International conference on Big Data and Information Analytics (BigDIA)

作者： Zixiao Jiao Wenhua Xiao Hailu Xin Daqian Liu Hui Yan Chao Chen Laboratory for Big Data and Decision National University of Defense Technology Changsha China Academy of Military Sciences Beijing China College of Systems Engineering National University of Defense Technology Changsha China Software College Liaoning Technical University Liaoning China School of Traffic and Transportation Engineering Central South University Changsha China

In contemporary shared bicycle scheduling systems, a common occurrence is a severe imbalance between regions, with one area suffering from a dearth of bicycles while another area is burdened with an excess. The task of balancing the distribution of vehicles can be abstracted as The Vehicle Routing Problem with Pickup and Delivery and Time Windows (VRPSPDTW). The primary objective is to efficiently schedule vehicles between multiple sites to minimize the overall transportation cost. However, in practical scheduling scenarios, the demand at each site undergoes dynamic fluctuations over time, thereby presenting a formidable challenge for problem-solving. Hence, this study employs a deep reinforcement learning algorithm equipped with a pointer network, constructing a computational environment capable of accommodating the dynamic nature of demand and lifting the constraints on the number of scheduled vehicles. Furthermore, the integration of a node masking mechanism enables the acquisition of high-quality scheduling strategies for addressing the shared bicycle scheduling predicament. Two distinct scheduling strategies are proposed, one prioritizing cost optimization and the other emphasizing user demand fulfillment. Empirical findings substantiate that the proposed model surpasses other conventional algorithms in terms of performance efficacy and computational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast firewall implementations for software and hardware-based routers

Fast firewall implementations for software and hardware-base...

引用

International conference on Network Protocols

作者： Lili Qiu G. Varghese S. Suri Microsoft Research Limited UK University of California San Diego USA University of California Santa Barbara USA

ISBN: (纸本)0769514294

Routers must perform packet classification at high speeds to efficiently implement functions such as firewalls and diffserv. Classification can be based on an arbitrary number of fields in the packet header. Performing classification quickly on an arbitrary number of fields is known to be difficult, and has poor worst-case complexity. In this paper, we re-examine two basic mechanisms that have been dismissed in the literature as being too inefficient: backtracking search and set pruning tries. We find using real databases that the time for backtracking search is much better than the worst-case bound; instead of /spl Omega/((logN)/sup k-1/), the search time is only roughly twice the optimal search time. Similarly, we find that set pruning tries (using a DAG optimization) have much better storage costs than the worst-case bound. We also propose several new techniques to further improve the two basic mechanisms. Our major ideas are: (i) backtracking search on a small memory budget, (ii) a novel compression algorithm, (iii) pipelining the search, (iv) the ability to trade-off smoothly between backtracking and set pruning. We quantify the performance gain of each technique using real databases. We show that on real firewall databases our schemes, with the accompanying optimizations, are close to optimal in time and storage.

关键词： Databases Filters Diffserv networks Pipeline processing Cost function Compression algorithms Resource management Sun Access control Spine

来源：评论

学校读者我要写书评

暂无评论

Latency-Minimized Design of secure transmissions in UAV-Aided Communications

Latency-Minimized Design of secure transmissions in UAV-Aide...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiongwei Wu Qiang Li Yawei Lu H. Vincent Poor Victor C. M. Leung P. C. Ching Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong SAR China School of Info. & Comm. Eng. University of Electronic Science and Technology of China Chengdu China Department of Electrical Engineering Princeton University Princeton USA College of Computer Science & Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations to provide communication service for remote mobile users due to their high mobility and flexible deployment. However, the line-of-sight (LoS) wireless links are vulnerable to be intercepted by the eavesdropper (Eve), which presents a major challenge for UAV-aided communications. In this paper, we propose a latency-minimized transmission scheme for satisfying legitimate users' (LUs') content requests securely against Eve. By leveraging physical-layer security (PLS) techniques, we formulate a transmission latency minimization problem by jointly optimizing the UAV trajectory and user association. The resulting problem is a mixed-integer nonlinear program (MINLP), which is known to be NP hard. Furthermore, the dimension of optimization variables is indeterminate, which again makes our problem very challenging. To efficiently address this, we utilize bisection to search for the minimum transmission delay and introduce a variational penalty method to address the associated subproblem via an inexact block coordinate descent approach. Moreover, we present a characterization for the optimal solution. Simulation results are provided to demonstrate the superior performance of the proposed design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation and evaluation of a 3D OSEM and median root prior (3D OSEM-MRP) reconstruction algorithm

Implementation and evaluation of a 3D OSEM and median root p...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： V. Bettinardi E. Pagani S. Alenius M. Teras M.C. Gilardi C. Labbe M. Jacobsen K. Thielemans M. Sadki C. Morel R. Levkovitz A. Ben-Tal T. Spinks G. Mitra F. Fazio Scientific Institute H.S.Raffaele INB-CNR University of Milano-Bicocca Milan Italy Signal Proc. Laboratory Tampere University of Technology Finland TUKS PET Center Finland Geneve Cantonal Hospital Switzerland MRC-CU Hammersmith Hospital Brunei University London UK Brunei University London UK Optimization Center Technion MINERVA Haifa Israel

A 3D OSEM and Median Root Prior (3D OSEM-MRP) algorithm has been evaluated for the reconstruction of 3D PET studies. The algorithm was implemented using the software package developed during the EU project PARAPET. Evaluation was performed using experimental phantom data simulating in terms of shape and size PET brain studies. For each phantom, high (/spl sim/200 Mcounts) and low (<50 Mcounts) count statistics 3D PET data were acquired. The performances of the algorithm were evaluated by calculating simple figures of merit (e.g. contrast, coefficient of variation, activity ratio between two regions) based on the use of regions of interest. The performances of the 3D OSEM-MRP were compared with those of a "pure" 3D OSEM and of the PROMIS algorithm, using different reconstruction filters. In all the considered experimental situations, 3D OSEM-MRP shows: 1) to converge to a stable solution, 2) to be quantitatively accurate, 3) to be very effective in noise reduction, particularly for low statistics data, 4) to maintain "good" spatial resolution. Compared with the 3D OSEM and PROMIS algorithms, 3D OSEM-MRP provides better or comparable results depending on the configuration parameters used for the reconstruction of the images.

关键词： Image reconstruction Positron emission tomography performance evaluation Imaging phantoms Statistics software algorithms software packages Brain modeling Shape Filters

来源：评论

学校读者我要写书评

暂无评论

Fast firewall implementations for software-based and hardware-based routers 01

Fast firewall implementations for software-based and hardwar...

引用

Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

作者： Lili Qiu George Varghese Subhash Suri Microsoft Research UCSD Washington University

ISBN: (纸本)9781581133349

Routers must perform packet classification at high speeds to efficiently implement functions such as firewalls and diffserv. Classification can be based on an arbitrary number of fields in the packet header. Performing classification quickly on an arbitrary number of fields is known to be difficult, and has poor worst-case *** this paper, we re-examine two basic mechanisms that have been dismissed in the literature as being too inefficient: backtracking search and set pruning tries. We find using real databases that the time for backtracking search is much better than the worst-case bound; instead of Ω((logN)k-1), the search time is only roughly twice the optimal search time1. Similarly, we find that set pruning tries (using a DAG optimization) have much better storage costs than the worstcase bound. We also propose several new techniques to further improve the two basic mechanisms. Our major ideas are (i) backtracking search on a small memory budget, (ii) a novel compression algorithm, (iii) pipelining the search, (iv) the ability to trade-off smoothly between backtracking and set pruning, and (v) algorithms to effectively make use of hardware if hardware is available. We quantify the performance gain of each technique using real databases. We show that on real firewall databases our schemes, with the accompanying optimizations, are close to optimal in time and storage.

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：