检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data Analysis (ICBDA)

作者： Xinyuan Sui Yaying Zhang Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

Traffic congestion in urban areas has become a critical issue in the world. As the limits of road topology and the influence of residents' commuting periodic patterns, the same part of the road network usually gets congested, and there are similar propagation paths when congestion occurs in an area. This paper aims to model the congestion propagation phenomenon and further discover the congestion propagation paths that frequently appeared. To this end, we propose an algorithm which analyzes the correlations between congestions on different road segments and constructs a congestion propagation graph to reflect the dynamic process of congestions. The traffic flow entropy is novelty considered to identify the potential essential road segment in traffic congestions. We adopt the Jaccard correlation to estimate the parameters employed. The experiments with the road network in Beijing, China and real-world GPS trajectory data indicate that our approach can reveal congestion propagation patterns and the dynamic process of congestion propagation.

关键词： Correlation Network topology Roads Heuristic algorithms Urban areas Trajectory Topology

来源：评论

学校读者我要写书评

暂无评论

Local-directed network coding in vehicular ad-hoc networks

Local-directed network coding in vehicular ad-hoc networks

引用

IEEE International Symposium on Intelligent Signal Processing and Communication systems (ISPACS)

作者： Haojie Luo Dongdong Zhang Chen Ye The Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

In this paper, we proposed a novel network coding method called local-directed network coding to improve the throughput of the vehicular ad-hoc network. Different from other vehicular network coding methods, we consider the direction of packet transmission. In detail, the intermediate node selects one main packet and some sub-packets from forwards and backwards sending queues, and then encodes these packets into one packet to broadcast. Simulation results show that our approach can efficiently improve the throughput of application layer in vehicular networks.

关键词： Encoding Buffer storage Accidents Vehicles Streaming media Artificial neural networks Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Image Retrieval Based on Manifold Learning and Incorporate Clustering

Image Retrieval Based on Manifold Learning and Incorporate C...

引用

GCIS, WRI Global Congress on Intelligent systems

作者： Jianzhu Cui Fuqiang Liu Zhipeng Li Jing Li The Key Laboratory of Embedded System and Service Computing University of Tongji Shanghai China

This paper presents a novel unsupervised learning framework named image retrieval based on manifold learning and incorporate clustering. The dimensionality of image descriptors used in image retrieval applications is quite high. Given a query image, our algorithm first makes use of manifold learning (LPP) for dimensionality reduction and manifold ranking algorithm to explore the relationship among all the data points in the feature space, and then measures relevance between the query and all the images in the database accordingly. Then we use the similarities among target images for improving the performance of the image retrieval systems by cluster-based retrieval of images by unsupervised learning. Our algorithm retrieves image clusters as retrieval results by applying K-means clustering algorithm to a collection of images collected by manifold ranking algorithm. Experimental results on a general-purpose image database show that our algorithm attains a significant improvement over existing systems.

关键词： Image retrieval Clustering algorithms Feedback Unsupervised learning Support vector machines Support vector machine classification Image databases Content based retrieval Intelligent systems Laboratories

来源：评论

学校读者我要写书评

暂无评论

Reliable web services selection based on finite state machine model

引用

Information Technology Journal 2011年第9期10卷 1662-1672页

作者： Shen, Hongjie Ding, Zhijun Chen, Hongzhong Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai 200092 China

Dynamically selecting suitable Web services (WSs) is crucial to users in Web services Composition (WSC). Generally, most works regard a Web service (WS) as the basic unit and compose the composite WS (CWS) end to end. However, a WS may comprise multiple operations that are invoked in sequence and the selection of WSs according to the model still is a NP problem. In this study, the WSs consist of some operations and then WSs selection problem is formalized as a Finite State Machine (FSM) process. This study proposed an algorithm to create the WSC Tree (WSCT), in which each path from root to leaf node is a feasible WSC execution path. Then, a heuristic algorithm is proposed to realize the selection of WSs based on the WSCT. The advantage of heuristic algorithm is that it can address the selection problem without traversing the whole WSCT but it still spends much time in the construction of the WSCT. So, in order to further decrease the time of selection, a backtracking algorithm is presented to select a feasible execution path without generating WSCT. At last, experiments show that heuristic algorithm is more effective than exhaustive method and the backtracking algorithm spend the less time than heuristic algorithm, the reliability of WSC execution path selected by backtracking algorithm can satisfy the requirement of users. So, this study proposed an algorithm to select a feasible WSC execution path within a reasonable time. © 2011 Asian Network for Scientific Information.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Counting Pedestrian in Crowded Subway Scene

Counting Pedestrian in Crowded Subway Scene

引用

Congress on Image and Signal Processing, CISP

作者： Keju Zu Fuqiang Liu Zhipeng Li Key Laboratory of Embedded System and Service Computing University of Tongji Shanghai China

When the high occlusion occurs in crowded scene, face detection is a better substitute for detecting pedestrian. In this paper, we present a novel crowd analysis method based on discriminative descriptor of faces and support vector machine (SVM) ensemble. Through manipulating the input features in the same sample set, the different input features of faces are extracted to train two SVM classifiers. The classification scores of two generated classifiers are combined adaptively to make a collective decision. The first SVM, as the principal classifier gives out most of face hypotheses, while the second SVM serves as secondary one to rejecting the false positive. We present experiment to test the proposed method in crowded subway video, and the result shows that the SVM ensemble outperforms the single SVM in counting the pedestrian.

关键词： Layout Support vector machines Support vector machine classification Face detection Histograms Surveillance Humans Lighting Cameras Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Real-Time Communication Method for mHealth Base on Extended XMPP Protocol

Real-Time Communication Method for mHealth Base on Extended ...

引用

The 9th International Conference on Wireless Communications,Networking and Mobile computing(WICOM 2013)

作者： Chenjie Shi Yu Fang The Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji University

Considering characteristic of mHealth communication and problems of existing methods, this paper presents a real-time communication method for mHealth based on extended XMPP protocol. The method can maintain the role status efficiently and reduce data latency during the communication process. Meanwhile, it can be extended flexibly to meet increasing communication demands of mHealth services. Furthermore, a system framework is presented to support telemonitoring scene. Finally, system implementation and feasibility tests verify the effectiveness of the method and framework.

关键词： mHealth XMPP Protocol Real-Time Communication

来源：评论

学校读者我要写书评

暂无评论

An Efficient Webpage Classification Algorithm Based on LSH

An Efficient Webpage Classification Algorithm Based on LSH

引用

International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2015

作者： Junjun Liu Haichun Sun Zhijun Ding The Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji University

With the explosive growth of Internet information,it is more and more important to fetch real-time and related *** it puts forward higher requirement on the speed of webpage classification which is one of common methods to retrieve and manage *** get a more efficient classifier,this paper proposes a webpage classification method based on locality sensitive hash *** which,three innovative modules including building feature dictionary,mapping feature vectors to fingerprints using Localitysensitive hashing,and extending webpage features are *** compare results show that the proposed algorithm has better performance in lower time than the na?ve bayes one.

关键词： Explosive growth Webpage classification Locality-sensitive hashing Fingerprint Extending webpage features

来源：评论

学校读者我要写书评

暂无评论

Accelerating Support Vector Machine Learning with GPU-Based MapReduce

Accelerating Support Vector Machine Learning with GPU-Based ...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Tianyao Sun Hanli Wang Yun Shen Jun Wu Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

ISBN: (纸本)9781479986989

With the exploding growth of data, the computational complexity required by learning Support Vector Machine (SVM) lays a heavy burden on real-world applications. To address this issue, parallel computational techniques can be employed such as the Graphics Processing Units (GPUs) and MapReduce model. As it is well known, GPUs are microprocessors on a multi-core architecture which reveal high performance in mass data parallel computing, and MapReduce allows computational tasks to be divided into a plurality of parts, distributed to various computing nodes and combined on a single node. In this paper, we propose a GPU-based MapReduce framework to accelerate SVM learning by jointly utilizing the parallel computing power of GPU and MapReduce. Extensive experimental results have verified the effectiveness and efficiency of the proposed approach.

关键词： Graphics processing units Support vector machines Kernel Training Optimization Acceleration Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Vehicle to Vehicle and Roadside Sensor Communication for Intelligent Navigation

Vehicle to Vehicle and Roadside Sensor Communication for Int...

引用

International Conference on Wireless Communications, Networking and Mobile computing (WiCom)

作者： Rongyan Xia Chen Ye Dongdong Zhang Key Laboratory of Embedded System and Service Computing University of Tongji Shanghai China

Hybrid sensor network technology is a key component of future ITS applications. In this paper, we propose a hybrid architecture that combined VANETs and roadside WSNs for intelligent navigation. Different from traditional ITS application, Sensors in WSNs and VANETs are used to perceive and exchange roadside and vehicular information to support the intelligent navigating decision process. We firstly give the system and protocol architecture, and then we discuss the scenarios and use cases of our system in intelligent navigation. After that, we describe the software and hardware implementation of our prototype, conduct a simulation on the discussed scenarios, and present a detailed data communication experimental result to prove the feasibility of our prototype.

关键词： Vehicles Wireless sensor networks Navigation Data communication Roads Prototypes Path planning

来源：评论

学校读者我要写书评

暂无评论

Vehicle classification based on the fusion of deep network features and traditional features

Vehicle classification based on the fusion of deep network f...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Hua Qian Yaying Zhang Chunmei Liu Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

Consider to the defect of traditional features which have high empirical components. A vehicle classification algorithm based on the fusion of higher-layer features of a deep network and traditional features was proposed. Firstly, the traditional features of PHOG and LBP-EOH were extracted. Secondly, the higher-layer features excavated from the vehicle pictures by deep belief networks were added, making these three kinds of features together by feature fusion. Finally, support vector machine is used to train and classify the vehicle. When the number of training samples is large enough, the algorithm has a significant effect compared to those with traditional features. It can achieve the accuracy of 95% in the six categories of vehicles.

关键词： Vehicles Support vector machines Feature extraction Algorithm design and 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：