期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到25篇文章
< 1 2 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Energy-aware trajectory and resource management for NOMA-enabled MEC in UAV-based airborne maneuvering networks:A PPO-driven approach 认领 引用
1
作者 Xudong WANG Lei FENG +3 位作者 Jiacheng WANG Jiangtian NIE Xiangwang HOU Geng SUN 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第5期84-97,共14页
Unmanned Aerial Vehicle(UAV)equipped with Mobile Edge Computing(MEC)server has become a promising solution for on-demand service provisioning in Airborne Maneuvering Networks(AMNs).However,it remains constrained by se... Unmanned Aerial Vehicle(UAV)equipped with Mobile Edge Computing(MEC)server has become a promising solution for on-demand service provisioning in Airborne Maneuvering Networks(AMNs).However,it remains constrained by severe multi-user interference and limited spectral resources.This work investigates a non-orthogonal multiple access-enabled MEC framework in AMNs to address spectrum limitations and support concurrent access for multiple Ground Terminals(GTs),where GTs are multiplexed in the power domain and decoded via successive interference cancellation at the UAV.An energy minimization problem is formulated to jointly optimize UAV flight trajectory,task offloading decisions,and power allocation.To address the resulting non-convex energy minimization problem,a hybrid optimization framework that integrates Proximal Policy Optimization(PPO)with convex programming is proposed.Specifically,the deep reinforcement learning component jointly learns the UAV trajectory,binary task offloading strategy,and uplink power control under dynamic network conditions.In parallel,a convex optimization module efficiently computes the UAV's flight time allocation to minimize propulsion energy.Simulation results demonstrate that the proposed PPO-driven approach significantly reduces total energy consumption compared to conventional baselines,validating its effectiveness for energyefficient MEC in UAV-based AMNs. 展开更多
关键词 Airborne maneuvering networks Mobile edge computing Non-orthogonal multiple access Proximal policy optimization Unmanned aerial vehicle
暂未订购 下载PDF
Ultra-wideband channel modeling and characterization under low altitude scenarios 认领 引用
2
作者 Taiya LEI Kai MAO +5 位作者 Qiuming ZHU Ruichen ZHANG Zhangfeng MA Boyu HUA Dusit NIYATO Qihui WU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第5期146-159,共14页
A Low-Altitude(LA)intelligent network with unmanned aerial vehicles is a key component of space-air-ground integrated communication networks.Moreover,the Ultra-Wideband(UWB)technique offers a promising solution of hig... A Low-Altitude(LA)intelligent network with unmanned aerial vehicles is a key component of space-air-ground integrated communication networks.Moreover,the Ultra-Wideband(UWB)technique offers a promising solution of high-speed data transmission in the LA intelligent network due to its broad frequency spectrum.A deep understanding of UWB channels in LA scenarios is vital for design,optimization,and evaluation of reliable communication links.This paper proposes a novel LA UWB channel model,which comprehensively considers the impact of continuous frequency components within the band on the channel parameters and characteristics.On this basis,we present a detailed generation method of bandwidth-dependent channel parameters,i.e.,Path Loss(PL),K-factor,cluster-related parameters,and Doppler frequency.Furthermore,the phenomenon of channel hardening and Doppler companding with respect to the ultra-wide bandwidth are analyzed.Finally,a UWB channel sounder is developed and applied to conduct lowaltitude channel measurements in a 28 GHz campus scenario.The measured results such as PL,K-factor,and cluster numbers show good agreement with the proposed model,validating its accuracy and applicability. 展开更多
关键词 Bandwidth-dependent parameter Channel measurement Low-altitude intelligent network Ultra-wideband channel modeling Unmanned aerial vehicle
暂未订购 下载PDF
Efficient foundation model service provision over airborne networks:Collaborative tuning and inference 认领 引用
3
作者 Zihan CHEN Longyu ZHOU +2 位作者 Shengyu ZHANG Chenyuan FENG Dusit NIYATO 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第5期98-110,共13页
Deploying foundation models across distributed airborne networks offers a promising solution for delivering flexible,high-coverage,and on-demand generative AI services.However,the deployment and tuning of foundation m... Deploying foundation models across distributed airborne networks offers a promising solution for delivering flexible,high-coverage,and on-demand generative AI services.However,the deployment and tuning of foundation models present critical challenges on airborne platforms such as Unmanned Aerial Vehicles(UAVs),due to the intensive computational requirements,substantial memory footprint,and high communication overhead,particularly given these platforms'limited power and memory capacity as well as the limited communication connections.In view of these,a collaborative fine-tuning and inference framework for deploying foundation models over UAV networks is proposed,which employs a split model deployment strategy to distribute computational loads across multiple UAVs.The framework also incorporates a multi-stage fine-tuning approach utilizing a large vision model-based knowledge distillation and personalized local tuning to further enhance performance while maintaining system stability despite UAV mobility.The proposed framework could achieve foundation model fine-tuning in a memory-and computationefficient manner.To further improve the communication and computation efficiency,two variants of the framework are proposed via leveraging over-the-air computations and parameter-efficient fine-tuning techniques in communication and local computation.Extensive experimental evaluation demonstrates the superior and stable performance of the proposed framework compared to baselines in terms of generalization,communication efficiency,memory efficiency,and scalability. 展开更多
关键词 Airborne networks Federated learning Collaborative learning Large model fine-tuning UAV communications Foundation models
暂未订购 下载PDF
Structure-Aware Diffusion Image Outpainting for Echocardiographic Field-of-View Extension 认领 引用
4
作者 Ruijia He Yixin Hu +3 位作者 Jinze Liu Qixin Zhang Duo Peng Yanyan Chen 《Computers, Materials & Continua》 SCIE EI 2026年第9期1698-1718,共21页
Transthoracic Echocardiography(TTE)often suffers from a limited field of view(FoV),which may obscure peripheral cardiac structures and hinder comprehensive visual assessment.Although FoV extension can be formulated as... Transthoracic Echocardiography(TTE)often suffers from a limited field of view(FoV),which may obscure peripheral cardiac structures and hinder comprehensive visual assessment.Although FoV extension can be formulated as outpainting,public studies on echocardiographic FoV outpainting remain scarce and are mainly represented by cGAN-based reconstruction methods such as echoGAN.However,in noisy ultrasound images with weak boundaries,the challenge is not only realistic texture synthesis,but also structural continuity across the observed-generated boundary.To address this issue,we propose a structure-aware diffusion framework for echocardiographic FoV outpainting.To the best of our knowledge,this is the first work to introduce diffusion models into this task,moving beyond the existing cGAN-based formulation.Our framework combines a diffusion baseline,a Structural Cue Encoder(SCE)for structure-sensitive conditioning,and Structure-aware Diffusion Learning(SDL)for structural regularization during denoising.Experiments show clear and consistent improvements over cGAN-based reconstruction,producing more coherent structures,smoother transitions,and better FoV extension quality. 展开更多
关键词 Field-of-view extension diffusion model image generation outpainting structure-aware learning transthoracic echocardiography
暂未订购 下载PDF
Secure and robust power allocation for covert UAV-aided IoT networks using NOMA 认领 引用
5
作者 Yuanai XIE Shisheng LIN +4 位作者 Xiao ZHANG Pan LAI Zhixin LIU Dusit NIYATO Tse-Tin CHAN 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2025年第10期144-157,共14页
The access of massive Internet of Things(IoT)users poses several challenges for Unmanned Aerial Vehicle(UAV)-aided communications,particularly in terms of security and reliability.This paper investigates a secure and ... The access of massive Internet of Things(IoT)users poses several challenges for Unmanned Aerial Vehicle(UAV)-aided communications,particularly in terms of security and reliability.This paper investigates a secure and robust power allocation scheme for UAV-aided IoT Non-Orthogonal Multiple Access(NOMA)downlink networks with a potential eavesdropper,considering imperfect Channel State Information(CSI).Given the noise uncertainty caused by the UAV’s mobility and the statistical channel estimation error,we formulate a robust optimization problem to maximize the total covert rate of all NOMA users,subject to covertness and rate-based reliability constraints.To solve this optimization problem,we first derive the minimum detection error rate and utilize the statistical characteristics(i.e.,the mean and variance of channel gain errors)to obtain the deterministic covertness and reliability constraints,respectively.We then prove that the problem is concave and determine the optimal power allocation algorithm using the Karush–Kuhn–Tucker conditions.Extensive numerical simulations validate the effectiveness of the proposed algorithm and demonstrate its ability to realize more secure and robust UAV-aided IoT systems. 展开更多
关键词 Unmanned aerial vehicle Wireless security Covert communication Non-orthogonal multiple access Imperfect channel state information Power allocation
暂未订购 下载PDF
Key Challenges and Research Directions for Space-Air-Ground Integrated Emergency Communication Networks 认领 引用
6
作者 Bo Xu Haitao Zhao +1 位作者 Jiawen Kang Dusit Niyato 《Engineering》 SCIE EI CSCD 2025年第11期52-55,共4页
In recent years,intensified environmental pollution and climate change have increasingly exposed the world to natural disasters such as earthquakes and floods,resulting in substantial economic losses[1].These disaster... In recent years,intensified environmental pollution and climate change have increasingly exposed the world to natural disasters such as earthquakes and floods,resulting in substantial economic losses[1].These disasters frequently damage terrestrial communication infrastructures,making the rapid deployment of emergency communication networks in affected areas critical in increasing rescue efficiency[2]. 展开更多
关键词 research directions space air ground integrated emergency communication networks terrestrial communication infrastructuresmaking key challenges environmental pollution natural disasters climate change
暂未订购 下载PDF
IRS-user matching and beamforming design for multi-active-IRS-and-UAV-aided secure directional modulation networks 认领 引用 被引量：1
7
作者 Ke YANG Siling FENG +5 位作者 Rongen DONG Xuehui WANG Yan WANG Jiatong BAI Yuanjian LI Jiangzhou WANG 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2025年第10期158-169,共12页
In this paper,a novel directional modulation(DM)network utilizing the distributed active intelligent reflecting surface(IRS)to enhance the secrecy sum-rate(SSR)performance is established,with each unmanned aerial vehi... In this paper,a novel directional modulation(DM)network utilizing the distributed active intelligent reflecting surface(IRS)to enhance the secrecy sum-rate(SSR)performance is established,with each unmanned aerial vehicle(UAV)hanging an IRS.The degree of freedom(DoF)is only two in the single-IRS-aided DM network,which will seriously limit its rate performance.Multiple active IRSs will create more DoFs for DM network and dramatically enhance its rate.Three IRS-user matching methods,path loss coefficient(PLC)matching,distance matching,and signal-to-interference-plus-noise ratio(SINR)matching,are proposed to enhance the SSR performance,where all IRSs are equipartitioned into two parts,one part is matched to Bob and the other part to Eve.The double layer leakage(DLL)and minimum-mean square error(MMSE)rules,called DLL-MMSE,are adopted to construct beamforming at transmitter,IRS and receiver,respectively.The double layer null-space projection(DLNSP),Rayleigh ratio(RR)and MMSE schemes,called DLNSP-RR-MMSE,are used to acquire the transmit beamforming vector,phase shift matrix(PSM)and receive beamforming vector,respectively.Simulation results show that the proposed SINR matching scheme outperforms the remaining two ones in terms of SSR.It is also verified that a significant SSR enhancement over single IRS is achieved by using multiple distributed IRSs. 展开更多
关键词 Directional modulation Intelligent reflecting surface Secrecy sum-rate Degree of freedom Unmanned aerial vehicle
暂未订购 下载PDF
A theoretical and experimental study on CO2 reduction selectivity of Mo2CTx MXene catalysts:Influence of surface termination 认领 引用
8
作者 Caihong Liang Zhonghan Zhang +6 位作者 Teddy Salim Zhihao Yen Daniel Yongyi Goh Lydia Helena Wong Zheng Liu Liang Wang Yeng Ming Lam 《Nano Research》 SCIE EI CSCD 2026年第2期1113-1122,共10页
Understanding the relationship between CO2 reduction reaction(CO2RR)performance and surface terminations of MXenes is crucial for designing effective electrocatalysts.This study explores the impact of common ter... Understanding the relationship between CO2 reduction reaction(CO2RR)performance and surface terminations of MXenes is crucial for designing effective electrocatalysts.This study explores the impact of common terminations on Mo2CTx using a computational hydrogen electrode(CHE)model integrated with a pseudo-microkinetic model(pseudo-MM).Unlike traditional CHE methods,CHE/pseudo-MM considers the energy differences of all steps,providing a comprehensive view of CO2RR mechanisms while reducing computational cost generated from calculating transitional state.The electrolyte is considered as acetonitrile with 1-ethyl-3-methylimidazolium tetra-fluoroborate(EMIMBF4)to inhibit the generation of hydrogen.Theoretical predictions reveal surface terminations dictate the selectivity of C1 products,whose proton is provided by EMIMBF4.The selectivity for fully-F,-O-and-OH-terminated Mo2CTx surfaces varies with the applied potential,as confirmed by experiments.Electrochemical CO2RR in acetonitrile with EMIMBF4 electrolyte confirms these predictions,showing that CH4 outperforms CO and gradually becomes the dominant product as the applied potential increases.These findings demonstrate the qualitative accuracy of the proposed CHE/pseudo-MM for predicting CO2RR selectivity,particularly for gaseous products,over Mo2CTx systems. 展开更多
关键词 C1selectivity acetonitrile/1-ethyl-3-methylimidazolium tetra-fluoroborate(EMIMBF4)electrolyte Mo2CTxMXene systems computational hydrogen electrode model pseudo-microkinetic model
暂未订购 下载PDF
Deep Variational Quantum Circuits with Barren-Plateau-Free Architectures 认领 引用
9
作者 Kaining Zhang Min-Hsiu Hsieh Dacheng Tao 《Artificial Intelligence Science and Engineering》 2026年第1期66-84,共19页
Variational quantum algorithms(VQAs)with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase.This result leads to a general belief th... Variational quantum algorithms(VQAs)with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase.This result leads to a general belief that a deep circuit will not be feasible.In this work,we provide a viable solution to the vanishing gradient problem for deep VQAs with theoretical guarantees.Specifically,we prove that for quantum controlled-layer and quantum residual network(QResNet),architectures,the expectation of the gradient norm can be lower bounded by a value that is independent of the qubit number and the circuit depth.Our results follow from a careful analysis of the gradient behavior on parameter space consisting of rotation angles,as employed in almost all VQAs,instead of relying on impractical 2-design assumptions.We conduct several numerical experiments as verifications,where only our circuits are trainable and converge,while hardware-efficient and random circuits with similar number of parameters in comparison cannot converge. 展开更多
关键词 variational quantum algorithms quantum machine learning barren plateaus
暂未订购 下载PDF
DP-Fed6G:An adaptive differential privacy-empowered federated learning framework for 6G networks 认领 引用
10
作者 Miao Du Peng Yang +2 位作者 Yinqiu Liu Xiaoming He Mingkai Chen 《Digital Communications and Networks》 SCIE EI CSCD 2025年第6期1994-2002,共9页
The advent of 6G networks is poised to drive a new era of intelligent,privacy-preserving distributed learning by leveraging advanced communication and AI-driven edge intelligence.Federated Learning(FL)has emerged as a... The advent of 6G networks is poised to drive a new era of intelligent,privacy-preserving distributed learning by leveraging advanced communication and AI-driven edge intelligence.Federated Learning(FL)has emerged as a promising paradigm to enable collaborative model training without exposing raw data.However,its deployment in 6G networks faces significant obstacles,including vulnerabilities to inference attacks,the complexities of heterogeneous and dynamic network environments,and the inherent trade-off between privacy protection and model performance.In response to these challenges,we introduce DP-Fed6G,a novel FL framework that integrates differential privacy(DP)to fortify data security while ensuring high-quality learning outcomes.Specifically,DPFed6G employs an adaptive noise injection strategy that dynamically adjusts privacy protection levels based on real-time 6G network conditions and device heterogeneity,ensuring robust data security while maximizing model performance and optimizing the trade-off between privacy and utility.Extensive experiments on three real-world healthcare datasets demonstrate that DP-Fed6G consistently outperforms existing baselines(DP-Fed SGD and DPFed Avg),achieving up to 10.3%higher test accuracy under the same privacy budget.The proposed framework thus provides a practical solution for secure and privacy-preserving AI in 6G,supporting intelligent decisionmaking in privacy-sensitive applications. 展开更多
关键词 Differential privacy Federated learning 6G Gaussian noise
暂未订购 下载PDF
Domain-Independent Gear Pitting Fault Diagnosis Using Transformer Encoder and LinSoftmax 认领 引用
11
作者 Liang Zou Huixuan Ling +3 位作者 Meng Lei Xin Fang Mingqi Cai Han Yu 《Big Data Mining and Analytics》 EI CSCD 2025年第5期1127-1147,共21页
Gear pitting fault is a common issue in gear systems,affecting transmission efficiency and potentially leading to severe equipment shutdowns.Effective diagnosis enhances reliability,reduces maintenance costs,and exten... Gear pitting fault is a common issue in gear systems,affecting transmission efficiency and potentially leading to severe equipment shutdowns.Effective diagnosis enhances reliability,reduces maintenance costs,and extends equipment lifespan.However,existing deep learning based methods often neglect the inherent structure of temporal vibration signals and fail to address domain variations,resulting in poor generalization and performance.To overcome these limitations,we propose a novel approach based on domain-independent features.Vibration signals are mapped to time-frequency representations via short-time Fourier transform,and dependencies between different frequencies are effectively captured using a Transformer encoder.The proposed method incorporates a feature decoupling structure that combines singular value decomposition and Pearson correlation coefficient to extract low-rank approximations of domain-related and pitting-related features,while quantifying their correlation.This approach mitigates feature degradation in constructing domain-independent features.Additionally,the weighted LinSoftmax function is introduced as a replacement for the traditional Softmax,leading to a more stable optimization target and improved model accuracy,with a distance-based penalty weight focusing on significant prediction errors.Experiments on the 2023 PHM Data Challenge dataset demonstrate the effectiveness of the proposed method,achieving a mean absolute error of 0.11,an accuracy of 92.32%,and a fault tolerance accuracy of 98.02%. 展开更多
关键词 gear pitting Transformer LinSoftmax domain generalization
A survey and benchmark evaluation for neural-network-based lossless universal compressors toward multi-source data 认领 引用 被引量：1
12
作者 Hui SUN Huidong MA +7 位作者 Feng LING Haonan XIE Yongxia SUN Liping YI Meng YAN Cheng ZHONG Xiaoguang LIU Gang WANG 《Frontiers of Computer Science》 SCIE EI CSCD 2025年第7期79-94,共16页
As various types of data grow explosively,largescale data storage,backup,and transmission become challenging,which motivates many researchers to propose efficient universal compression algorithms for multi-source data... As various types of data grow explosively,largescale data storage,backup,and transmission become challenging,which motivates many researchers to propose efficient universal compression algorithms for multi-source data.In recent years,due to the emergence of hardware acceleration devices such as GPUs,TPUs,DPUs,and FPGAs,the performance bottleneck of neural networks(NN)has been overcome,making NN-based compression algorithms increasingly practical and popular.However,the research survey for the NN-based universal lossless compressors has not been conducted yet,and there is also a lack of unified evaluation metrics.To address the above problems,in this paper,we present a holistic survey as well as benchmark evaluations.Specifically,i)we thoroughly investigate NNbased lossless universal compression algorithms toward multisource data and classify them into 3 types:static pre-training,adaptive,and semi-adaptive.ii)We unify 19 evaluation metrics to comprehensively assess the compression effect,resource consumption,and model performance of compressors.iii)We conduct experiments more than 4600 CPU/GPU hours to evaluate 17 state-of-the-art compressors on 28 real-world datasets across data types of text,images,videos,audio,etc.iv)We also summarize the strengths and drawbacks of NNbased lossless data compressors and discuss promising research directions.We summarize the results as the NN-based Lossless Compressors Benchmark(NNLCB,See fahaihi.github.io/NNLCB website),which will be updated and maintained continuously in the future. 展开更多
关键词 lossless compression benchmark evaluation universal compressors neural networks deep learning
暂未订购 下载PDF
Leci:Learnable Evolutionary Category Intermediates for Unsupervised Domain Adaptive Segmentation 认领 引用 被引量：1
13
作者 Qiming ZHANG Yufei XU +1 位作者 Jing ZHANG Dacheng TAO 《Artificial Intelligence Science and Engineering》 2025年第1期37-51,共15页
To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,s... To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods. 展开更多
关键词 unsupervised domain adaptation semantic segmentation deep learning
暂未订购 下载PDF
Foundation models and intelligent decision-making:Progress,challenges,and perspectives 认领 引用 被引量：8
14
作者 Jincai Huang Yongjun Xu +68 位作者 Qi Wang QiWang Xingxing Liang Fei Wang Zhao Zhang Wei Wei Boxuan Zhang Libo Huang Jingru Chang Liantao Ma Ting Ma Yuxuan Liang Jie Zhang Jian Guo Xuhui Jiang Xinxin Fan Zhulin An Tingting Li Xuefei Li Zezhi Shao Tangwen Qian Tao Sun Boyu Diao Chuanguang Yang Chenqing Yu Yiqing Wu Mengxian Li Haifeng Zhang Yongcheng Zeng Zhicheng Zhang Zhengqiu Zhu Yiqin Lv Aming Li Xu Chen Bo An Wei Xiao Chenguang Bai Yuxing Mao Zhigang Yin Sheng Gui Wentao Su Yinghao Zhu Junyi Gao Xinyu He Yizhou Li Guangyin Jin Xiang Ao Xuehao Zhai Haoran Tan Lijun Yun Hongquan Shi Jun Li Changjun Fan Kuihua Huang Ewen Harrison Victor CMLeung Sihang Qiu Yanjie Dong Xiaolong Zheng Gang Wang Yu Zheng Yuanzhuo Wang Jiafeng Guo Lizhe Wang Xueqi Cheng Yaonan Wang Shanlin Yang Mengyin Fu Aiguo Fei 《The Innovation》 EI 2025年第6期105-144,104,共40页
Intelligent decision-making(IDM)is a cornerstone of artificial intelligence(AI)designed to automate or augment decision processes.Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make... Intelligent decision-making(IDM)is a cornerstone of artificial intelligence(AI)designed to automate or augment decision processes.Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps,such as AI agents and high-level reinforcement learning.Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision,language,and sensory data—into a cohesive decision-making process.Foundation models(FMs)have become pivotal in science and industry,transforming decision-making and research capabilities.Their large-scale,multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare,life sciences,and education.This survey examines IDM’s evolution,advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains,highlighting the challenges and opportunities in building efficient,adaptive,and ethical decision systems. 展开更多
关键词 intelligent agents artificial intelligence ai designed decompose complex tasks advanced frameworks ai agents foundation models automate augment decision processesmodern intelligent decision making
面向6G网络的AI与通信融合探析:基础、挑战与未来研究机遇 认领 引用 被引量：1
15
作者 崔琪楣 尤肖虎 +22 位作者 倪巍 南国顺 张雪菲 张建华 吕昕晨 艾明 陶小峰 冯志勇 张平 武庆庆 陶梅霞 黄永明 黄崇文 刘光毅 彭程晖 潘志文 孙韬 Dusit NIYATO Tao CHEN Muhammad Khurram KHAN Abbas JAMALIPOUR Mohsen GUIZANI Chau YUEN 《中国科学：信息科学》 CAS CSCD 北大核心 2026年第1期241-242,共2页
随着第六代移动通信(6G)向超高速率、全域覆盖和智能服务方向的演进,人工智能(AI)与通信技术的深度融合已成为突破传统性能边界、重构网络生态体系的核心驱动力[1,2].在该趋势下,6G网络将实现从“人–人连接”“人机物连接”到“万物智... 随着第六代移动通信(6G)向超高速率、全域覆盖和智能服务方向的演进,人工智能(AI)与通信技术的深度融合已成为突破传统性能边界、重构网络生态体系的核心驱动力[1,2].在该趋势下,6G网络将实现从“人–人连接”“人机物连接”到“万物智联”的跨越.AI强大的数据分析与决策能力,能使网络更好地感知、理解和适应复杂多变的无线环境,满足差异大、个性化的用户需求.然而,6G网络与AI的深度融合也面临多重矛盾性挑战:从数据层面看,AI语义压缩技术可以提高编码效率并减少带宽占用,但模型参数、训练数据等附加传输需求可能抵消其带来的部分增益;从能耗方面看,AI驱动的智能资源分配能够显著提高能效,但其算法的运行与计算又带来了额外的能耗,需要在能效提升与算力消耗之间寻求平衡;从可靠性看,AI的动态优化能力可以增强网络的弹性响应性能,但在复杂环境下,其算法决策的不确定性可能引发新的可靠性风险. 展开更多
关键词 AI 能耗 智能资源分配 数据层面 通信融合 6G网络
Dual-verification-based model fingerprints against ambiguity attacks 认领 引用
16
作者 Boyao Zhao Haozhe Chen +2 位作者 Jie Zhang Weiming Zhang Nenghai Yu 《Cybersecurity》 EI CSCD 2026年第2期133-150,共18页
Efforts have been made to safeguard DNNs from intellectual property infringement.Among different techniques,model fingerprinting has gained popularity due to its ability to examine potential infringement without alter... Efforts have been made to safeguard DNNs from intellectual property infringement.Among different techniques,model fingerprinting has gained popularity due to its ability to examine potential infringement without altering the model’s parameters.However,there is a concern regarding the vulnerability of previous model fingerprints to“ambiguity attacks,”where attackers may use fabricated fingerprints to bypass ownership verification,potentially leading to disputes.To address this issue,we propose a dual-verification-based fingerprint authentication system that incorporates the verification of fingerprint genuineness.Briefly,this system involves two authentication processes:conventional fingerprint methods for authenticating model copyrights and the incorporation of copyright information into the fingerprint feature map to confirm ownership of the model fingerprint.Extensive experiments have been conducted to demonstrate the effectiveness of our approach in resisting ambiguity attacks and managing attempts to remove the fingerprint. 展开更多
关键词 Model security IP protection Model fingerprinting Ambiguity attack
How well will LLMs perform for graph layout tasks? 认领 引用
17
作者 Yilun Fan Xianglei Lyu +3 位作者 Lei Wang Ying Zhao Fangfang Zhou Yong Wang 《Visual Informatics》 EI CSCD 2026年第1期75-87,共13页
arge Language Models(LLMs)have demonstrated impressive capabilities in various applications,motivating visualization researchers to explore the usage of LLMs for visualization tasks such as automated visualization rec... arge Language Models(LLMs)have demonstrated impressive capabilities in various applications,motivating visualization researchers to explore the usage of LLMs for visualization tasks such as automated visualization recommendation,code generation and misleading visualization detection.However,it remains unclear how well will LLMs perform for graph layout,a classic and fundamental research question in visualization.To fill this gap,this paper presents a systematic evaluation of three state-of-the-art LLMs(i.e.,GPT-4o,Gemini 2.0,DeepSeek-V3)on three key dimensions of graph layout:graph data understanding,layout generation,and layout evaluation.Our experiments cover five representative types of graphs,two graph scales,and two widely used graph representation formats.Our results provide insightful findings on the capabilities of LLMs for each key dimension of graph layout tasks.First,LLMs exhibit strong performance in fundamental graph understanding tasks when code generation is permitted,but their structural reasoning ability declines significantly in pure text-based scenarios.Second,LLMs have the potential to produce promising layouts,though they occasionally generate poor results.Third,visual input generally enhances their ability to evaluate layout quality,while text-only prompts may result in unreliable assessments of graph layout quality.These findings provide valuable insights for advancing future research on leveraging LLMs for graph layout. 展开更多
关键词 Large language models(LLMs) Graph layout Graph data understanding Evaluation
人工智能安全与隐私综述 认领 引用
18
作者 何新磊 徐国文 +26 位作者 韩星烁 王骞 赵令辰 沈超 蔺琛皓 赵正宇 李前 杨乐 纪守领 李少锋 朱浩瑾 王志波 郑锐 朱天清 李琦 贺超翔 王啟帆 胡宏盛 王烁 孙士锋 姚宏伟 秦湛 陈恺 赵月 李洪伟 黄欣沂 冯登国 《中国科学：信息科学》 CAS CSCD 北大核心 2026年第2期481-482,共2页
随着人工智能(artificial intelligence,AI)技术从传统机器学习不断迈向生成式智能与基座模型(foundation models),其在金融、医疗、交通、工业控制等关键领域的渗透日益加深,系统形态也愈发复杂.AI系统已经从单一模型、单节点训练的集... 随着人工智能(artificial intelligence,AI)技术从传统机器学习不断迈向生成式智能与基座模型(foundation models),其在金融、医疗、交通、工业控制等关键领域的渗透日益加深,系统形态也愈发复杂.AI系统已经从单一模型、单节点训练的集中式形态,演化为涵盖联邦学习(federated learning)、拆分学习(split learning)、云边协同以及多模态基座模型在内的庞大生态. 展开更多
关键词 基座模型 机器学习 生成式智能 安全 金融 隐私
Effective degree of freedom for near-field plane-based XL-MIMO with tri-polarization 认领 引用
19
作者 Zhe WANG Jiayi ZHANG +3 位作者 Wenhui YI Huahua XIAO Dusit NIYATO Bo AI 《Frontiers of Information Technology & Electronic Engineering》 SCIE EI CSCD 2024年第12期1723-1731,共9页
In this paper we study the effective degree of freedom(EDoF)for extremely large-scale multipleinput multiple-output(XL-MIMO)systems.We consider two XL-MIMO hardware designs,uniform planar array(UPA)based and continuou... In this paper we study the effective degree of freedom(EDoF)for extremely large-scale multipleinput multiple-output(XL-MIMO)systems.We consider two XL-MIMO hardware designs,uniform planar array(UPA)based and continuous aperture(CAP)based XL-MIMO,as well as two representative near-field channel models:scalar Green function based and dyadic Green function with triple polarization based models. 展开更多
关键词 field planar function
暂未订购 下载PDF
JobViz:Skill-driven visual exploration of job advertisements 认领 引用 被引量：1
20
作者 Ran Wang Qianhe Chen +2 位作者 Yong Wang Lewei Xiong Boyang Shen 《Visual Informatics》 EI 2024年第3期18-28,共11页
Online job advertisements on various job portals or websites have become the most popular way for people to find potential career opportunities nowadays.However,the majority of these job sites are limited to offering ... Online job advertisements on various job portals or websites have become the most popular way for people to find potential career opportunities nowadays.However,the majority of these job sites are limited to offering fundamental filters such as job titles,keywords,and compensation ranges.This often poses a challenge for job seekers in efficiently identifying relevant job advertisements that align with their unique skill sets amidst a vast sea of listings.Thus,we propose well-coordinated visualizations to provide job seekers with three levels of details of job information:a skill-job overview visualizes skill sets,employment posts as well as relationships between them with a hierarchical visualization design;a post exploration view leverages an augmented radar-chart glyph to represent job posts and further facilitates users’swift comprehension of the pertinent skills necessitated by respective positions;a post detail view lists the specifics of selected job posts for profound analysis and comparison.By using a real-world recruitment advertisement dataset collected from 51Job,one of the largest job websites in China,we conducted two case studies and user interviews to evaluate JobViz.The results demonstrated the usefulness and effectiveness of our approach. 展开更多
关键词 Visual exploration Job advertisements Skill-driven
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈