检索结果-内蒙古大学图书馆

作者： Zhu, Hu Xu, Guoxia Liu, Lu Deng, Lizhen Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunication Nanjing China Department of Computer Science Norwegian University of Science and Technology Gjovik Norway National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and Telecommunication Nanjing China

Smoke has a very bad effect on the outdoor vision system. Not only are the videos with poor visual effects obtained, but also the quality and structure of the videos are reduced. In this paper, we propose a video smoke removal method based on low-rank tensor completion via spatial-temporal continuity constraint. The proposed method is based on the smoke mixing model and consider the sparseness of smoke and the global and local consistency of clean video. Then, the optimal solution of the smoke removal algorithm model is quickly realized by the Alternating Direction Method of Multiplier. Finally, we evaluate the experiment results of real-world data and simulated data from the visual effects and objective indicators. And the experiment results show that our proposed algorithm can achieve better smoke removal results. © 2021 John Wiley & Sons, Ltd.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Research on image compression and transmission mechanism for wireless multimedia sensor networks

Research on image compression and transmission mechanism for...

引用

2nd Annual Conference on Electrical and Control Engineering, ICECE 2011

作者： Xiao, Fu Zhang, Pan Sun, Li-Juan Wang, Jing Wang, Ru-Chuan College of Computer Nanjing University of Posts and Telecommunications Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing China

ISBN: (纸本)9781424481637

A image compression and adaptive smoothing transmission mechanism for wireless multimedia sensor networks. Goal of our work is to minimize image distortion with the multimedia sensor network conditions varying constantly. Method which uses Set Partitioning in Hierarchical Trees (SPIHT) algorithm based on lifting wavelets for real-time images compression is first presented, and then a framework for realtime image delivery self-adapting over a TCP-friendly connection is depicted. In the context of this scheme, an adaptive smoothing algorithm is also developed based on the predicted available bandwidth to stream real-time image over the TCP-friendly rate control (TFRC) Protocol. Through simulation experiments, it has been shown that this adaptive algorithm performs for a wide-range of the bandwidth scenarios, and a smooth TCP-friendly real-time image transfer for wireless multimedia sensor networks can be accomplished by this proposed scheme. © 2011 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

A trusted QoS architecture for wireless multimedia sensor networks

A trusted QoS architecture for wireless multimedia sensor ne...

引用

作者： Ye, Qian Wu, Meng Wang, Yu Fei College of Computer Nanjing University of Posts and Telecommunications China Key Lab of 'Broadband Wireless Communication and Sensor Network Technology' of Ministry of Education College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications China Research Institute of Information Technology and Communication China Electric Power Research Institute China

ISBN: (纸本)9783038351399

Developing trusted QoS architecture is important for wireless multimedia sensor networks considering various applications with different QoS requirements. First, the diverse multimedia traffic were analyzed and classified based on application requirements, service model, and multimedia coding method in wireless multimedia sensor networks. And the QoS requirements related to the multimedia traffic were also discussed. Then, a trust management framework was designed for cluster-based wireless multimedia sensor networks. The proposed framework can be used to next-hop selection in secure routing protocol. Finally, trusted QoS architecture was proposed. In the architecture, QoS manager observes and maintains information about QoS factors, and also responsible for QoS scheduling based on different QoS requirements. Trust Manager observes and maintains information about trust factors in WMSNs, and also responsible for trust computing based on different methods of trust factors aggregation. © (2014) Trans Tech Publications, Switzerland.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Finformer: A Static-dynamic Spatiotemporal Framework for Stock Trend Prediction

Finformer: A Static-dynamic Spatiotemporal Framework for Sto...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Zu, Yi Mi, Jiacong Song, Lingning Lu, Shan He, Jieyue Southeast University School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Nanjing China Southeast University School of Software Engineering Nanjing China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd Nanjing China

ISBN: (纸本)9798350324457

The core of quantitative investment lies in predicting future trends in stock prices. The future trend of a stock is closely related to the industry it belongs to and its relationship with other stocks. Although some research has focused on stock trend prediction in recent years, most studies have only considered the stock's own time series feature, neglecting the spatial features between stocks. Some research has incorporated spatial information, but typically only considered predefined static relationships. At the same time, capturing dynamic spatial information in the market has been a long-standing challenge. Thus, we propose a spatio-temporal model, Finformer, in order to go beyond traditional time series models. We designed a sparse static-dynamic transformer to capture dynamic market spatial information as it changes over time and combined predefined relationships to extract highly correlated spatial features in the stock market. To effectively integrate spatial and temporal features, we introduced an adaptive spatio-temporal fusion module that dynamically fuses spatio-temporal features based on market conditions at different periods. Experiments on two real-world stock market datasets show that our proposed model outperforms the state-of-the-art baselines in the signal-based and portfolio-based metrics, which are widely concerned in the financial field. Ablation study and hyper-parameter study further reveal the effectiveness of each module in the model and the impact of hyper-parameters. The code will be made publicly available. 1 © 2023 IEEE.

关键词： computational finance deep learning stock trend prediction transformer

来源：评论

学校读者我要写书评

暂无评论

Co-whitening of i-vectors for short and long duration speaker verification 19

Co-whitening of i-vectors for short and long duration speake...

引用

19th Annual Conference of the International Speech communication, INTERSPEECH 2018

作者： Xu, Longting Lee, Kong Aik Li, Haizhou Yang, Zhen Department of Electrical and Computer Engineering National University of Singapore Singapore Data Science Research Laboratories NEC Corporation Japan Broadband Wireless Communication and Sensor Network Technology Key Lab Nanjing University of Posts and Telecommunications China

An i-vector is a fixed-length and low-rank representation of a speech utterance. It has been used extensively in text-independent speaker verification. Ideally, speech utterances from the same speaker would map to an unique i-vector. However, this is not the case due to some intrinsic and extrinsic factors like physical condition of the speaker, channel difference, noise and notably the duration of speech utterances. In particular, we found that i-vectors extracted from short utterances exhibit larger variance than that of long utterances. To address the problem, we propose a co-whitening approach, taking into account the duration, while maximizing the correlation between the i-vectors of short and long duration. The proposed co-whitening method was derived based on canonical correlation analysis (CCA). Experimental results on NIST SRE 2010 show that co-whitening method is effective in compensating the duration mismatch, leading to a reduction of up to 13.07% in equal error rate (EER). © 2018 International Speech communication Association. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Salient object detection via background contrast 40

Salient object detection via background contrast

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Zhou, Quan Li, Nianyi Chen, Jianxin Cai, Shu Latecki, Longin Jan Key Lab of Ministry of Education for Broad Band Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications China Department of Computer and Information Sciences University of Delaware Newark United States Department of Computer and Information Sciences Temple University Philadelphia United States

ISBN: (纸本)9781467369978

This paper addresses the problem of salient object detection. We introduce a novel framework which aims to automatically identify salient regions in natural images based on two key ideas. The first one is to consider the statistical spatial distribution of saliency and non-saliency regions as two complementary processes. The second one is based on the assumption that contrast saliency with respect to background regions outperforms those with respect to entire image. Experimental results demonstrate the effectiveness of our approach over 12 state-of-the-art models. © 2015 IEEE.

关键词： background contrast salient object detection spatial distribution

来源：评论

学校读者我要写书评

暂无评论

Robust transceiver design based on interference alignment for multi-user multi-cell mimo networks with channel uncertainty

arXiv

引用

arXiv 2017年

作者： Xie, Xianzhong Yang, Helin Vasilakos, Athanasios V. Chongqing Key Lab of Computer Network and Communication Technology Chongqing University of Posts and Telecommunications Chongqing China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Computer and Telecommunications Engineering University of Western Macedonia Greece

In this paper, we firstly exploit the inter-user interference (IUI) and inter-cell interference (ICI) as useful references to develop a robust transceiver design based on interference alignment for a downlink multi-user multi-cell multiple-input multiple-output (MIMO) interference network under channel estimation error. At transmitters, we propose a two-tier transmit beamforming strategy, we first achieve the inner beamforming direction and allocated power by minimizing the interference leakage as well as maximizing the system energy efficiency, respectively. Then, for the outer beamformer design, we develop an efficient conjugate gradient Grassmann manifold subspace tracking algorithm to minimize the distances between the subspace spanned by interference and the interference subspace in the time varying channel. At receivers, we propose a practical interference alignment based on fast and robust fast data projection method (FDPM) subspace tracking algorithm, to achieve the receive beamformer under channel uncertainty. Numerical results show that our proposed robust transceiver design achieves better performance compared with some existing methods in terms of the sum rate and the energy *** Codes H.4.3 Copyright © 2017, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Repurposed Drugs against SARS-CoV-2 based on Text Mining and Molecular Docking Analysis 23

Prediction of Potential Repurposed Drugs against SARS-CoV-2 ...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Jie Zhou Yi-Qing Xu Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology China

ISBN: (纸本)9798400707674

Many research papers focusing the relationships between drugs and coronavirus-related protein interactions are indexed in the PubMed database. These studies provide a reference for predicting potential repurposed drugs against SARS-CoV-2. Drug repurposing, the most efficient strategy to quickly deploy new effective therapeutic drugs against SARS-CoV-2, can shorten the time and reduce the cost compared to de novo drug discovery. The purpose of this study was to predict potential repurposed drugs and drug pairs against SARS-CoV-2 using text mining and molecular docking *** first constructed a coronavirus-related protein names list and a drug names list using the relevant protein and drug databases. We also constructed a qualifier list. A crawler program was implemented to retrieve the desired parts from the relevant papers in the PubMed database using records from the three query lists. Based on these extracted parts, we constructed a document set, a document drug names set, and a document protein names set. Then, we used the method proposed in our previous work to calculate the document vector of each document in the document set and the TF, IDF, and TF–IDF values. We calculated the vectors of each drug and protein in the document drug names set and document protein names set based on the document vectors. The cosine similarity between the protein vector and drug vector was calculated and the score of the pair of protein and drug was defined by the cosine similarity. Next, we selected the protein–drug pairs that scored above a given threshold as the predicted interactions for coronavirus-related protein–drug pairs and then extracted all the drugs from these predicted interactions and combined them to form distinct drug pairs. Finally, the drugs with PubChem 3D structure were simulated by a molecular docking tool with the four recently identified important SARS-CoV-2 proteins, and the drug pairs were simulated by the molecular docking tool with the SARS-CoV-2

关键词： SARS-CoV-2 coronavirus drug repurposing molecular docking text mining

来源：评论

学校读者我要写书评

暂无评论

A trust information search model based on simulated annealing in P2P network

引用

Information technology Journal 2013年第15期12卷 3289-3293页

作者： Xu, He Huang, Han-Chen Wang, Ruchuan College of Computer Nanjing University of Posts and Telecommunications Jiangsu Nanjing 210003 China Jiangsu High Technology Research Key Laboratory Wireless Sensor Networks Jiangsu Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Jiangsu Province Nanjing 210003 China Department of Leisure Management Yu Da University Miaoli 36143 Taiwan

Trust information search algorithm is one of the most important components of P2P trust model. Considering the large number of nodes and the wide range of information each node contains in P2P network, efficient search algorithm can improve the network efficiency and attract more users to join P2P network. Moreover, efficient search algorithm can also let each node in the network know the current state of the network in time. This study designs an SABS (Simulated Annealing Based Search) model based on Simulated Annealing (SA) to search the trust information in P2P network. Simulation results show that this model can obtain the optimal path and the shortest distance of the network with appropriate parameter values. © 2013 Asian network for Scientific Information.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A load-balanced data aggregation scheduling for duty-cycled wireless sensor networks

A load-balanced data aggregation scheduling for duty-cycled ...

引用

2012 4th IEEE International Conference on Cloud Computing technology and Science, CloudCom 2012

作者： Chen, Zhengyu Yang, Geng Chen, Lei Xu, Jian Wang, Haiyong Key Lab of Broadband Wireless Communication and Sensor Network Technology of Ministry of Education Nanjing University of Posts AndTelecommunications Nanjing 210046 China College of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing 210046 China School of Information Technology Jinling Institute of Technology Nanjing 211169 China

ISBN: (纸本)9781467345095

To bridge the gap between limited energy supplies of the sensor nodes and the system lifetime, duty-cycle Wireless Sensor networks (WSNs) with data aggregation are studied in this paper. We proposed a load-balanced and latency-efficient data aggregation scheduling for duty-cycled WSNs. A shortest path tree (SPT) is used as the routing structure for data aggregation scheduling. In SPT, parent-children assignments are well-designed to assign nodes from level h+1 to the parents at level h such that every parent has a balanced load, while reducing the sleep latency which is a period of time for a sender to wait for its parent to be active. Finally, through the simulation and comparisons, we prove the effectiveness of our approach. © 2012 IEEE.

关键词： Scheduling

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：