检索结果-内蒙古大学图书馆

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Vehicle localisation using a single camera

Vehicle localisation using a single camera

引用

IEEE Symposium on Intelligent Vehicle

作者： Jianzhu Cui Fuqiang Liu Zhipeng Li Zhen Jia Key Laboratory of Embedded System and Service Computing supported by Ministry of Education University of Tongji Shanghai China United Technologies Research Center Shanghai China

Lots of rear end collisions due to driver inattention have been identified as a major automotive safety issue. A short advance warning can reduce the number and severity of the rear end collisions. This paper describes a Forward Collision Warning (FCW) system based on monocular vision, and presents a new vehicle detection method: appearance-based hypothesis generation, template tracking-based hypothesis verification which can remove false positive detections and automatic image matting for detection refinement. The FCW system uses time to collision (TTC) to trigger the *** order to compute time to collision (TTC), firstly, haar and adaboost algorithm is utilized to detect the vehicle; Secondly, we use simplified Lucas-Kanade algorithm and virtual edge to remove false positive detection and use automatic image matting to do detection refinement; Thirdly, hierarchical tracking system is introduced for vehicle tracking; Camera calibration is utilized to get the headway distance and TTC at last. The use of a single low cost camera results in an affordable system which is simple to install. The FCW system has been tested in outdoor environment, showing robust and accurate performance.

关键词： Cameras Vehicle detection Road accidents Radar tracking Image edge detection Calibration Radar detection Laser radar Educational technology Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Adaptation of Mismatching services Based on labelled Interface Automata

Adaptation of Mismatching Services Based on Labelled Interfa...

引用

Fifth International Conference on Semantics,Knowledge and Grid(第五届语义、知识与网格国际会议 SKG 2009)

作者： Tao Liu Guosun Zeng Department of Computer Science and Technology Tongji University Shanghai 200092 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji Universit

In today's web, more and more software and applications are wrapped as services. However interactions between services are not always perfectly completed because of mismatches among them. service mediation and adaptation problems obtain increasingly concerns. In this paper, we propose an extension of interface automata, labelled interface automata, to illustrate mismatching services and adaptation. We characterize the problem by classifying different kinds of adaptation scenarios. Then we focus on how to use labelled interface automata to illustrate the building of adaption service between mismatching services.

关键词： mismatching service adaptation interface automata

来源：评论

学校读者我要写书评

暂无评论

Tracking Salient keypoints for Human Action Recognition

Tracking Salient Keypoints for Human Action Recognition

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Hanli Wang Yun Yi Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China Department of Mathematics and Computer Science Gannan Normal University Ganzhou China

ISBN: (纸本)9781479986989

It plays an important role to recognize human actions from realistic videos in multimedia event detection and understanding. To this aim, a novel human tracking approach is proposed in this paper. Firstly, salient key points trajectories are generated to track human actions at multiple spatial scales. Then, camera motion elimination is utilized to further improve the robustness of motion trajectories. To depict human motions accurately and efficiently, the Histogram of Oriented Gradient (HOG), Histogram of Optical Flow (HOF) and Motion Boundary Histogram (MBH) are employed with the Fisher vector model being utilized to aggregate these three features. Extensive experimental results on four challenging human action video datasets demonstrate that the proposed approach is able to achieve better recognition performances in a more computationally efficient manner as compared with a number of state-of-the-art approaches.

关键词： Trajectory Videos Tracking Cameras Robustness Feature extraction Optical saturation

来源：评论

学校读者我要写书评

暂无评论

Multicast capacity scaling for cognitive networks: General extended primary network

Multicast capacity scaling for cognitive networks: General e...

引用

2010 IEEE 7th International Conference on Mobile Adhoc and Sensor systems, MASS 2010

作者： Wang, Cheng Li, Xiang-Yang Tang, Shaojie Jiang, Changjun Department of Computer Science Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China Department of Computer Science Illinois Institute of Technology Chicago IL 60616 United States

ISBN: (纸本)9781424474882

We study the capacity scaling laws for the cognitive network that consists of the primary hybrid network (PhN) and secondary ad hoc network (SaN). PhN is further comprised of an ad hoc network and a base station based (BS-based) network. SaN and PhN are overlapping in the same deployment region, operate on the same spectrum, but are independent with each other in terms of communication requirements. The primary users (PUs), i.e., the ad hoc nodes in PhN, have the priority to access the spectrum. The secondary users (SUs), i.e., the ad hoc nodes in SaN, are equipped with cognitive radios, and have the functionalities to sense the idle spectrum and obtain the necessary information of primary nodes in PhN. We assume that PhN adopts one out of three classical types of strategies, i.e., pure ad hoc strategy, BS-based strategy, and hybrid strategy. We aim to directly derive multicast capacity for SaN to unify the unicast and broadcast capacity under two basic principles: (1) The throughput for PhN cannot be undermined in order sense due to the presence of SaN. (2) The protocol adopted by PhN does not alter in the interest of SaN, anyway. Depending on which type of strategy is adopted in PhN, we design the optimal-throughput strategy for SaN. We show that there exists a threshold of the density of SUs according to the density of PUs beyond which it can be proven that: (1) when PhN adopts the pure ad hoc strategy or hybrid strategy, SaN can achieve the multicast capacity of the same order as it is stand-alone;(2) when PhN adopts the BS-based strategy, SaN can asymptotically achieve the multicast capacity of the same order as if PhN were absent, if some conditions of the relations among the number of SUs, PUs, the destinations of each multicast sessions in SaN, and the base stations in PhN hold. ©2010 IEEE.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

Social incentive policies to engage commercial building occupants in demand response

Social incentive policies to engage commercial building occu...

引用

2014 IEEE International Conference on Automation Science and Engineering, CASE 2014

作者： Li, Sisi Deng, Kun Zhou, Meng Chu Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07012 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai201804 China Coordinated Science Laboratory University of Illinois at Urbana-Champaign UrbanaIL61801 United States

Occupants' comfort is the primary target in a building operation. However their efforts are often neglected and ruled out from traditional control strategies of energy-efficient building management systems. Occupant-engaged control strategies have recently attracted many research attentions and demonstrated great potentials for energy saving. With them, occupants' behavior is incorporated into the closed-loop control methods in which their initiatives actively contribute to building services and energy utility by explicitly expressing their preferences. This work proposes an occupant-engaged demand response (DR) strategy for building automation in which occupants are actively engaged to adapt their energy consumption in response to incentive opportunities designed by facility managers. A model-based study and a Nash-Equilibrium-based solution are provided to assist facility managers with the design of social incentive policies to promote occupant participation, along with the guarantee of lucrativeness for a DR event. © 2014 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Algorithm for Location based on Distance-Loss Model in Complex Environment

A Novel Adaptive Algorithm for Location based on Distance-Lo...

引用

IEEE International Conference on Computer Supported Cooperative Work in Design

作者： Hao Fang Fei Li Feng Zhang Min Liu Weiming Shen School of Electronic and Information Engineering Tongji University Department of Computer Zhejiang University City College The Key Laboratory of Embedded System and Service Computing Tongji University

ISBN: (纸本)9781509019168

Location based services are the hottest applications on mobile device nowadays. Indoor wireless position is the key technology to enable location based service to work well indoors, where Global Position system normally couldn't work. The main tendency of indoor wireless position is based on Bluetooth and RSSI (radio signal strength indicator). RSSI is the key parameter for wireless position. But values of RSSI are affected by environment factors easily. Because of this reason, results got from the indoor location technology are usually imprecise and unacceptable. In this paper, an adaptive algorithm based on Distance-Loss model in complex environment is introduced to deal with such problems. The algorithm makes the model adapt to the environment by several parameters which are not influenced by environment. The stability and the accuracy of the algorithm is evidenced by a series of strict experiences.

关键词： Complex environment Distance-loss model RSSI Self-adaptation Location

来源：评论

学校读者我要写书评

暂无评论

An efficient method for skyline recommendation in distributed networks

引用

Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology 2015年第5期37卷 1214-1219页

作者： Huang, Zhen-Hua Zhang, Bo School of Electronics and Information Tongji University Shanghai201804 China Key Laboratory of Embedded System and Service Computing Tongji University Shanghai201804 China College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai200234 China

Based on distributed networks of the Super-Peer Architecture (SPA), this paper proposes Efficient Method for Skyline Recommendation in Distributed Networks (EMSRDN), to handle u skyline recommendation instructions by prestore w skyline snapshots. The EMSRDN method fully considers the characteristic of storage and communication of SPA networks, and uses the map/reduce distributed computation model. The EMSRDN algorithm can fast produce the optimal w skyline snapshots through the phase of heuristically constructing the initial set of snapshot. The detailed theoretical analyses and extensive experiments demonstrate that the proposed EMSRDN algorithm is both efficient and practical. ©, 2015, Science Press. All right reserved.

关键词： Information services

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of dual-arm cluster tools for wafer fabrication with revisiting

Modeling and analysis of dual-arm cluster tools for wafer fa...

引用

2011 7th IEEE International Conference on Automation Science and Engineering, CASE 2011

作者： Qiao, Yan Wu, NaiQi Zhou, MengChu Department of Industrial Engineering School of Mechatronics Engineering Guangdong University of Technology Guangzhou 510006 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102-1982 United States

ISBN: (纸本)9781457717307

Some wafer fabrication processes are repeated processes, e.g. atomic layer deposition (ALD) process. For such processes, the wafers need to visit some processing modules for a number of times, which complicates the cycle time analysis. This paper studies the cycle time analysis problem for such processes. With a Petri net model, it is found that such processes contain local cycles involving only the revisiting PMs and global cycles involving both revisiting and non-revisiting PMs. The process switches between these two types of cycles such that the process never reaches a steady state. Based on this finding, the mechanism underlying such processes is revealed and analytical expressions are given for the calculation of their cycle time. Illustrative examples are presented to show the application of the proposed approach. © 2011 IEEE.

关键词： Atomic layer deposition

来源：评论

学校读者我要写书评

暂无评论

A Cloudedge-Combined Data Placement Strategy Based On User Access Regions

A Cloudedge-Combined Data Placement Strategy Based On User A...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Eryang Cao Pengwei Wang Chungang Yan Changjun Jiang The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science and Technology Donghua University Shanghai China

ISBN: (数字)9781665422321

ISBN: (纸本)9781665446662

To improve the availability of data in the cloud and avoid vendor lock-in risk, multi-cloud storage is attracting more and more attentions. However, accessing data from the cloud usually has some disadvantages such as higher latency and more bandwidth-consuming. Edge computing, which has become popular in recent years, could effectively solve the above problems while it usually reduces availability. Storage only in the cloud or edge environment is limited by many factors. To this end, we build mathematical model which is abstracted from real access mode of users in consideration of multi-cloud and edge. This paper presents a method combined NSGAII with multi-group method which has better ability of global search to help users determine cloud and edge services to store and access data object. A large number of experiments using real service provider information demonstrate that the proposed algorithm outperforms existing methods and effectiveness of it.

关键词： Cloud computing Data privacy Search problems Data models Delays Mathematical model Edge computing

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：