检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Tenghui Peng Rongqing Zhang Xiang Cheng Liuqing Yang School of Software Engineering Tongji University Shanghai China State Key Laboratory of Advanced Optical Communication Systems and Networks Peking University Beijing China Department of Electrical and Computer Engineering Colorado State University CO USA

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

In recent years, massive multiple-input multiple-output (MIMO) has been regarded as a promising technique in the fifth-generation (5G) communication systems. With the ability of focusing transmission beams on users, massive MIMO has a natural advantage in the field of physical layer security to improve the system secrecy performance. However, in practical mobile systems, the imperfect channel state information (CSI) caused by the channel estimation error and the transmission and processing delay will have a non-negligible impact on the system performance. In this paper, we investigate secure communications in a multi-user massive MIMO-enabled vehicular communication networks. Considering the influence of imperfect CSI on the secrecy performance, we derive a tight asymptotic lower bound of the system secrecy capacity under both perfect and imperfect CSI. Moreover, we further analyze the impact of vehicle speed on the system secrecy performance and propose a channel prediction scheme based on (Long Short-Term Memory) LSTM model to compensate for the negative effects of imperfect CSI, which can improve the system secrecy performance in high mobility scenario. Simulation results show that the imperfect CSI severely reduces the system secrecy capacity, but its negative effects can be effectively alleviated through the designed LSTM-based channel prediction and compensation scheme.

关键词： MIMO communication Channel estimation Precoding Interference Network security Physical layer Antennas

来源：评论

学校读者我要写书评

暂无评论

Joint Scheduling, Computing, and Load Balancing for Time Sensitive Traffic in SDN-Enabled Space-Air-Ground Integrated 6 G networks: A Federated Reinforcement Learning Approach

引用

IEEE Transactions on Mobile Computing 2025年

作者： Sun, Haitong Zhang, Haijun Ma, Hui Leung, Victor C.M Hebei Key Laboratory of Space-Air-Ground Intelligent Communication Beijing100083 China University of Science and Technology Beijing Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Beijing100083 China Shenzhen University Department of Computer Science and Software Engineering Shenzhen518061 China University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Low Earth Orbit (LEO) constellations and Unmanned Aerial Vehicle (UAV) networks enable wide coverage for the sixth generation (6G) mobile communication. However, it is a challenge to achieve high scheduling success rate, ultra-low latency, and efficient load balance in the Space-Air-Ground Integrated 6G Network (SAGGIN). This paper addresses the following issue: How to effectively and orderly transmit time-sensitive traffic in SAGGIN under strict deadlines, limited computational ability, and restrained link capacity? Specifically, this paper uses software-Defined Networking (SDN) and designs a joint optimization method to enhance the traffic transmission ability of SAGGIN. Considering response time, computing cost, and link capacity in SAGGIN, the scheduling, computing, and load balance issues are modeled as a multi-objective optimization problem that minimizes the worst-case response time and computing cost of data frames while maximizing the network flow. Then, this paper leverages a Federated Reinforcement Learning (FRL) scheme to solve the problem. Results show that the FRL could achieve great scheduling, computing, and load balance performance. Specifically, our method can successfully schedule 80% of the traffic at most when the current network load is around 90%. Furthermore, the computational delay could reduce around 50%. © 2002-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generating superpixels for high-resolution images with Decoupled Patch Calibration

arXiv

引用

arXiv 2021年

作者： Wang, Yaxiong Wei, Yunchao Qian, Xueming Zhu, Li Yang, Yi The School of Software Engineering Xi'an Jiaotong University Xi'an710049 China School of Computer and Information Technology Beijing Jiaotong University Beijing100000 China The Key Laboratory for Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi'an710049 China The SMILES Laboratory Xi'an Jiaotong University Xi'an710049 China Zhibian Technology Co. Ltd. Taizhou317000 China The School of Software Xi'an Jiaotong University Xi'an710049 China School of Computer Science and Technology Zhejiang University Hangzhou310000 China

Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning. However, the very high-resolution superpixel segmentation still remains challenging due to the expensive memory and computation cost, making the current advanced superpixel networks fail to process. In this paper, we devise Patch Calibration networks (PCNet), aiming to efficiently and accurately implement high-resolution superpixel segmentation. PCNet follows the principle of producing high-resolution output from low-resolution input for saving GPU memory and relieving computation cost. To recall the fine details destroyed by the down-sampling operation, we propose a novel Decoupled Patch Calibration (DPC) branch for collaboratively augment the main superpixel generation branch. In particular, DPC takes a local patch from the high-resolution images and dynamically generates a binary mask to impose the network to focus on region boundaries. By sharing the parameters of DPC and main branches, the fine-detailed knowledge learned from high-resolution patches will be transferred to help calibrate the destroyed information. To the best of our knowledge, we make the first attempt to consider the deep-learning-based superpixel generation for high-resolution cases. To facilitate this research, we build evaluation benchmarks from two public datasets and one new constructed one, covering a wide range of diversities from fine-grained human parts to cityscapes. Extensive experiments demonstrate that our PCNet can not only perform favorably against the state-of-the-arts in the quantitative results but also improve the resolution upper bound from 3K to 5K on 1080Ti GPUs. © 2021, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Device-Free Gesture Recognition Capability of Mobile Communication Signals

引用

IEEE Transactions on Communications 2025年

作者： Wu, Jingmiao He, Weijie Sun, Kai Huang, Wei Zhang, Haijun Leung, Victor C. M. Inner Mongolia University School of Electronic Information Engineering Inner Mongolia Key Laboratory of Intelligent Communication and Sensing and Signal Processing Hohhot010021 China University of Science and Technology at Beijing Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Beijing100083 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Device-free gesture recognition using mobile communication signals is a convenient and efficient technology with broad application prospects in smart homes and human-computer interaction. It utilizes the effect of gestures on surrounding signals to achieve gesture recognition. The cell-specific reference signals (CRS) information can be used to achieve the task in close-range training scenarios. However, when gestures are performed at long-range or in non-training scenarios, the recognition performance will significantly degrade. To enhance device-free gesture recognition capability in arbitrary scenarios, we propose the signal quality enhancement algorithm and the gesture spectrogram construction method to solve this problem. Specifically, we superimpose the CRS information from multiple carriers to improve the gesture signal-to-noise ratio and increase the gesture sensing range. Then, we extract the gesture dynamic components from the CRS information and construct gesture spectrograms to represent scenario-independent gesture motion patterns. Using the gesture spectrogram features, we design a deep network to accomplish the gesture recognition task. We built a prototype system on a software-defined radio platform. Experimental results show that our proposed method can effectively increase the gesture sensing range from 30m² to 228m² and achieve an average recognition accuracy of 82.5% for five types of gestures in arbitrary scenarios. © 1972-2012 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

ReGO: Reference-Guided Outpainting for Scenery Image

arXiv

引用

arXiv 2021年

作者： Wang, Yaxiong Wei, Yunchao Qian, Xueming Zhu, Li Yang, Yi The School of Software Engineering Xi’an Jiaotong University Xi'An710049 China Institute of Information Science Beijing Jiaotong University Beijing100000 China The Key Laboratory for Intelligent Networks and Network Security Ministry of Education Xi’an Jiaotong University Xi'An710049 China The SMILES Laboratory Xi’an Jiaotong University Xi'An710049 China Zhibian Technology Co. Ltd. Taizhou317000 China The School of Software Xi’an Jiaotong University Xi'An710049 China School of Computer Science and Technology Zhejiang University Hangzhou310000 China

We aim to tackle the challenging yet practical scenery image outpainting task in this work. Recently, generative adversarial learning has significantly advanced the image outpainting by producing semantic consistent content for the given image. However, the existing methods always suffer from the blurry texture and the artifacts of the generative part, making the overall outpainting results lack authenticity. To overcome the weakness, this work investigates a principle way to synthesize texture-rich results by borrowing pixels from its neighbors (i.e. , reference images), named Reference-Guided Outpainting (ReGO). Particularly, the ReGO designs an Adaptive Content Selection (ACS) module to transfer the pixel of reference images for texture compensating of the target one. To prevent the style of the generated part from being affected by the reference images, a style ranking loss is further proposed to augment the ReGO to synthesize style-consistent results. Extensive experiments on two sceneary benchmarks, NS6K [3], NS8K [9] and SUN Attribute [25], well demonstrate the effectiveness of our ReGO. Our code is available at https://***/wangyxxjtu/ReGOPytorch. © 2021, CC BY.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Trading off Charging and Sensing for Stochastic Events Monitoring in WRSNs

Trading off Charging and Sensing for Stochastic Events Monit...

引用

International Conference on Network Protocols

作者： Yu Sun Chi Lin Haipeng Dai Qiang Lin Lei Wang Guowei Wu School of Software Technology Dalian University of Technology Dalian China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China Dalian University of Science and Technology Dalian China Acoustics Science and Technology Laboratory Harbin Engineering University Harbin China

ISBN: (数字)9781728169927

ISBN: (纸本)9781728169934

As an epoch-making technology, wireless power transfer incredibly achieves energy transmission wirelessly, enabling reliable energy supplement for wireless rechargeable sensor networks (WRSNs). Existing methods mainly concentrate on performance improvement theoretically, neglecting the fact that most Commercial Off-The-Shelf (COTS) rechargeable sensors (e.g., WISP and Powercast) are not allowed to conduct sensing and energy harvesting tasks simultaneously, termed charging exclusivity. Therefore, their schemes are not feasible for practical applications. In this paper, we focus on the charging exclusivity issue in stochastic events monitoring while improving network performance. In specific, we pay close attention to trading off charging and sensing tasks and formulate a combinatorial optimization problem with routing constraints. We introduce novel discretization techniques and investigate the routing problem to reformulate the original problem into the maximization of a submodular function. With a slightly relaxed budget, the output of our proposed algorithm is better than (1 1/e)/2 of the optimal solution to the original problem with a -smaller charging radius (1 - ξ)D c . Through extensive simulations, numerical results show that in terms of charging utility, our algorithm outperforms baseline algorithms by 21.3% on average. Moreover, we conduct test-bed experiments to demonstrate the feasibility of our scheme in real scenarios.

关键词： Sensors Monitoring Wireless sensor networks Task analysis Stochastic processes Wireless communication software

来源：评论

学校读者我要写书评

暂无评论

A NOMA Power Allocation Strategy Based on Genetic Algorithm 8th

A NOMA Power Allocation Strategy Based on Genetic Algorithm

引用

8th International Conference on Communications, Signal Processing, and Systems, CSPS 2019

作者： Yin, Lu Chenggong, Wang Kai, Mao Kuanxin, Bao Haowei, Bian Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Nanjing210003 China Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Nanjing University of Posts and Telecommunications Ministry of Education Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9789811394089

The NOMA technology uses the power domain non-orthogonal multiplexing method to enable multiple users to occupy the entire frequency band simultaneously to transmit signals. In order to maximize the total transmission rate of the system, an effective method is to use the genetic algorithm for NOMA power allocation. In this paper, the NOMA downlink system model is constructed, and the objective function and constraints are analyzed. A NOMA power allocation strategy based on genetic algorithm is proposed. The algorithm distributes user power based on the criterion of maximizing total transmission rate, therefore the algorithm has random search capabilities and relatively low search complexity. The simulation results show that when the system transmits power or multiplexed users is fixed the proposed algorithm outperforms the fixed power allocation algorithm in the total transmission rate. The total system transmission rate of the genetic algorithm is similar to the full space search algorithm. As the number of multiplexed users increases, the computational complexity of genetic algorithms is much lower than that of full-space search algorithms. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Graph-Based File Dispatching Protocol With D2D-Aided UAV-NOMA Communications in Large-Scale networks

Graph-Based File Dispatching Protocol With D2D-Aided UAV-NOM...

引用

IEEE Conference on Wireless Communications and Networking

作者： Baoji Wang Rongqing Zhang Chen Chen Xiang Cheng Liuqing Yan State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing China school of Software Engineering Tongji University Shanghai China Department of Electrical & Computer Engineering Colorado State University CO USA

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131078

Unmanned aerial vehicle (UAV)-assisted communications are expected to become an important part of the next generation mobile communication systems, due to the high mobility of the UAVs. Non-orthogonal multiple access (NOMA) is regarded as a rosy technology in the fifth generation (5G) mobile communication systems, since it can effectively improve the spectral efficiency. In this paper, we combine the advantages of the UAV-assisted communications and NOMA, and propose a device-to-device (D2D)-enhanced UAV-NOMA network architecture, in which D2D is introduced to increase the file dispatching efficiency. Resource reuse based on spatial reuse is also allowed to further improve the spectral efficiency. Then, we propose a graph-based file dispatching (GFD) protocol to control the interference and minimize the UAV-assisted file dispatching mission time. Simulation results verify the advantages of our proposed D2D-enhanced UAV-NOMA network architecture and the efficiency of our designed GFD protocol.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A NOMA Power Allocation Method Based on Greedy Algorithm 8th

A NOMA Power Allocation Method Based on Greedy Algorithm

引用

8th International Conference on Communications, Signal Processing, and Systems, CSPS 2019

作者： Lu, Yin Chen, Shuai Mao, Kai Bian, Haowei Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Nanjing210003 China Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Nanjing University of Posts and Telecommunications Ministry of Education Nanjing210003 China Nanjing University of Posts and Telecommunications Nanjing210003 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9789811394089

In the existing Non-Orthogonal Multiple Access power allocation algorithm, the iterative water-filling algorithm is a commonly used algorithm, which has good performance but high complexity. In order to reduce the complexity, this paper divides the power allocation problem of Non-Orthogonal Multiple Access into two steps. Firstly, the water-filling algorithm is used to complete the power allocation between sub-carriers, then the greedy algorithm is used to allocate power to the superimposed users in the carrier. Many elements in the candidate power allocation coefficient set that are impossible to be optimal solutions are deleted by using the sum of power distribution coefficients of each user and the product of throughput, which effectively reducing the complexity. The simulation results show that the proposed algorithm has a slightly lower performance than the iterative water injection algorithm, but it effectively reduces the complexity. The performance of the proposed algorithm is better than other traditional algorithms, and a good compromise between system performance and complexity is achieved. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

BiLock: User authentication via dental occlusion biometrics

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2018年第3期2卷 1-20页

作者： Zou, Yongpan Zhao, Meng Zhou, Zimu Lin, Jiawei Li, Mo Wu, Kaishun College of Computer Science and Software Engineering Shenzhen University China Computer Engineering and Networks Laboratory ETH Zurich Switzerland School of Computer Science and Engineering Nanyang Technological University Singapore

User authentication on smart devices is indispensable to keep data privacy and security. It is especially significant for emerging wearable devices such as smartwatches considering data sensitivity in them. However, conventional authentication methods are not applicable for wearables due to constraints of size and hardware, which makes present wearable devices lack convenient, secure and low-cost authentication schemes. To tackle this problem, we reveal a novel biometric authentication mechanism which makes use of sounds of human dental occlusion (i.e., tooth click). We demonstrate its feasibility by comprehensive measurement study, and design a prototype-BiLock with two Android platforms. Extensive real-world experiments have been conducted to evaluate the accuracy, robustness and security of BiLock in different environments. The results show that BiLock can achieve less than 5% average false reject rate and 0.95% average false accept rate even in a noisy environment. Comparative experiments also demonstrate that BiLock possesses advantages in robustness to noise and security against replay and observation attacks over existing voiceprinting schemes. © 2018 Association for Computing Machinery.

关键词： Biometrics

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：