检索结果-内蒙古大学图书馆

2012 International Conference on Web Information Systems and Mining, WISM 2012

作者： Wu, Rong Wang, Ruchuan Sha, Chao Qian, Liyang College of Computer Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9783642334689

Wireless multimedia sensor networks consist of unattended multimedia nodes with limited storage, energy and computation and communication capabilities. And energy is the most crucial resource for nodes. Clustering technique has been proven to be an effective approach for datagathering in wireless multimedia sensor networks. Therefore, this paper presents a novel clustering mechanism based on image-oriented correlation coefficient to reduce redundancy transmission so as to conserve network energy. And the aim is achieved through taking advantage of the correlation coefficient of captured images and RSSI value of nodes to avoid excessive computation and transmission. Moreover, a new cluster header election method is also presented to make the network's load balance on energy. The simulation results show that the correlation coefficient threshold greatly affects the number and average size of clusters. And compared with another clustering algorithm based on overlapping FoVs, our clustering mechanism is more effective in prolonging network lifetime. © Springer-Verlag Berlin Heidelberg 2012.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

BrainPST: Pre-training Stacked Transformers for Dynamic Brain Functional network Analysis

BrainPST: Pre-training Stacked Transformers for Dynamic Brai...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jinlong Hu Yangmin Huang Yi Zhuo Shoubin Dong Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

Deep learning methods have been applied for dynamic brain functional network analysis recently. However, they are usually restricted by the complex spatio-temporal dynamics and the limited labeled data. In this paper, we proposed a stacked Transformer neural network, namely BrainPST, to capture spatio-temporal patterns for dynamic brain functional network classification. BrainPST model integrated spatial and temporal information by stacking two Transformers: one for learning snapshot networks and the other for learning sequence of functional connections. Unlike recent models, BrainPST was designed to pre-train the stacked Transformer network by leveraging unlabeled existing brain imaging data. A pre-training framework with designed pre-training strategies was proposed to learn general spatio-temporal representations from the unlabeled brain networks, and to fine-tune the pre-trained model in downstream tasks. BrainPST is a conceptually simple and effective model. The results of experiments showed the BrainPST model without pre-training achieved comparative performance with the recent models, and the pre-trained BrainPST obtained new state-of-the-art performance. The pre-trained BrainPST improved 3.92% of AUC compared with the model without pre-training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer and Snowball Graph Convolution Learning for Brain Functional network Analysis

Transformer and Snowball Graph Convolution Learning for Brai...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jinlong Hu Yangmin Huang Shoubin Dong School of Computer Science and Engineering Guangdong Key Lab of Communication and Computer Network South China University of Technology Guangzhou China

Advanced deep learning methods, especially graph neural networks (GNNs), are increasingly expected to learn from brain functional network data and predict brain disorders. In this paper, we proposed a novel Transformer and snowball encoding networks (TSEN) for brain functional network classification, which introduced Transformer architecture with graph snowball connection into GNNs for learning whole-graph representation. TSEN combined graph snowball connection with graph Transformer by snowball encoding layers, which enhanced the power to capture multi-scale information and global patterns of brain functional networks. TSEN also introduced snowball graph convolution as position embedding in Transformer structure, which was a simple yet effective method for capturing local patterns naturally. We evaluated the proposed model by two large-scale brain functional network datasets from autism spectrum disorder and major depressive disorder respectively, and the results demonstrated that TSEN outperformed the state-of-the-art GNN models and the graph-transformer based GNN models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSEN: TRANSFORMER AND SNOWBALL GRAPH CONVOLUTION LEARNING FOR BRAIN FUNCTIONAL network CLASSIFICATION

arXiv

引用

arXiv 2023年

作者： Hu, Jinlong Huang, Yangmin Dong, Shoubin Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Content Centric networking: A New Approach to Big Data Distribution

引用

ZTE communications 2013年第2期11卷 3-10页

作者： Yi Zhu Zhengkun Mi Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications School of Computer Science and Telecommunication Engineering University of Jiangsu

In this paper, we explore network architecture anal key technologies for content-centric networking （CCN）, an emerging networking technology in the big-data era. We descrihe the structure anti operation mechanism of tl CCN node. Then we discuss mobility management, routing strategy, and caching policy in CCN. For better network performance, we propose a probability cache replacement policy that is based on cotent popularity. We also propose and evaluate a probability cache with evicted copy-up decision policy.

关键词： big data content-centric networking caching policy, mobility management routing strategy

来源：评论

学校读者我要写书评

暂无评论

Deep feature guided image retargeting 34

Deep feature guided image retargeting

引用

34th IEEE International Conference on Visual communications and Image Processing, VCIP 2019

作者： Wu, Jinan Xie, Rong Song, Li Liu, Bo Shanghai Jiao Tong University Institute of Image Communication and Network Engineering China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China University of Technology School of Computer Science Sydney Australia

ISBN: (纸本)9781728137230

Image retargeting is the technique to display images via devices with various aspect ratios and sizes. Traditional content-Aware retargeting methods rely on low-level features to predict pixel-wise importance and can hardly preserve both the structure lines and salient regions of the source image. To address this problem, we propose a novel adaptive image warping approach which integrates with deep convolutional neural network. In the proposed method, a visual importance map and a foreground mask map are generated by a pre-Trained network. The two maps and other constraints guide the warping process to yield retargeted results with less distortions. Extensive experiments in terms of visual quality and a user study are carried out on the widely used RetargetMe dataset. Experimental results show that our method outperforms current state-of-Art image retargeting methods. © 2019 IEEE.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

An expanding ring prediction and location aided AODV routing algorithm

An expanding ring prediction and location aided AODV routing...

引用

2011 International Conference on Information technology, computer Engineering and Management Sciences, ICM 2011

作者： Cheng, Chunling Hao, Jingbo Zhang, Dengyin College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab. of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China

ISBN: (纸本)9780769545226

On the battlefield, the cooperative fighting and communication among combat vehicles require higher service level of real-time transmission. Combat vehicles' fast moving and the links' frequent disruption lead to the increase of packet loss rate, packet delay and routing control overhead ratio. This paper proposes an expanding ring prediction and location aided AODV routing algorithm. It improves AODV routing protocol from both routing discovery and maintenance phases. In the rouing discovery phase, the algorithm limits the scope of sending RREQ through predicting the topology ring;and during the route maintenance phase, it predicts the motion range of destination node with the information provided by GPS to avoid blindness routing. The simulation results show that the proposed routing algorithm can greatly cut down the overload of combat vehicular network, improve the routing delay and reduce packet loss rate. It can meet the real-time requirements of the service transmission among combat vehicles and also improve the performance of the combat vehicular network. © 2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Gossip-based indexing ring topology for 2-dimension spatial data in overlay networks

Gossip-based indexing ring topology for 2-dimension spatial ...

引用

2012 International Workshop on Information and Electronics Engineering, IWIEE 2012

作者： Zou, Z.Q. Wang, Y. Hu, B. Wang, R.C. College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab. of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China

Overlay networks are used widely in the Internet, such as retrieval and share of files, multimedia games and so on. However, in distributed system, the retrieval and share of 2-dimension spatial data still have some difficult problems and can not solve the complex retrieval of 2-dimension spatial data efficiently. This article presents a new indexing overlay networks, named 2D-Ring, which is the ring topology based on gossip for 2-dimension spatial data. The peers in our overlay networks exchange the information periodically and update each local view by constructing algorithm. 2-dimension spatial data is divided by quad-tree and mapped into control points, which are hashed into 2D-Ring by SHA-1 hash function. In such way, the problem of 2-dimension spatial data indexing is converted to the problem of searching peers in the 2D-Ring. A large of extensive experiments show that the time complexity of constructing algorithm of 2D-Ring can reach convergence logarithmically as a function of the network size and hold higher hit rate and lower query delay. © 2011 Published by Elsevier Ltd.

关键词： Overlay networks

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficiency Based Resource Allocation for D2D communication and Cellular networks

Energy-Efficiency Based Resource Allocation for D2D Communic...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Layanah AlWreikat Rong Chai Osama M.F. Abu-Sharkh Chongqing University of Posts and Telecommunications Chongqing Chongqing CN Key Lab of Mobile Communication Technology Chongqing University of Posts and Telecommunications Chongqing China Department of Computer Engineering Princess Sumaya University for Technology Amman Jordan

In this paper, we present an energy efficiency based resource allocation scheme for a heterogeneous integrated network consisting of device-to-device (D2D) communication system and a cellular communication system. We study the power allocation and network mode selection scheme for users' coexistence of both systems in terms of energy efficiency maximization of the heterogeneous network (Het Net). The formulated optimization problem is a fractional non-convex problem, the standard convex optimization techniques cannot be applied directly. With the use of fractional programming and dual problem formulation, we are able to solve the non-convex problem, taking into consideration the minimum data rate required, the minimum received power and the maximum device dependent radiated power constraints. Results show that the optimal solution can be achieved with a relatively small number of iterations. Also results show that the increase in both the number of users and system data rate does not necessarily lead to an increase in the energy efficiency of the network.

关键词： Resource management Transmitters Energy efficiency Optimization Bandwidth Power demand Linear programming

来源：评论

学校读者我要写书评

暂无评论

Unifying and Improving Graph Convolutional Neural networks with Wavelet Denoising Filters 23

Unifying and Improving Graph Convolutional Neural Networks w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Li, Xiaona Han, Huijin Yan, Xiaoran Sun, Lu Ning, Zhaolong Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN's capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets. © 2023 ACM.

关键词： Convolution

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：