检索结果-内蒙古大学图书馆

Multi-IRS-Aided Secure Communication in UAV-MEC Networks

IEEE Transactions on Vehicular technology 2025年第5期74卷 7327-7338页

作者： Gao, Yuan Wang, Zhenyu Zhang, Yu Lu, Weidang Tang, Jie Zhao, Nan Gao, Feifei Academy of Military Science of the PLA Beijing100084 China Zhejiang University of Technology College of Information Engineering Hangzhou310023 China South China University of Technology School of Electronic and Information Engineering Guangzhou510641 China Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Tsinghua National Laboratory for Information Science and Technology Beijing100084 China

With the merits of high mobility and easy deployment, mounting mobile edge computing (MEC) servers on unmanned aerial vehicles (UAVs) can efficiently fulfill the task offloading of ground users (GUs) over a large area. Nevertheless, data security is a challenging issue for the computation offloading in UAV-MEC networks, especially when there exist flying eavesdroppers. An intelligent reflecting surface (IRS) assisted secure communication scheme for a UAV-MEC network is proposed in this paper, wherein multiple IRSs are utilized to help the secure computation offloading from GUs against a UAV eavesdropper. Our aim is to maximize the secure computation capacity through the joint optimization of the IRS phase-shift, allocation of communication and computing resources and trajectory of UAV. We firstly solve the problem under a fixed UAV trajectory by alternating optimization to obtain the resource allocation and IRS phase-shift, wherein Dinkebach and Taylor expansion methods are used to transform the subproblems into tractable forms. Then, by adopting the proximal policy optimization, a joint optimization approach which further incorporates the UAV trajectory optimization is proposed. Numerical results verify that compared with benchmarks, the proposed scheme efficiently improves the system secure computation capacity. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Multi-Output and Multi-Task Regression for Supershape Reconstruction from 3D Point Clouds

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Performance of a four deep neural network structure in moiré fringe intelligent analysis

引用

Applied Optics 2025年第9期64卷 2208-2216页

作者： Zeng, Xinyu Chen, Yunyun Cheng, Weihao Xie, Wenzhuo Yang, Cuihong State Key Laboratory Cultivation Base of Atmospheric Optoelectronic Detection and Information Fusion Nanjing University of Information Science & Technology Nanjing210044 China Jiangsu Engineering Research Center for Intelligent Optoelectronic Sensing Technology of Atmosphere Nanjing University of Information Science & Technology Nanjing210044 China Jiangsu International Joint Laboratory on Meteorological Photonics and Optoelectronic Detection Nanjing University of Information Science & Technology Nanjing210044 China Nanjing University of Information Science & Technology Nanjing210044 China

Moiré fringe analysis holds significant importance in the assessment of flow fields, while deep learning is advancing rapidly and is frequently employed to handle complex computational challenges. In this paper, the performance of U-net, Unet++, Unet 3+, and ResUnet in moiré fringe analysis is compared and analyzed. The results indicate significant differences among the four neural networks in terms of the training time, prediction speed, prediction accuracy, and generalization capability regarding positional variations. Among the four neural networks, ResUnet exhibits the shortest training times, highest accuracy, and fastest prediction speeds while also exhibiting good generalization capability. Consequently, in practical applications, using ResUnet for moiré fringe analysis is an excellent choice. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Discriminative feature encoding for intrinsic image decomposition

引用

Computational Visual Media 2023年第3期9卷 597-618页

作者： Zongji Wang Yunfei Liu Feng Lu Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518000China

Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image *** work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high *** focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input *** achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding *** define feature distribution divergence to efficiently separate the feature vectors of different intrinsic *** feature distributions are also constrained to fit the real ones through a feature distribution *** addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image *** method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent *** results indicate that our proposed network structure can outperform the existing state-of-the-art.

关键词： intrinsic image decomposition deep learning feature distribution data refinement

来源：评论

学校读者我要写书评

暂无评论

Constructed TiO_(2)/WO_(3)heterojunction with strengthened nano-trees structure for highly stable electrochromic energy storage device

引用

Journal of Advanced Ceramics 2023年第3期12卷 634-648页

作者： Lili Zhao Zhuoan Cai Xiaoyang Wang Wenbo Liao Simin Huang Lingyun Ye Jilie Fang Chunxing Wu Hao Qiu Lei Miao School of Chemical Engineering and Energy Technology Dongguan University of TechnologyDongguan 523808China Guangxi Key Laboratory of Information Materials Engineering Research Center of Electronic Information Materials and DevicesMinistry of EducationSchool of Materials Science and EngineeringGuilin University of Electronic TechnologyGuilin 541004China Guangdong Provincial Key Laboratory of Distributed Energy Systems Dongguan 523808China

Tungsten trioxide(WO_(3))has been widely regarded as a prospective bifunctional material due to its electrochromic and pseudocapacitive properties,while still facing the dilemma of inadequate cycle stability and trapping-induced ***,inspired by the trees-strengthening approach,a unique titanium dioxide(TiO_(2))nanorod arrays strengthened WO_(3)nano-trees(TWNTs)heterojunction was rationally designed and *** sharp contrast to the transmittance modulation(ΔT)attenuation of primary WO_(3)nano-trees during cycling,the TWNTs film showed not only excellent electrochromic performance but also fascinating cycle stability(77.35%retention of the initialΔT after 10,000 cycles).Besides,the trapping-induced degradation could be easily rejuvenated by a potentiostatic de-trapping *** electrochromic energy storage device(EESD)was further assembled based on the TWNTs film to deliver excellentΔT(up to 79.5%at 633 nm),fast switching speed(tc/tb=1.9 s/14.8 s),extremely high coloration efficiency value(443.4 cm^(2)·C^(−1)),and long-term cycle stability(over 10,000 charge/discharge cycles).This innovative study provided in-depth insights into the electrochromism nature and a significant step in the realization of stable electrochromic-energy storage application,paving the way for multifunctional smart windows as well as next-generation optoelectronic devices.

关键词： electrochromic(EC) WO_(3)nano-trees cycle stability TiO_(2)nanorod arrays(TiO_(2)NRAs) energy storage

来源：评论

学校读者我要写书评

暂无评论

Improving real-time physiological signs estimation using plethysmography wave and heterogeneous embedded system

引用

Journal of Medical engineering and technology 2024年第8期48卷 296-314页

作者： El khadiri, Zakaria Latif, Rachid Saddik, Amine Jenkal, Wissam Laboratory of Systems Engineering and Information Technology LISTI National School of Applied Sciences Ibn Zohr University Agadir Agadir Morocco

Our work presents a real-time embedded implementation of a proposed approach for physiological signs monitoring, such as heart and breathing rates, using a Photoplethysmography signal (PPG) retrieved from digital RGB cameras. The proposed algorithm was implemented in an embedded architecture to assess both the processing time and algorithmic complexity. The proposed method is based on image processing techniques to extract the noisy PPG signal and signal processing, filtering, and decomposition algorithm to estimate the instantaneous vitals indicators. On the embedded implementation side, the common criteria that must be studied are the accuracy of the result estimation, processing time optimisation, and hardware-software adoption. The latter standard is met by the hardware-software co-design concept which will lead to adopting the algorithm’s layers with an embedded platform architecture. On our side, we will principally use the High-Level Synthesis (HLS) as a parallel programming language and the computing homogeneous/heterogeneous devices (CPU/GPU). Our proposed optimised algorithm’s implementation offers a gain of x5.05, x24.96, and x36.68 compared with the native version using MATLAB and the optimised version using C/C++, OpenMP, and OpenCL tool, respectively, in some functional blocks. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Robust Software Defined Multicast in Broadband LEO Constellations

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9802-9813页

作者： Dong, Yan Wang, Chenxin Wang, Liangyuan Yang, Yihang Hu, Menglan Peng, Kai Cai, Chao Xiong, Zehui Huazhong University of Science and Technology Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Wuhan430074 China Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore487372 Singapore

In broadband Low Earth Orbit (LEO) satellite networks, efficient video delivery is achieved through multicast techniques, which combine the bandwidth of both the satellite Access Networks and the Backbone Networks, resulting in significant bandwidth savings. However, previous research on multicast routing in LEO constellations has primarily focused on multicast in an ideal state, overlooking the challenges of obstacle avoidance posed by satellite failures or link congestion in real-world scenarios. In this paper, we introduce Software-Defined Multicast (SDM) to broadband LEO constellations and propose a robust SDM policy capable of effectively managing the dynamic nature of LEO constellation networks. To address the obstacle avoidance requirements, we develop an Obstacle-Avoiding Rectilinear Steiner Tree (OA-RST) algorithm and construct an intelligent multicast routing tree. Additionally, we present a resilient multicast management strategy to ensure seamless maintenance and management of multicast groups, even in the face of frequent satellite switching, dynamic membership updates, and resource contention among multiple groups. Simulation results demonstrate the effectiveness and efficiency of our proposed routing tree construction algorithm and management scheme in minimizing the total multicast tree length, conserving network bandwidth resources, and maintaining stable routing in the network. © 1967-2012 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Reconfiguration of vertex-disjoint shortest paths on graphs

引用

Journal of Graph Algorithms and Applications 2024年第3期28卷 87-101页

作者： Saito, Rin Eto, Hiroshi Ito, Takehiro Uehara, Ryuhei Graduate School of Information Sciences Tohoku University Sendai Japan School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan School of Information Science Japan Advanced Institute of Science and Technology Nomi Japan

We introduce and study reconfiguration problems for (internally) vertex-disjoint shortest paths: Given two tuples of internally vertex-disjoint shortest paths for fixed terminal pairs in an unweighted graph, we are asked to determine whether one tuple can be transformed into the other by exchanging a single vertex of one shortest path in the tuple at a time, so that all intermediate results remain tuples of internally vertex-disjoint shortest paths. We also study the shortest variant of the problem, that is, we wish to minimize the number of vertex-exchange steps required for such a transformation, if exists. These problems generalize the well-studied Shortest Path Reconfiguration problem. In this paper, we analyze the complexity of these problems from the viewpoint of graph classes, and give some interesting contrast. © 2024, Brown University. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Mobile mini-fluorimeter for antibiotic aptasensing based on surface-plasmonic effect of burlike nanogolds enhanced by digitized imaging diagnosis

引用

Chinese Chemical Letters 2024年第5期35卷 418-422页

作者： Tiantian Man Fulin Zhu Yaqi Huang Yuhao Piao Yan Su Shengyuan Deng Ying Wan School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of Metabolic Engineering and Biosynthesis Technology Ministry of Industry and Information TechnologySchool of Environmental and Biological EngineeringNanjing University of Science and TechnologyNanjing 210094China

Antibiotic abuse now poses a grave threat to global ecology and bestirs public concerns about the residue issue in daily *** traceability measurements along supply chain or logistic circulation have become increasingly essential given the labile nature of diverse synthetic residuals on *** an attempt to answer this urgency,here a miniaturized fluorometric aptasensor prototype was contrived that catered to the point-of-care screening norm for two typical additives:chloramphenicol and *** key target-indicating module worked in vitro based on the competitive binding-induced fluorescence recovery of fluorescein-labeled aptamers,which were photobleached beforehand in the format of double helix on burlike nanogold ***“prickly”geometry of the latter not just enriched the capture probes at preferentially substrate-accessible spires;but also contributed to a tip-enhanced surface plasmon effect,sensitizing the signal-on during the duplex dissociation even at nanomolar threshold of the *** the other hand,to encompass a full portable,a set of optical devices were mounted within a 3D-printed cartridge(adaptor)to converge the light beam and route it towards the detector,for which the smartphone camera came up in handy with a home-developed App for calibrating the emissive *** by the high-dynamic-range compression,an imaging diagnostic algorithm was built in to grid and digitize each slide in the album for augmented detection ***,a novel bio-to-silico integration was invented that capable of in situ rapid reporting on the antibiotic presence with high sensitivity and *** field practices in spiked milk on sales proved the precision and rudimentary feasibility of the well-assembled model of appliance,thus holding nice prospects in nonexpert(e.g.,family and local community)utilities for foodborne antibiotic identification.

关键词： Chloramphenicol and enrofloxacin Aptasensor Gold nanoburs Smartphone fluorimetric suite Digitized image postprocessing

来源：评论

学校读者我要写书评

暂无评论

Traffic sign recognition model based on scale sequence features and high-order spatial interactions

引用

Neural Computing and Applications 2025年第5期37卷 3605-3620页

作者： Zhang, Gan Wang, Yafei Li, Wenju Fu, Xianping School of Information Science and Technology Dalian Maritime University Dalian116026 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China Pengcheng Laboratory Shenzhen518055 China

Traffic sign recognition is an integral part of driver assistance systems play a crucial role in enhancing road safety. Due to a large number of challenging targets, such as occlusion, distortion, and small targets in actual scenes, existing methods still have bottlenecks in the accuracy of detection and recognition. Therefore, this paper proposes a real-time traffic sign recognition model based on scale sequence features (SSFs) and high-order spatial interactions (HOSIs) on the basis of YOLOv5. This model extracted scale-invariant SSF using a high-dimensional convolution on the underlying feature map to improve the detection effect of multi-scale targets. At the same time, recursive gated convolution modules are integrated into the feature pyramid network, expanding the interactions to arbitrary order and providing richer feature information for high-order convolutions. In addition, a cross-stage partial (CSP) structure is incorporated into the spatial pooling pyramid, which improves the structure’s performance without introducing excessive computational complexity. The experimental results show that the proposed model achieves 95.5% and 99.92% of mAP on Tsinghua–Tencent 100K (TT100K) and German Traffic Sign Recognition Benchmark (GTSRB), respectively, which surpass the performance of the most advanced model and meets the requirements of real-time detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

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：