检索结果-内蒙古大学图书馆

Review on Video Object Tracking Based on Deep Learning

Journal of New Media 2019年第2期1卷 63-74页

作者： Fangming Bi Xin Ma Wei Chen Weidong Fang Huayi Chen Jingru Li Biruk Assefa College of Computer Science and Technology China University of Mining and TechnologyXuzhou221116China Mine Digitization Engineering Research Center of the Ministry of Education China University of Mining and TechnologyXuzhou221116China Key Laboratory of Wireless Sensor Network&Communication Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai201899China Information Communication Technology Department Wollo UniversityDessie EthiopiaEthiopia

Video object tracking is an important research topic of computer vision, whichfinds a wide range of applications in video surveillance, robotics, human-computerinteraction and so on. Although many moving object tracking algorithms have beenproposed, there are still many difficulties in the actual tracking process, such asillumination change, occlusion, motion blurring, scale change, self-change and so ***, the development of object tracking technology is still challenging. Theemergence of deep learning theory and method provides a new opportunity for theresearch of object tracking, and it is also the main theoretical framework for the researchof moving object tracking algorithm in this paper. In this paper, the existing deeptracking-based target tracking algorithms are classified and sorted out. Based on theprevious knowledge and my own understanding, several solutions are proposed for theexisting methods. In addition, the existing deep learning target tracking method is stilldifficult to meet the requirements of real-time, how to design the network and trackingprocess to achieve speed and effect improvement, there is still a lot of research space.

关键词： Object tracking deep learning neural work

来源：评论

学校读者我要写书评

暂无评论

Practical phase-modulation stabilization in quantum key distribution via machine learning

arXiv

引用

arXiv 2019年

作者： Liu, Jing-Yang Ding, Hua-Jian Zhang, Chun-Mei Xie, Shi-Peng Wang, Qin Institute of quantum information and technology Nanjing University of Posts and Telecommunications Nanjing210003 China Broadband Wireless Communication and Sensor Network TechnologyKey Lab of Ministry of Education Ministry of Education Nanjing210003 China Telecommunication and NetworksNational Engineering Research Center NUPT Nanjing210003 China

In practical implementation of quantum key distributions (QKD), it requires efficient, real-time feedback control to maintain system stability when facing disturbance from either external environment or imperfect internal components. Usually, a"scanning-and-transmitting" program is adopted to compensate physical parameter variations of devices, which can provide accurate compensation but may cost plenty of time in stopping and calibrating processes, resulting in reduced efficiency in key transmission. Here we for the first propose to employ a well known machine learning model, i.e., the Long Short-Term Memory network (LSTM), to predict those physical parameter variations in advance and actively perform real-time control on corresponding QKD devices. Experimentally, we take the phase-coding scheme as an example and run the LSTM model based QKD system for more than 10 days. Experimental results show that we can keep the same level of quantum-bit error rate as the traditional"scanning-and-transmitting" program by employing our new machine learning method, but dramatically reducing the scanning time and resulting in significantly enhanced key transmission efficiency. Furthermore, our present machine learning model should also be applicable to any other QKD systems using any coding scheme or QKD protocols, and thus seems a very promising candidate in large-scale application of quantum communication network in the near future. Copyright © 2019, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Framework with Spatial-Temporal Attention Mechanism for Cellular Traffic Prediction

A Deep Learning Framework with Spatial-Temporal Attention Me...

引用

IEEE Globecom Workshops

作者： Yun Gao Xin Wei Liang Zhou Haibing Lv College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China National Engineering Research Center for Communication and Information Technology (NUPT) Nanjing China Key Laboratory of Broadband Wireless Communications and Sensor Network Technology Ministry of Education (NUPT) Nanjing China Wireline Product Planning Dept Wireline Product Operation ZTE Corporation Nanjing China

ISBN: (数字)9781728109602

ISBN: (纸本)9781728109619

Currently, traffic prediction in cellular communication has become an important way to relieve traffic congestion, and then guarantee users' quality of experience (QoE) in multimedia service. However, when concerning traffic prediction in the context of big data, traditional deep learning models only have limited memory lengths and thus do not satisfy high prediction accuracy demand. In this paper, we design a new deep learningbased framework, which is built on our proposed novel spatialtemporal attention mechanism, to further increase the prediction accuracy of cellular traffic resource. Specifically, we firstly design a big data hierarchical architecture with four levels to extract meaningful information. Then, considering that cellular traffic resource from base stations characterizes spatial-temporal dependencies, we integrate conventional temporal attention mechanism for target area with that from spatial neighbor areas, proposing a novel spatial-temporal attention mechanism. Finally, we utilize this spatial-temporal attention mechanism based LSTM (STaLSTMs) to predict cellular traffic resource from base stations. Experimental results demonstrate that our proposed framework has better performances in cellular traffic prediction than other competing models. Importantly, in some application scenarios, this framework can also maintain high accuracy but only with 60% data.

关键词： Big Data Machine learning Data models Predictive models Base stations Quality of experience Time series analysis

来源：评论

学校读者我要写书评

暂无评论

lednet: A lightweight encoder-decoder network for real-time semantic segmentation

arXiv

引用

arXiv 2019年

作者： Wang, Yu Zhou, Quan Liu, Jia Xiong, Jian Gao, Guangwei Wu, Xiaofu Latecki, Longin Jan National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications China Key Lab. of Broadband Wireless Communications and Sensor Network Technology Nanjing University of Posts & Telecommunications China Institute of Advanced Technology Nanjing University of Posts & Telecommunications China Department of Computer and Information Sciences Temple University Philadelphia United States

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Economy-mode Framework for Task Offloading in Fog Computing networks

An Economy-mode Framework for Task Offloading in Fog Computi...

引用

International Conference on wireless Communications and Signal Processing (WCSP)

作者： Beibei Wang Fei Shen Xujie Li Fei Qin Feng Yan Siyuan Zhou College of computer and information Hohai University Nanjing China Shanghai Research Center for Wireless Communications Shanghai China Key Lab for Wireless Sensor network and Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China The School of Electronic and Electrical Communication Engineering University of Chinese Academy of Sciences Beijing China National Mobile Communications Research Laboratory Southeast University Nanjing China

In the fog network, by offtoading the computing tasks to the fog nodes (FNs) located at the edge of the network, the task processing delay of the terminal nodes (TNs) can be reduced significantly. However, not all the FNs are willing to help TNs for free. Therefore, an economy-mode framework for task offtoading in the fog network is required to motivate the FNs. In this paper, we formulate the task offtoading problem based on Stackelberg game. The TN with computing tasks acts as the leader and its strategy is the optimal unit computing price. Each FN with idle resources acts as the follower and its strategy is the sharable optimal proportion of computing capability. Firstly, the leader predicts the followers' strategies and provides the unit computing price. Next, given the price, the followers will do exactly what the leader wishes, which is the system optimal point. By maximizing the utility functions of both the TN and FNs, a win-win solution is obtained. The numerical simulations indicate the importance of our proposed economy-mode framework for task offtoading.

关键词： Task analysis Delays Games Energy consumption Edge computing Computational modeling wireless communication

来源：评论

学校读者我要写书评

暂无评论

Power allocation optimization in MC-NOMA systems for maximizing weighted sum-rate 24

Power allocation optimization in MC-NOMA systems for maximiz...

引用

24th Asia-Pacific Conference on Communications, APCC 2018

作者： Chen, Ruilu Wang, Xiaoming Xu, Youyun School of Telecommunication and Information Engineering Nanjing Univ. of Posts and Telecom. Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing Univ. of Posts and Telecom. Nanjing China National Engineering Research Center of Comm. and Network Nanjing Univ. of Posts and Telecom. Nanjing China

ISBN: (纸本)9781538669280

In this paper, we investigate a power allocation scheme in downlink multi-carrier non-orthogonal multiple access (MC-NOMA) systems for maximizing weighted sum-rate. Taking user-priority into account, we add the weighting factors into the formulated optimization problem. Firstly, we give sufficient and necessary concavity conditions that should be satisfied by the proposed weighted sum-rate maximization problem. Then, for more generally non-concave case, we use a first order approximation to convert the optimization problem and provide an iterative power allocation algorithm to find the globally optimal solution. Simulation results show that our proposed algorithm is superior to orthogonal frequency division multiple access (OFDMA) scheme and average power allocation scheme. © 2018 IEEE.

关键词： Frequency division multiple access

来源：评论

学校读者我要写书评

暂无评论

Study on the Segmentation Method of Multi-Phase CT Liver Tumor Based on Dual Channel U-Nets

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Changchang Xu Dong Hu YaoDong Zhang Yuwei Pang Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications Nanjing 210003 China Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Nanjing 210003 China Education Ministry's Engineering Research Center of Ubiquitous Network and Heath Service Nanjing University of Posts and Telecommunications Nanjing 210003 China The first clinical medical college of Nanjing Medical University Nanjing University of Posts and Telecommunications Nanjing 210003 China

As a common malignant tumor disease, hepatocellular carcinoma is the most common cancers in the world. The incidence of hepatocellular carcinoma in China is higher than that in the world. Therefore, it is very important for doctors to separate liver and tumor from CT images by means of computer-aided diagnosis and treatment. In this paper, a multiscale DC-CUNets network liver tumor segmentation method is proposed to enhance the fusion of multi-phase image features in CT, the scale of liver tumors, and the optimization of network training process. (1) A multistage CT liver tumor segmentation method based on two-channel cascaded U-Nets (DC-CUNets) is proposed. The liver was segmented using the first-order U-Net, and then the segmented area of interest of the liver was input into the second-order U-Net network to segment liver tumors. We designed two-channel U-Nets to learn the image characteristics of CT images in arterial and venous phases respectively, and to achieve two-channel feature fusion through feature cascade to improve the overall accuracy of liver tumor segmentation.(2) A multistage CT liver tumor segmentation method based on multiscale DC-CUNets was proposed. For the scale problem of liver tumors, we designed a two-layer multiscale void convolution module to obtain image features at different scales for large, medium and small tumors, and fuse the multiscale features at the output of the module. We have replaced the convolution layer of the fourth module in the second-order two-channel liver tumor segmentation U-Nets by the two-layer multiscale cavity convolution module to implement multiscale DC-CUNets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measurement-device-independent quantum communication without encryption

引用

Science Bulletin 2018年第20期63卷 1345-1350页

作者： Peng-Hao Niu Zeng-Rong Zhou Zai-Sheng Lin Yu-Bo Sheng Liu-Guo Yin Gui-Lu Long state Key Laboratory of Low-dimensional Quantum Physics Beijing 100084.China Department of Physics Tsinghua UniversityBeijing 100084China Collaborative Innovation Center of Quantum Matter Beijing 100084China Beijing Academy of Quantum Information Sciences Beijing 100193China Beijing National Research Center for Information Science and Technology BeUing 100084China School of Information and Technology.Tsinghua University Beijing 100084China lnstiute of Quantum Information and Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China College of Telecommunications &Information Engineering Nanjing University of Posts and TelecommunicationsNanjing 210003China Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and TelecommunicationsMinistry of EducationNanjing 210003China

Security in communication is vital in modern life. At present, security is realized by an encryption process in cryptography. It is unbelievable if a secure communication is achievable without encryption. In quantum cryptography, there is a unique form of quantum communication, quantum secure direct communication, where secret information is transmitted directly over a quantum channel. Quantum secure direct communication is drastically distinct from our conventional concept of secure communication, because it does not require key distribution, key storage and ciphertext transmission, and eliminates the encryption procedure completely. Hence it avoids in principle all the security loopholes associated with key and ciphertext in traditional secure communications. For practical implementation, defects always exist in real devices and it may downgrade the security. Among the various device imperfections, those with the measurement devices are the most prominent and serious ones. Here we report a measurementdevice-independent quantum secure direct communication protocol using Einstein-Podolsky-Rosen pairs. This protocol eradicates the security vulnerabilities associated with the measurement device,and greatly enhances the practical security of quantum secure direct communication. In addition to the security advantage, this protocol has an extended communication distance, and a high communication capacity.

关键词： Quantum secure direct communication Measurement-device-independent Quantum dialogue Encryption Cryptography

来源：评论

学校读者我要写书评

暂无评论

Load Feedback-Based Resource Scheduling and Dynamic Migration-Based Data Locality for Virtual Hadoop Clusters in OpenStack-Based Clouds

引用

Tsinghua Science and technology 2017年第2期22卷 149-159页

作者： Dan Tao Zhaowen Lin Bingxu Wang School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003China Network and Information Center Institute of Network TechnologyScience and Technology on Information Transmission and Dissemination in Communication Networks LaboratoryNational Engineering Laboratory for Mobile Network SecurityBeijing University of Posts and TelecommunicationsBeijing 100876China

With cloud computing technology becoming more mature, it is essential to combine the big data processing tool Hadoop with the Infrastructure as a Service（Iaa S） cloud platform. In this study, we first propose a new Dynamic Hadoop Cluster on Iaa S（DHCI） architecture, which includes four key modules： monitoring,scheduling, Virtual Machine（VM） management, and VM migration modules. The load of both physical hosts and VMs is collected by the monitoring module and can be used to design resource scheduling and data locality solutions. Second, we present a simple load feedback-based resource scheduling scheme. The resource allocation can be avoided on overburdened physical hosts or the strong scalability of virtual cluster can be achieved by fluctuating the number of VMs. To improve the flexibility, we adopt the separated deployment of the computation and storage VMs in the DHCI architecture, which negatively impacts the data locality. Third, we reuse the method of VM migration and propose a dynamic migration-based data locality scheme using parallel computing entropy. We migrate the computation nodes to different host（s） or rack（s） where the corresponding storage nodes are deployed to satisfy the requirement of data locality. We evaluate our solutions in a realistic scenario based on Open *** experimental results demonstrate the effectiveness of our solutions that contribute to balance the workload and performance improvement, even under heavy-loaded cloud system conditions.

关键词： Hadoop resource scheduling data locality Infrastructure as a Service（Iaas） OpenStack

来源：评论

学校读者我要写书评

暂无评论

Full-duplex light communication with a monolithic multicomponent system

引用

Light(Science & Applications) 2018年第1期7卷 255-261页

作者： Yongjin Wang Xin Wang Bingcheng Zhu Zheng Shi Jialei Yuan Xumin Gao Yuhuai Liu Xiaojuan Sun Dabing Li Hiroshi Amano Peter Grünberg Research Center Nanjing University of Posts and TelecommunicationsNanjing 210003China Laboratory of Broadband Wireless Communication and Sensor Network Technology(Nanjing University of Posts and Telecommunications) Ministry of EducationNanjing 210003China Department of Electronics Engineering Zhengzhou UniversityScience Road 100Zhengzhou 450001China State Key Laboratory of Luminescence and Applications Changchun Institute of OpticsFine Mechanics and PhysicsChinese Academy of SciencesChangchun 130033China Institute of Materials and Systems for Sustainability Nagoya UniversityNagoya 464-8062Japan

A monolithic multicomponent system is proposed and implemented on a III-nitride-on-silicon platform,whereby two multiple-quantum-well diodes(MQW-diodes)are interconnected by a suspended *** MQW-diodes have an identical low-In-content InGaN/Al0.10Ga0.90N MQW structure and are produced by the same fabrication process *** appropriately biased,both MQW-diodes operate under a simultaneous emission-detection mode and function as a transmitter and a receiver at the same time,forming an in-plane full-duplex light communication ***-time full-duplex audio communication is experimentally demonstrated using the monolithic multicomponent system in combination with an external circuit.

关键词： communication monolithic diodes

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：