检索结果-内蒙古大学图书馆

MCDS: An Effective Multi-UAV Collaborative Decision-Making System in Mobile Edge computing Networks

IEEE Internet of Things Journal 2025年

作者： Xiong, Naixue Zhong, Weiyu Chen, Yuxiang He, Dacheng Li, Yuhui Chen, Linshu Liang, Wei Sanya Research Institute of Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology China Sanya Research Institute of Hunan University of Science and Technology Hunan University School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Information Science and Engineering China The Hong Kong Polytechnic University Department of Computing Hong Kong

Mobile Edge computing (MEC) pushes computing resources from the network center to the network edge to provide efficient and reliable computing services. However, due to the mobility and diversity of mobile users (MUs), edge servers (ESs) are likely to be overloaded, which leads to a rapid decline in the quality of service provided by the MEC system. This paper introduces unmanned aerial vehicles (UAVs) to solve the problem of ES overload. This paper presents an effective Multi-UAV Collaborative Decision-Making System (MCDS) tailored to optimize task offloading and resource allocation in MEC networks. The proposed system seeks to reduce task computing delays and energy consumption while guaranteeing timely task completion and compliance with resource constraints. We design a distributed two-stage optimization algorithm to jointly optimize the task offloading decision and resource allocation of the collaborative computing system (UAVs, ESs, and MUs). To address the flight cooperation problem of multi-UAVs, we also proposed a task-aware scheduling algorithm for multi-UAVs. In addition, we conducted a large number of simulation experiments. Experimental results show that our two-stage optimization scheme is lower than other benchmark algorithms in terms of task completion delay, energy consumption and total cost of objective function. Specifically, compared with seven baseline algorithms under three different system setting scenarios, our algorithm reduces the total cost by an average of 38.79%, the energy consumption by an average of 40.70%, and the delay by an average of 15.67%. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Mini-InternVL: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance

引用

Visual Intelligence 2024年第1期2卷 1-17页

作者： Gao, Zhangwei Chen, Zhe Cui, Erfei Ren, Yiming Wang, Weiyun Zhu, Jinguo Tian, Hao Ye, Shenglong He, Junjun Zhu, Xizhou Lu, Lewei Lu, Tong Qiao, Yu Dai, Jifeng Wang, Wenhai Shanghai AI Laboratory Shanghai 200232 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Computer Science Nanjing University Nanjing 210023 China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen 518055 China School of Computer Science Fudan University Shanghai 200433 China SenseTime Research Shanghai 200233 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing 100084 China Department of Information Engineering The Chinese University of Hong Kong 999077 Hong Kong

Multi-modal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a wide range of domains. However, the large model scale and associated high computational cost pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices, thereby hindering their widespread application. In this work, we introduce Mini-InternVL, a series of MLLMs with parameters ranging from 1 billion to 4 billion, which achieves 90% of the performance with only 5% of the parameters. This significant improvement in efficiency and effectiveness makes our models more accessible and applicable in various real-world scenarios. To further promote the adoption of our models, we are developing a unified adaptation framework for Mini-InternVL, which enables our models to transfer and outperform specialized models in downstream tasks, including autonomous driving, medical image processing, and remote sensing. We believe that our models can provide valuable insights and resources to advance the development of efficient and effective MLLMs. © The Author(s) 2024.

关键词： Knowledge distillation Lightweight multi-modal large language model Vision-language model Visual instruction tuning

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional nanoscale reduced-angle ptycho-tomographic imaging with deep learning(RAPID)

引用

eLight 2023年第1期3卷 198-210页

作者： Ziling Wu Iksung Kang Yudong Yao Yi Jiang Junjing Deng Jeffrey Klug Stefan Vogt George Barbastathis Department of Mechanical Engineering Massachusetts Institute of TechnologyCambridgeMA 02139USA Department of Electrical Engineering and Computer Science Massachusetts Institute of TechnologyCambridgeMA 02139USA Argonne National Laboratory LemontIL 60439USA Singapore-MIT Alliance for Research and Technology(SMART)Centre Singapore 138602Singapore Present Address:Singapore-MIT Alliance for Research and Technology(SMART)Centre Singapore 138602Singapore Present Address:University of California BerkeleyCA 94720USA

X-ray ptychographic tomography is a nondestructive method for three dimensional(3D)imaging with nanometer-sized resolvable *** size of the volume that can be imaged is almost arbitrary,limited only by the penetration depth and the available scanning *** we present a method that rapidly accelerates the imaging operation over a given volume through acquiring a limited set of data via large angular reduction and compensating for the resulting ill-posedness through deeply learned *** proposed 3D reconstruction method“RAPID”relies initially on a subset of the object measured with the nominal number of required illumination angles and treats the reconstructions from the conventional two-step approach as ground *** is then trained to reproduce equal fidelity from much fewer *** training,it performs with similar fidelity on the hitherto unexamined portions of the object,previously not shown during training,with a limited set of *** our experimental demonstration,the nominal number of angles was 349 and the reduced number of angles was 21,resulting in a×140 aggregate speedup over a volume of 4.48×93.18×3.92μm^(3) and with(14 nm)^(3) feature size,i.e.-10^(8) ***’s key distinguishing feature over earlier attempts is the incorporation of atrous spatial pyramid pooling modules into the deep neural network framework in an anisotropic *** found that adjusting the atrous rate improves reconstruction fidelity because it expands the convolutional kernels’range to match the physics of multi-slice ptychography without significantly increasing the number of parameters.

关键词： X-ray ptychographic tomography Deep learning Reduced-angle Rapid imaging Atrous spatial pyramid pooling Anisotropic

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Model for Clinical Time Series Prediction: Enhancing ICU Readmission Prediction

An Attention-Based Model for Clinical Time Series Prediction...

引用

International eConference on computer and Knowledge engineering (ICCKE)

作者： Hananeh Sadat Madinei Mohammad Reza Keyvanpour Seyed Vahab Shojaedini Department of Computer Engineering Data Mining Laboratory Faculty of Engineering Alzahra University Tehran Iran Department of Electrical Engineering Iranian Research Organization for Science and Technology Tehran Iran

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

In recent years, time series prediction has become a highly interesting topic in various applied areas, including clinical time series analysis. Hospitals and other clinical healthcare systems collect Electronic Health Records. These records contain important information that needs to be mined. This information provides a solid basis for predicting hospital readmission, helping to improve healthcare, enhance patient outcomes, and optimize hospital resources. This study introduces a novel deep learning attention-based approach for predicting 30-day ICU readmissions using clinical time series information extracted from the MIMIC III dataset. This approach incorporates time-aware positional encoding into the attention mechanism to enhance predictive performance by capturing the temporal representation of data and considering the temporal order of clinical time series data. This model is compared with cutting-edge models. The significant enhancements in the model performance achieved by the proposed method highlight the effectiveness of incorporating time-aware positional encoding in capturing temporal dependencies and improving prediction outcomes. These results underscore the potential of advanced attention mechanisms in clinical time series analysis.

关键词： Deep learning Analytical models Attention mechanisms Hospitals Computational modeling Time series analysis Predictive models Encoding Data models Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Structural RC computer aided intelligent analysis and computational performance via experimental investigations

引用

Structural engineering and Mechanics 2024年第3期90卷 253-261页

作者： Huang, Y.C. Lulios, TuMuli Chang, Chu-Ho Noor, M. Nasir Shao, Jen-Chung Chiu, Chien-Liang Lee, Tsair-Fwu Wang, Renata Information Technology Faculty Duy Tân University 254 Nguyen Van Linh Danang Viet Nam Princess Margaret Hospital Funafuti Island Private Mail Bag Tuvalu College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan College of Maritime National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Medical Physics and Informatics Laboratory of Electronics Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Information and Research Center of China 1/9 Road: 2 Block: D Section: 15 Dhaka1216 Bangladesh

This research explores a new finite element model for the free vibration analysis of bi-directional functionally graded (BDFG) beams. The model is based on an efficient higher-order shear deformation beam theory that incorporates a trigonometric warping function for both transverse shear deformation and stress to guarantee traction-free boundary conditions without the necessity of shear correction factors. The proposed two-node beam element has three degrees of freedom per node, and the inter-element continuity is retained using both C1 and C0 continuities for kinematics variables. In addition, the mechanical properties of the (BDFG) beam vary gradually and smoothly in both the in-plane and out-of-plane beam’s directions according to an exponential power-law distribution. The highly elevated performance of the developed model is shown by comparing it to conceptual frameworks and solution procedures. Detailed numerical investigations are also conducted to examine the impact of boundary conditions, the bi-directional gradient indices, and the slenderness ratio on the free vibration response of BDFG beams. The suggested finite element beam model is an excellent potential tool for the design and the mechanical behavior estimation of BDFG structures. © 2024 Techno-Press, Ltd.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

RECURSIVE DISENTANGLEMENT NETWORK 10

RECURSIVE DISENTANGLEMENT NETWORK

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Chen, Yixuan Shi, Yubin Li, Dongsheng Wang, Yujiang Dong, Mingzhi Zhao, Yingying Dick, Robert Lv, Qin Yang, Fan Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Microsoft Research Asia Shanghai China Department of Computing Imperial College London London United Kingdom Department of Electrical Engineering and Computer Science University of Michigan Michigan United States Department of Computer Science University of Colorado Boulder Boulder United States School of Microelectronics Fudan University Shanghai China

Disentangled feature representation is essential for data-efficient learning. The feature space of deep models is inherently compositional. Existing β-VAE-based methods, which only apply disentanglement regularization to the resulting embedding space of deep models, cannot effectively regularize such compositional feature space, resulting in unsatisfactory disentangled results. In this paper, we formulate the compositional disentanglement learning problem from an information-theoretic perspective and propose a recursive disentanglement network (RecurD) that propagates regulatory inductive bias recursively across the compositional feature space during disentangled representation learning. Experimental studies demonstrate that RecurD outperforms β-VAE and several of its state-of-the-art variants on disentangled representation learning and enables more data-efficient downstream machine learning tasks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Differentiating structure of in situ and ex situ formation of laser-induced graphene hybrids

引用

Rare Metals 2022年第9期41卷 3035-3044页

作者： Li-Bei Huang Wei-Hua Guo Le Cheng Jian-Jun Su Yun Song Fei-Jun Hu Ying Lo Law Zheng Yan Jian Lin Ru-Quan Ye State Key Laboratory of Marine Pollution Department of ChemistryCity University of Hong KongHong Kong999077China Department of Mechanical and Aerospace Engineering University of MissouriColumbiaMO65211USA Department of Biomedical Biological&Chemical EngineeringUniversity of MissouriColumbiaMO65211USA Department of Electrical Engineering and Computer Science University of MissouriColumbiaMO65211USA City University of Hong Kong Shenzhen Research Institute Shenzhen518057China

Laser-induced graphene(LIG)has been exploited in various fields,such as batteries,water treatment,and flexible actuators and sensors,with the advantages of ease in patternable fabrication and graphene/metal hybrid *** in situ method which includes a single lase step and the ex situ method which uses two lase steps are both widely implemented to synthesize graphene/metal ***,the differences in the structures and properties of the resulting hybrids are not fully ***,we investigate the advantages of ex situ and in situ methods for preparing LIG hybrids using NiFe/LIG as an *** morphology,elemental composition,resistance to strong acid,and application in electrocatalysis and dye adsorption of ex situ and in situ NiFe/LIG hybrids were systematically studied and ***-dispersive X-ray spectrometry(EDS)and vibrating sample magnetometry(VSM)results confirmed the structural differences between the NiFe/LIG *** nanoparticles are mostly wrapped by carbon layers in the in situ NiFe/LIG hybrid,while the ex situ NiFe/LIG hybrid largely exposes the metal *** structural differences are significant for tailoring performance in applications,such as wastewater treatment and *** work provides insights into the synthesis and properties of LIGs and has important implications for future applications.

关键词： Ex situ In situ Laser-induced graphene Metal-containing hybrids Oxygen evolution reaction Dye adsorption

来源：评论

学校读者我要写书评

暂无评论

Optical polarized orthogonal matrix

引用

Photonics research 2025年第2期13卷 373-381页

作者： SHUJUN ZHENG JIAREN TAN XIANMIAO XU HONGJIE LIU YI YANG XIAO LIN XIAODI TAN Information Photonics Research Center College of Photonic and Electronic EngineeringFujian Normal UniversityFuzhou 350117China Department of Electrical and Computer Engineering Duke UniversityDurhamNorth Carolina 27708USA College of Photonic and Electronic Engineering Key Laboratory of Opto-Electronic Science and for Medicine of Ministry of EducationFujian Provincial Key Laboratory of Photonics TechnologyFujian Provincial Engineering Technology Research Center of Photoelectric Sensing ApplicationFujian Normal UniversityFuzhou 350117China

Multiplexing technology serves as an effective approach to increase both information storage and transmission ***,when exploring multiplexing methods across various dimensions,the polarization dimension encounters limitations stemming from the finite orthogonal *** that only two mutually orthogonal polarizations are identifiable on the basic Poincarésphere,this poses a hindrance to polarization *** overcome this challenge,we propose a construction method for the optical polarized orthogonal matrix(OPOM),which is not constrained by the number of orthogonal ***,we experimentally validate its application in high-dimensional multiplexing of polarization *** explore polarization holography technology,capable of recording amplitude,phase,and polarization,for the purpose of recording and selective reconstruction of polarization *** research reveals that,despite identical polarization states,multiple images can be independently manipulated within distinct polarization channels through orthogonal polarization combinations,owing to the orthogonal selectivity among information.

关键词： two mutually orthogonal polarizations optical polarized orthogonal matrix construction method multiplexing methods polarization dimension multiplexing orthogonal polarization combinations polarization holography

来源：评论

学校读者我要写书评

暂无评论

Toward Scene Understanding with Depth and Object-Aware Clustering in Contested Environment 22

Toward Scene Understanding with Depth and Object-Aware Clust...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Bhurtel, Manish Siwakoti, Yuba R. Rawat, Danda B. Sadler, Brian M. Fossaceca, John M. Rice, Daniel O. Howard University Department of Electrical Engineering and Computer Science WashingtonDC United States U.S. Army Research Laboratory AdelphiMD United States Bae Systems Fast Labs BurlingtonMA United States

ISBN: (纸本)9798350345346

Scene understanding in a contested battlefield is one of the very difficult tasks for detecting and identifying threats. In a complex battlefield, multiple autonomous robots for multi-domain operations are likely to track the activities of the same threat/objects leading to inefficient and redundant tasks. To address this problem, we propose a novel and effective object clustering framework that takes into account the position and depth of objects scattered in the scene. This framework enables the robot to focus solely on the objects of interest. Our system model incorporates YOLOv5 object detection model (ODM) and a pre-trained depth estimation model (DEM), whose outputs are fed into the KMeans Clustering (KM C) model. To train YOLOv5, we create our own battlefield dataset entitled 'Common Objects in Battlefield (COBA)' which is split into a training dataset and a validation dataset using our customized object-aware stratified 7-fold cross-validation technique. We present the creation of minimum optimal clusters assuming the minimum number of available battlefield robots. These clusters exhibit accurate relative distances among objects, further validating the effectiveness of our approach for depth and object-aware clustering for scene understanding. Overall, our proposed approach facilitates efficient work division among robots, enhances decision-making capabilities, and helps to improve situational awareness in battlefield scenarios. © 2023 IEEE.

关键词： clustering depth estimation object detection scene understanding situational awareness task allocation

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：