检索结果-内蒙古大学图书馆

IEEE Conference on Global Communications (GLOBECOM)

作者： Qianru Wang Liping Qian Yuan Wu Xiaoniu Yang College of Information Engineering Zhejiang University of Technology Hangzhou China State Key Laboratory of Internet of Things for Smart City University of Macau China Science and Technology on Communication Information Security Control Laboratory Jiaxing China Institute of Cyberspace Security Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

With the growing demand for image transmission, there is a need for solutions that offer low energy consumption and low latency. In this paper, we present a novel relay-assisted system based on non-orthogonal multiple access (NOMA) and mobile edge computing (MEC). Our proposed system compresses images at the device end, decompresses them at either a relay or a cloud server (CS). The primary objective is to minimize system energy consumption under given task delay constraints. Considering that this is a non-convex optimization problem, we solve it by decomposing it into a continuous subproblem and a discrete subproblem. To solve the continuous subproblem, we convexify it by introducing new parameters and change variables to get the optimal the computing power of devices, relay and CS, sampling rate of devices, transmission power of devices and relay. To solve the discrete subproblem, we propose a cross-entropy (CE) algorithm to obtain the optimal decompression decision and subcarrier allocation decision. Simulation results demonstrate the accuracy and effectiveness of our algorithm in optimizing total energy consumption compared to the Linear Interactive and General Optimizer (LINGO) and frequency division multiple access (FDMA) methods.

关键词： Performance evaluation NOMA Energy consumption Image coding Multi-access edge computing Simulation Optimization methods Resource management Servers Relays

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Global Convergence Guarantees of (A)GIST for a Family of Nonconvex Sparse Learning Problems

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 3276-3288页

作者： Zhang, Hengmin Qian, Feng Shang, Fanhua Du, Wenli Qian, Jianjun Yang, Jian East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education School of Information Science and Engineering Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an710071 China Peng Cheng Laboratory Shenzhen518066 China Nanjing University of Science and Technology Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

In recent years, most of the studies have shown that the generalized iterated shrinkage thresholdings (GISTs) have become the commonly used first-order optimization algorithms in sparse learning problems. The nonconvex relaxations of the \ell _{0} -norm usually achieve better performance than the convex case (e.g., \ell _{1} -norm) since the former can achieve a nearly unbiased solver. To increase the calculation efficiency, this work further provides an accelerated GIST version, that is, AGIST, through the extrapolation-based acceleration technique, which can contribute to reduce the number of iterations when solving a family of nonconvex sparse learning problems. Besides, we present the algorithmic analysis, including both local and global convergence guarantees, as well as other intermediate results for the GIST and AGIST, denoted as (A)GIST, by virtue of the Kurdyka-Lojasiewica (KL) property and some milder assumptions. Numerical experiments on both synthetic data and real-world databases can demonstrate that the convergence results of objective function accord to the theoretical properties and nonconvex sparse learning methods can achieve superior performance over some convex ones. © 2013 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Sparsity-enhanced Convolutional Neural Network for IoT Cyberattacks Detection 17

Sparsity-enhanced Convolutional Neural Network for IoT Cyber...

引用

17th International Conference on Computational Intelligence and security, CIS 2021

作者： Kang, Yingyun Feng, Yongxin Chen, Yongqun Wang, Wei School of Information Science and Engineering Shenyang Ligong University Shenyang China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

ISBN: (纸本)9781665494892

The Internet of Things (IoT) is a collection of interconnected devices that can be linked without the need for human interaction. IoT will have a significant impact on our lives in terms of economics, commerce, and society. IoT network nodes are typically resource-constrained, which makes them attractive targets for cyberattacks. However, due to the unique properties of IoT nodes, current solutions are insufficient to cover the complete security spectrum of IoT networks. A more intelligent IoT network security solution is required. Artificial intelligence is one of the most suited computing paradigms for providing embedded intelligence in IoT and is being used to address various security issues. To detect IoT cyber threats, we introduce a sparsity-enhanced convolutional neural network in this paper. Recently published IoT datasets are used for experiments. The proposed neural network is effective by experimental results and analysis. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Target-Before-Detect Algorithm for Passive MIMO Radar Based on Improved Particle Filter

Target-Before-Detect Algorithm for Passive MIMO Radar Based ...

引用

作者： Yawen Zhou Jiawei Zhu Tingsong Song Siyi Yao Rui Lai Yuning Guo School of Electronic Science and Technology University Science and Technology on Communication Information Security Control Laboratory

In order to improve the target detection performance of passive multiple-input-multiple-output(PMR) radar system,a Target-Before-Detect(TBD) algorithm based on improved particle filter is proposed in this paper. As a classical TBD algorithm, particle filter algorithm can realize the gain accumulation of target signal in time domain and effectively improve the performance of target detection. Although this algorithm has performed well in passive single-input-singleoutput(SISO) radar(PSR) systems, it cannot be directly applied to PMR systems. Therefore, an improved particle filtering algorithm based on passive MIMO radar is proposed in this paper. This method takes advantage of the PMR spatial accumulation and proposes a novel particle weight calculation method, which uses the false alarm probability distribution of detector to calculate the weight of the particle, so as to obtain the gain accumulation of the target in time and space. The simulation results show that the detection probability of the proposed algorithm can reach 90% even when the target-path signal-to-noise ratio(SNR) is low. Meanwhile, the good detection performance of the proposed algorithm is verified by comparing with the single frame detection results.

关键词： Passive Multiple-Input-Multiple-Output (MIMO)Radar Target-Before-Detect(TBD) Particle Filter

来源：评论

学校读者我要写书评

暂无评论

A DOA estimation method for area array based on dimensionality reduction processing 7

A DOA estimation method for area array based on dimensionali...

引用

7th International Conference on information science and control Engineering, ICISCE 2020

作者： Wei, Sun Yu, Han Qing, Zhou Science and Technology on Commuication Information Security Control Laboratory No.36 Research Institute of CETC Jiaxing314033 China

ISBN: (纸本)9781728164069

Aiming at the problems of traditional beamforming algorithms that require a two-dimensional angle search for two-dimensional DOA estimation using rectangular arrays, which takes a long time, this paper provides a dimensionality reduction method through theoretical derivation and numerical calculation. This method uses coordinate conversion and secondary optimization, successively calculates the angle of the target relative to the X and Y axes, and combines the idea of least squares to finally calculate the azimuth and elevation angle of the target, turning the two-dimensional problem into a one-dimensional search, which greatly reduces the amount of calculation. The simulation results show that the angle estimation accuracy of this method is equivalent to that of the traditional MUSIC method, but its algorithm complexity and calculation time are reduced a lot, which is very suitable for engineering applications. © 2020 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Non-line-of-Sight Recognition Algorithm Based on Deep Learning

Non-line-of-Sight Recognition Algorithm Based on Deep Learni...

引用

International Conference on Internet of Things, Communication and Intelligent technology, IoTCIT 2022

作者： Zhang, Chengjun Wang, Hongmei Wang, Zhiwei Wang, Faguang Min, Minghui Li, Shiyin School of Information and Control Engineering China University of Mining and Technology Jiangsu Xuzhou221116 China Xuzhou First People’s Hospital Xuzhou221116 China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education and School of Cyber Science and Engineering Wuhan University Wuhan430072 China

ISBN: (纸本)9789819904150

With the development of the information age, large indoor places such as hospitals, mines and factories have higher and higher requirements for indoor positioning. GPS and other common outdoor positioning methods cannot meet the requirements of accurate indoor navigation. Ultra-wideband is widely used in indoor places because of its strong anti-interference and high accuracy. Accurate identification of errors in UWB indoor non-visual range helps to improve the data for positioning. Therefore, this study combined with convolutional neural network to solve the problem of low recognition rate of non-line-of-sight signals in indoor scenes, and proposed an improved convolutional neural network based on empirical mode decomposition (EMD), wavelet domain denoising (WD) and improved CNN) fusion model EMD-WD-CNN. First, the channel impulse response signal of UWB is denoised based on the EMD-WD algorithm, and then the denoised signal is used as the input of the CNN model for training. The comparison based on similar algorithms shows that the improved CNN model can significantly improve the line-of-sight and NLOS recognition rate of different media in indoor environment. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A Passive Navigation Algorithm Based on Derivative Dynamic Time Regularization Geomagnetic Matching 2

A Passive Navigation Algorithm Based on Derivative Dynamic T...

引用

2021 2nd International Conference on Modeling, Big Data Analytics and Simulation, MBDAS 2021

作者： Wang, Yiteng Bao, Jinhong Li, Zehua Science and Technology on Communication Information Security Control Laboratory China No.36 Research Institute of China Electronics Technology Group Corporation China College of Telecommunication Engineering Hangzhou Dianzi University Hangzhou310018 China

As satellite positioning has shortcomings such as susceptibility to multipath interference, we look forward to using a new algorithm to solve these problems. The method of derivative dynamic time regularization is used as the matching method of geomagnetic navigation. Due to the factors of the inertial device itself, a certain cumulative error will occur in the positioning solution of the inertial navigation (INS). Therefore, an outdoor error model needs to be established, and the positioning error is corrected by filtering technology. To solve this problem, the Unscented Kalman Filter is used to fuse the positioning results of the two to obtain a more accurate positioning, with an average accuracy within 1.5 meters. © Published under licence by IOP Publishing Ltd.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

The Anti-Interference Algorithm of BPSK Spread Spectrum Signal Based on Generative Adversarial Networks 7

The Anti-Interference Algorithm of BPSK Spread Spectrum Sign...

引用

7th International Conference on Signal and Image Processing, ICSIP 2022

作者： Han, Yu Zhang, Minghong Shen, Lei Wang, Lijun The 36th Research Institute of China Electronics Technology Group Corporation Science and Technology on Communication Information Security Control Laboratory Jiaxing China Hangzhou Dianzi University School of Communication Engineering Hangzhou China

ISBN: (数字)9781665495639

ISBN: (纸本)9781665495639

In order to avoid the problem of unsatisfactory anti-jamming effect when the interference feature extraction of traditional anti-jamming algorithm is inaccurate, this paper takes BPSK spread spectrum signal as the research object, and proposes an anti-jamming algorithm for BPSK spread spectrum signal based on generative adversarial network. The algorithm firstly despreads the spread spectrum signal, and then images the despread signal, and uses the known disturbed despread signal set and undisturbed signal set for network training. The mapping relationship between the disturbed despread signal image and the undisturbed despread signal image is constructed by generative adversarial network, so as to achieve the purpose of interference suppression. Experiments show that the signal anti-jamming algorithm based on generative adversarial network proposed in this paper has better interference suppression ability than the frequency-domain notch anti-jamming algorithm under multi-tone interference and narrow-band noise interference. © 2022 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Localization and Recognition of Subwavelength Non-Cooperative Entities Based on SISO Time Reversal and Neural Networks

引用

IEEE Sensors Journal 2024年

作者： Wang, Yinchen Duan, Yu Ye, Yuqi Wang, Ren Li, Biao Jiang, Bin Liu, Xin Wang, Bing-Zhong University of Electronic Science and Technology of China Institute of Applied Physics Chengdu611731 China No. 36 Research Institute of CETC Communication Information Security Control Laboratory Jiaxing314033 China

The simultaneous localization and recognition of subwavelength non-cooperative entities within complex multi-scattering environments using a simplified system continues to pose a substantial challenge. In this paper, we address this challenge by synergistically integrating time reversal time-frequency phase prints (TRTFPPs) and neural networks. Initially, a time reversal (TR) single-input single-output (SISO) framework is employed to generate TRTFPPs. Subsequently, neural networks are employed to comprehend the TRTFPPs. Specifically, a cascaded neural network structure is embraced, encompassing both a recognition neural network and distinct neural networks for localizing different entities. Using the devised method, we have achieved the simultaneous subwavelength recognition and localization through numerical simulations for metallic entities and experimental testing for metallic and non-metallic entities. The proposed methodology holds applicability across various electromagnetic systems, including but not limited to detection, imaging, human-computer interaction, and the Internet of Things (IoT). © 2001-2012 IEEE.

关键词： Multiple scattering

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：