检索结果-南通市图书馆

Multi-sensor multispectral reconstruction framework based on projection and reconstruction

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第3期67卷 246-262页

作者： Tianshuai LI Tianzhu LIU Xian LI Yanfeng GU Yukun WANG Yushi CHEN School of Electronics and information Engineering Harbin Institute of Technology Heilongjiang Province key laboratory of space-Air-Ground Integrated intelligent Remote Sensing

The scarcity and low spatial resolution of hyperspectral images(HSIs) have become a major problem limiting the application of the images. In recent years, spectral reconstruction(SR) has been applied to convert multispectral images(MSIs) with abundant quantities and high spatial resolution into HSIs. With the launch of several new multispectral(MS) satellites with a short repeat period, the simultaneous acquisition of images from multiple MS sensors in the same area is gradually becoming feasible. Unfortunately, existing SR methods only consider the reconstruction of the MSIs of a single sensor without considering using MSIs from different MS sensors to obtain a better construction effect through their complementary bands. However,multi-sensor SR is characterized by two problems: inconsistency in the amplitude information of real multisensor imaging and difficulty in the extraction of the complex correlations of bands from different sensors.To solve these problems, this paper proposes a multi-sensor SR framework based on a two-step approach in which the problems of amplitude inconsistency and band information extraction are solved using an ideal projection network and an ideal multi-sensor SR network, respectively. The effectiveness of the proposed method is verified by experiments on three datasets.

关键词： spectral reconstruction spectral superresolution hyperspectral image multispectral image neural networks multi-sensor

SDGNN: Symmetry-Preserving Dual-Stream Graph Neural networks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1717-1719页

作者： Jiufang Chen Ye Yuan Xin Luo the College of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 the chongqing key laboratory of Big Data and intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China the College of Computer and information Science Southwest UniversityChongqing 400715China IEEE

Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.

关键词： representation preserving undirected

Policy network-Based Dual-Agent Deep Reinforcement Learning for Multi-Resource Task Offloading in Multi-Access Edge Cloud networks

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

China Communications 2024年第4期21卷 53-73页

作者： Feng Chuan Zhang Xu Han Pengchao Ma Tianchun Gong Xiaoxue School of Communications and information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Institute of intelligent Communication and network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China key laboratory of Big Data intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China School of information Engineering Guangdong University of TechnologyGuangzhou 510006China

The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC networks can support a wide range of applications. MEC networks can also leverage various types of resources, including computation resources, network resources, radio resources,and location-based resources, to provide multidimensional resources for intelligent applications in 5/6G.However, tasks generated by users often consist of multiple subtasks that require different types of resources. It is a challenging problem to offload multiresource task requests to the edge cloud aiming at maximizing benefits due to the heterogeneity of resources provided by devices. To address this issue,we mathematically model the task requests with multiple subtasks. Then, the problem of task offloading of multi-resource task requests is proved to be NP-hard. Furthermore, we propose a novel Dual-Agent Deep Reinforcement Learning algorithm with Node First and Link features(NF_L_DA_DRL) based on the policy network, to optimize the benefits generated by offloading multi-resource task requests in MEC networks. Finally, simulation results show that the proposed algorithm can effectively improve the benefit of task offloading with higher resource utilization compared with baseline algorithms.

关键词： benefit maximization deep reinforcement learning multi-access edge cloud task offloading

Service Function Chain Migration in LEO Satellite networks

在线全文

学校读者我要写书评

暂无评论

China Communications 2024年第3期21卷 247-259页

作者： Geng Yuhui Wang Niwei Chen Xi Xu Xiaofan Zhou Changsheng Yang Junyi Xiao Zhenyu Cao Xianbin School of Electronic and information Engineering Beihang UniversityBeijing 100191China key laboratory of Advanced Technology of Near space information System Ministry of Industry and Information Technology of ChinaBeijing 100191China Shanghai key laboratory of Satellite network Shanghai 201204China Shanghai Satellite network Research Institute Co. Ltd.Shanghai 201204China

With the advancements of software defined network(SDN)and network function virtualization(NFV),service function chain(SFC)placement becomes a crucial enabler for flexible resource scheduling in low earth orbit(LEO)satellite networks.While due to the scarcity of bandwidth resources and dynamic topology of LEO satellites,the static SFC placement schemes may cause performance degradation,resource waste and even service failure.In this paper,we consider migration and establish an online migration model,especially considering the dynamic topology.Given the scarcity of bandwidth resources,the model aims to maximize the total number of accepted SFCs while incurring as little bandwidth cost of SFC transmission and migration as possible.Due to its NP-hardness,we propose a heuristic minimized dynamic SFC migration(MDSM)algorithm that only triggers the migration procedure when new SFCs are rejected.Simulation results demonstrate that MDSM achieves a performance close to the upper bound with lower complexity.

关键词： network function virtualization(NFV) resource allocation satellite networks service function chain(SFC) SFC migration SFC placement soft-ware defined network(SDN)

Exploring reservoir computing:Implementation via double stochastic nanowire networks

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第3期33卷 572-582页

作者：唐健峰夏磊李广隶付军段书凯王丽丹 College of Artificial Intelligence Southwest UniversityChongqing 400715China Brain-inspired Computing & intelligent Control of chongqing key laboratory Chongqing 400715China National & Local Joint Engineering laboratory of intelligent Transmission and Control Technology Chongqing 400715China chongqing Brain Science Collaborative Innovation Center Chongqing 400715China key laboratory of Luminescence Analysis and Molecular Sensing Ministry of EducationSouthwest UniversityChongqing 400715China State key laboratory of intelligent Vehicle Safety Technology Chongqing 400715China

Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.

关键词： double-layer stochastic(DS)nanowire network architecture neuromorphic computation nanowire network reservoir computing time series prediction

Finite-time bearing-only formation of first-order multi-agent systems under pinning control

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第5期67卷 331-332页

作者： Chenjun LIU Wei ZHU Fenglan SUN key laboratory of intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications

Formation control of multi-agent systems(MASs) has been applied in various fields, such as autonomous navigation and target encirclement, due to its ability to facilitate coordination and achieve the desired formation or space configuration. Bearing-based formation control offers greater practicality than position-based or distance-based approaches since bearing information is inexpensive and simple to acquire, such as utilizing optical cameras.

关键词： Multi agent systems

Boosting Adversarial Training with Learnable Distribution

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3247-3265页

作者： Kai Chen Jinwei Wang James Msughter Adeke Guangjie Liu Yuewei Dai School of Electronics and information Engineering Nanjing University of Information Science and TechnologyNanjing210044China key laboratory of intelligent Support Technology for Complex Environments Ministry of EducationNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Nanjing Center for Applied Mathematics Nanjing211135China

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.

关键词： Adversarial training feature space learnable distribution distribution centroid

Air-Ground Collaborative Mobile Edge Computing:Architecture,Challenges,and Opportunities

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第5期21卷 1-16页

作者： Qin Zhen He Shoushuai Wang Hai Qu Yuben Dai Haipeng Xiong Fei Wei Zhenhua Li Hailong College of Communications Engineering Army Engineering University of PLANanjing 210000China Department of information and Communication Noncommissioned Officer Academy of PAPHangzhou 310000China key laboratory of Dynamic Cognitive System of Electromagnetic Spectrum space Ministry of Industry and Information TechnologyNanjing 211106China College of Electronic and information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China State key laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China CMC Political and Law Commission Beijing100120China Xi’an Research Institute of High Technology Xi’an 710025China

By pushing computation,cache,and network control to the edge,mobile edge computing(MEC)is expected to play a leading role in fifth generation(5G)and future sixth generation(6G).Nevertheless,facing ubiquitous fast-growing computational demands,it is impossible for a single MEC paradigm to effectively support high-quality intelligent services at end user equipments(UEs).To address this issue,we propose an air-ground collaborative MEC(AGCMEC)architecture in this article.The proposed AGCMEC integrates all potentially available MEC servers within air and ground in the envisioned 6G,by a variety of collaborative ways to provide computation services at their best for UEs.Firstly,we introduce the AGC-MEC architecture and elaborate three typical use cases.Then,we discuss four main challenges in the AGC-MEC as well as their potential solutions.Next,we conduct a case study of collaborative service placement for AGC-MEC to validate the effectiveness of the proposed collaborative service placement strategy.Finally,we highlight several potential research directions of the AGC-MEC.

关键词： air-ground architecture collaborative mobile edge computing

Application of deep learning methods combined with physical background in wide field of view imaging atmospheric Cherenkov telescopes

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第4期35卷 208-220页

作者： Ao-Yan Cheng Hao Cai Shi Chen Tian-Lu Chen Xiang Dong You-Liang Feng Qi Gao Quan-Bu Gou Yi-Qing Guo Hong-Bo Hu Ming-Ming Kang Hai-Jin Li Chen Liu Mao-Yuan Liu Wei Liu Fang-Sheng Min Chu-Cheng Pan Bing-Qiang Qiao Xiang-Li Qian Hui-Ying Sun Yu-Chang Sun Ao-Bo Wang Xu Wang Zhen Wang Guang-Guang Xin Yu-Hua Yao Qiang Yuan Yi Zhang School of Physics and Technology Wuhan UniversityWuhan 430072China School of Physics and Astronomy Yunnan UniversityKunming 650091China Ministry of Education The Key Laboratory of Cosmic Rays(Tibet University)Lhasa 850000China key laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China University of Chinese Academy of Sciences 19 A Yuquan RoadShijingshan DistrictBeijing 100049China College of Physics Sichuan UniversityChengdu 610064China School of intelligent Engineering Shandong Management UniversityJinan 250357China Tsung‑Dao Lee Institute Shanghai Jiao Tong UniversityShanghai 200240China Suzhou Aerospace information Research Institute Suzhou 215123China College of Physics Chongqing UniversityNo.55 Daxuecheng South RoadHigh‑tech DistrictChongqing 401331China key laboratory of Dark Matter and space Astronomy Purple Mountain ObservatoryChinese Academy of SciencesNanjing 210008China

The High Altitude Detection of Astronomical Radiation(HADAR)experiment,which was constructed in Tibet,China,combines the wide-angle advantages of traditional EAS array detectors with the high-sensitivity advantages of focused Cherenkov detectors.Its objective is to observe transient sources such as gamma-ray bursts and the counterparts of gravitational waves.This study aims to utilize the latest AI technology to enhance the sensitivity of HADAR experiments.Training datasets and models with distinctive creativity were constructed by incorporating the relevant physical theories for various applications.These models can determine the type,energy,and direction of the incident particles after careful design.We obtained a background identification accuracy of 98.6%,a relative energy reconstruction error of 10.0%,and an angular resolution of 0.22°in a test dataset at 10 TeV.These findings demonstrate the significant potential for enhancing the precision and dependability of detector data analysis in astrophysical research.By using deep learning techniques,the HADAR experiment’s observational sensitivity to the Crab Nebula has surpassed that of MAGIC and H.E.S.S.at energies below 0.5 TeV and remains competitive with conventional narrow-field Cherenkov telescopes at higher energies.In addition,our experiment offers a new approach for dealing with strongly connected,scattered data.

关键词： VHE gamma-ray astronomy HADAR Deep learning Convolutional neural networks