检索结果-内蒙古大学图书馆

Object-Attribute-Relation Representation Based Video Semantic Communication

IEEE Journal on Selected Areas in Communications 2025年第7期43卷 2446-2461页

作者： Du, Qiyuan Duan, Yiping Yang, Qianqian Tao, Xiaoming Debbah, Merouane Tsinghua University Department of Electronic Engineering Beijing China Beijing China State Key Laboratory of Space Network and Communications Beijing China Zhejiang University College of Information Science and Electronic Engineering Hangzhou China Xinjiang University School of Computer Science and Technology Xinjiang China Khalifa University KU6G Research Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates University Paris-Saclay CentraleSupelec Gif-sur-Yvette91192 France

With the rapid growth of multimedia data volume, there is an increasing need for efficient video transmission in applications such as virtual reality and future video streaming services. Semantic communication is emerging as a vital technique for ensuring efficient and reliable transmission in low-bandwidth, high-noise settings. However, most current approaches focus on joint source-channel coding (JSCC) that depends on end-to-end training. These methods often lack an interpretable semantic representation and struggle with adaptability to various downstream tasks. In this paper, we introduce the use of object-attribute-relation (OAR) as a semantic framework for videos to facilitate low bit-rate coding and enhance the JSCC process for more effective video transmission. We utilize OAR sequences for both low bit-rate representation and generative video reconstruction. Additionally, we incorporate OAR into the image JSCC model to prioritize communication resources for areas more critical to downstream tasks. Our experiments on traffic surveillance video datasets assess the effectiveness of our approach in terms of video transmission performance. The empirical findings demonstrate that our OAR-based video coding method not only outperforms H.265 coding at lower bit-rates but also synergizes with JSCC to deliver robust and efficient video transmission. © 1983-2012 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Stackelberg Game-Based Pricing and Offloading for the DVFS-Enabled MEC systems

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2502-2515页

作者： Mei, Jing Zeng, Cuibin Tong, Zhao Yang, Zhibang Li, Keqin Hunan Normal University College of Information Science and Engineering Changsha410081 China Changsha University in Changsha Hunan Province Key Laboratory of Industrial Internet Technology and Security Hunan 410022 China Hunan University College of Information Science and Engineering Changsha410012 China National Supercomputing Center Hunan Changsha410082 China State University of New York Department of Computer Science New YorkNY12561 United States

Due to the limited computing resources of both mobile devices (MDs) and the mobile edge computing (MEC) server, devising reasonable strategies for MD task offloading, MEC server resource pricing, and resource allocation is crucial. In this paper, a scenario is considered, comprising multiple MDs and a single MEC server. Each MD has a divisible task in each time slot, allowing for partial offloading and the option to discard parts of the task. The MEC server contains multiple computing units with the same computing power, and its computing resources can be dynamically adjusted through dynamic voltage and frequency scaling (DVFS) according to the size of tasks offloaded by MDs. At any given time slice, a Stackelberg game is formulated based on the strategies of the MDs and the strategy of the MEC server. An iterative evolution algorithm is employed to explore the optimal strategies for MDs and the MEC server. Simulation results demonstrate that both parties can reach an equilibrium state through the game, and these experiments confirm that the algorithm effectively enhances system efficiency. © 2004-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Approaches for Myopic Maculopathy Plus Lesions Segmentation 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Xiao, Fan Hou, Junlin Xu, Jilan Xu, Yiqian Zhang, Bo Zhang, Yuejie Zou, Haidong Feng, Rui Academy for Engineering and Technology Fudan University Shanghai China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopia is a leading cause of visual impairment and blindness in several countries. Effective diagnosis and intervention are crucial, typically relying on manual image analysis by ophthalmologists, which is time-consuming and experience-dependent. In this work, we introduce an ensemble of deep learning techniques for myopic maculopathy plus lesions segmentation. Specifically, we utilize UNet, UNet++, and DeeplabV3+ to segment three lesions with strong data augmentation. Our ensembled model has proved to be effective in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). This dataset covers classification, segmentation, and spherical equivalent prediction, fostering automated analysis research. Extensive experiments on the MMAC dataset reveal the superior performance of our proposed approach, which ranked 1st on the challenge leaderboard. This work addresses a critical need for accurate and efficient myopic maculopathy diagnosis and intervention. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stream Algorithm for Spatio-Temporal Fusion in Remote Sensing

引用

IEEE Geoscience and Remote Sensing Letters 2025年

作者： Wang, Shiying Zou, Xuechao Wang, Wentao Liu, Yao Zhang, Shun Cao, Tengfei Tao, Pin Qinghai University School of Computer Technology and Application Xining China Qinghai University Intelligent Computing and Application Laboratory of Qinghai Province China School of Computer Science & Technology Beijing China Tsinghua University Department of Computer Science and Technology Beijing China Ministry of Education Key Laboratory of Pervasive Computing China

The spatio-temporal fusion technology can effectively solve the problem of missing time series data. However, existing algorithms often struggle to accurately capture surface feature changes and fine details. To overcome these limitations, this paper introduces FemSTF, a flexible two-stream algorithm for remote sensing spatio-temporal fusion, which consists of three main stages: image sharpening, image fusion, and edge optimization. In the first stage, techniques such as interpolation, classification, and blending are employed to address missing pixel values caused by minimal input data. In the second stage, a two-stream strategy is introduced to enhance fusion accuracy, enabling the algorithm to capture regional detail changes with high sensitivity to surface variations. The third stage focuses on edge optimization, generating high-resolution predictive images under minimal input conditions (three images) while retaining rich texture and edge details. Notably, FemSTF achieves a performance comparable to that of methods requiring five input images. Experimental results demonstrate that FemSTF outperforms mainstream algorithms across multiple datasets. Ablation experiments confirm the effectiveness of the two-stream strategy, highlighting its role in enhancing remote sensing data processing accuracy. This study offers an efficient solution for spatio-temporal fusion, demonstrating great potential in the field. © 2004-2012 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

NR-Isomap: An Incremental Approach with Gaussian Process Kernels for Denoising 6

NR-Isomap: An Incremental Approach with Gaussian Process Ker...

引用

6th International Conference on Big Data and Artificial Intelligence, BDAI 2023

作者： Yousaf, Mahwish Khan, Muhammad Saaadat Shakoor Ullah, Shamsher Wang, Shou Jing, Li University of Science and Technology of China School of Computer Science and Technology Hefei China Chinese Academy of Sciences Institute of Solid-State Physics Key Laboratory of Materials Physics Hefei China Unit of System and Technology University of Management and Technology Department Knowledge Sialkot Pakistan

ISBN: (纸本)9798350303667

The Isomap is a popular nonlinear dimensionality reduction method often used for low-dimensional embedding space. When the big data is noisy, Isomap often fails because of the graph structure' Short-Circuit Edges (SCE) problem. In this paper, an incremental Noise-Reduction Isomap (NR-Isomap) approach is to address the SCE problem in a graph structure. The GP kernels are combined with the manifold learning approach and provide significant results. NR-Isomap is based on the Hessian Locally Linear Embedding (HLLE) algorithm with Gaussian Process (GP) kernels. The HLLE algorithm provides the optimal solution to the SCE problem caused by an overly noisy dataset. NR-Isomap provides an answer to the Isomap SCE problem in noisy big data problems that cannot be handled using existing methods. Therefore, the GP kernel significantly improves and measures the performance of the NRI-somap accuracy. Our NR-Isomap method outperforms experiments on SK-Learn datasets and shows efficient results compared to Isomap. Our NR Isomap is much more efficient and faster compared to Isomap. The efficiency and accuracy of the NR-Isomap method are demonstrated theoretically and compared with other manifold learning methods. © 2023 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Fusing Latent Dirichlet Allocation with Fuzzy Matching for Improved Topic Expressiveness in Text Mining 3

Fusing Latent Dirichlet Allocation with Fuzzy Matching for I...

引用

3rd International Conference on Digital Data Processing, DDP 2023

作者： Yu, Jiahua Fong, Simon Song, Qun Tang, Lianggui Millham, Richard C. University of Macau Taipa Department of Computer and Information Science Macau China Chongqing Technology and Business University Chongqing Key Laboratory of Intelligent Perception and Blockchain Department of Artificial Intelligence Chongqing China Durban University of Technology Faculty of Accounting and Informatics Durban South Africa

ISBN: (纸本)9798350329018

This paper introduces an innovative fusion of Latent Dirichlet Allocation (LDA) with fuzzy matching, aiming to elevate the expressiveness of topics in text mining. Traditional LDA techniques, while effective, often fall short in capturing the intricate semantic nuances and contextual variations of keywords within a given document. In this enhanced version, we propose a methodology that seamlessly integrates LDA with fuzzy matching algorithms, offering a more refined approach to topic modeling. The key distinction lies in the enhanced model's ability to not only identify keywords but also accommodate their diverse forms and variations, thus creating a more comprehensive and expressive representation of topics. The integration of fuzzy matching enriches the association between topics and the underlying text by considering partial matches and accounting for variations in spelling, structure, and context. This enhancement ensures a more accurate reflection of the intricate relationships between topics and the surrounding text, fostering a deeper understanding of the document's content. To validate the effectiveness of our proposed approach, we conducted extensive experiments on diverse textual datasets. Results demonstrate that the enhanced model consistently outperforms traditional LDA in terms of capturing topic expressiveness. By revealing the subtle nuances and contextual richness within documents, our methodology contributes to a more nuanced and insightful interpretation of textual data. This paper provides a significant advancement in the field of text mining, offering researchers and practitioners an enhanced tool for uncovering the hidden layers of meaning embedded in large corpora of text. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On Differentiation Among Pilot Signals of Multiple Mobile Targets in Retro-Reflective Beamforming for Wireless Power Transmission

引用

Engineering 2023年第11期30卷 55-62页

作者： Xin Wang Long Li Tie Jun Cui Mingyu Lu School of Electrical Engineering Chongqing UniversityChongqing 400044China School of Electronic Engineering Xidian UniversityXi’an 710071China State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast UniversityNanjing 210096China Department of Electrical and Computer Engineering West Virginia University Institute of TechnologyBeckleyWV 25801USA

An experimental study is conducted on several retro-reflective beamforming schemes for wireless power transmission to multiple wireless power receivers(referred to herein as“targets”).The experimental results demonstrate that,when multiple targets broadcast continuous-wave pilot signals at respective frequencies,a retro-reflective wireless power transmitter is capable of generating multiple wireless power beams aiming at the respective targets as long as the multiple pilot signals are explicitly separated from one another by the wireless power ***,various practical complications are identified when the pilot signals of multiple targets are not appropriately differentiated from each other by the wireless power ***,when multiple pilot signals are considered to be carried by the same frequency,the wireless power transmission performance becomes heavily dependent on the interaction among the pilot signals,which is highly undesirable in *** conclusion,it is essential for a retro-reflective wireless power transmitter to explicitly discriminate multiple targets’pilot signals among each other.

关键词： Wireless power transmission Microwave antenna array Retro-reflective beamforming Pilot signal Multiple access

来源：评论

学校读者我要写书评

暂无评论

An Anisotropic Time-Domain Discontinuous Galerkin VIE method for Analysis of Scattering from Magnetized Plasma 11

An Anisotropic Time-Domain Discontinuous Galerkin VIE method...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Zhao, Ying Neng, Wenjie Ding, Dazhi Nanjing Tech University College of Computer Science and Information Engineering Nanjing China State Key Laboratory of Millimeter Waves Nanjing China Nanjing University of Science and Technology Department of Communication Engineering Nanjing China

ISBN: (纸本)9798350326277

We propose a time-domain discontinuous Galerkin volume integral equation (DGTD-VIE) method for transient scattering property from magnetized plasma. Due to the dispersive and anisotropic permittivity of the magnetized plasma, the relationship between the volumetric current and the total electric field is established through recursive convolution. Numerical examples are presented to validate the accuracy and effectiveness of the proposed method. © 2023 IEEE.

关键词： anisotropic medium Discontinuous Galerkin integral equation method magnetized plasma

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-Based Benchmarking Experiment Settings for Evolutionary Multi-Objective Optimization

arXiv

引用

arXiv 2025年

作者： Pang, Lie Meng Ishibuchi, Hisao Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

When we manually design an evolutionary optimization algorithm, we implicitly or explicitly assume a set of target optimization problems. In the case of automated algorithm design, target optimization problems are usually explicitly shown. Recently, the use of large language models (LLMs) for the design of evolutionary multi-objective optimization (EMO) algorithms have been examined in some studies. In those studies, target multi-objective problems are not always explicitly shown. It is well known in the EMO community that the performance evaluation results of EMO algorithms depend on not only test problems but also many other factors such as performance indicators, reference point, termination condition, and population size. Thus, it is likely that the designed EMO algorithms by LLMs depends on those factors. In this paper, we try to examine the implicit assumption about the performance comparison of EMO algorithms in LLMs. For this purpose, we ask LLMs to design a benchmarking experiment of EMO algorithms. Our experiments show that LLMs often suggest classical benchmark settings: Performance examination of NSGA-II, MOEA/D and NSGA-III on ZDT, DTLZ and WFG by HV and IGD under the standard parameter specifications. Copyright © 2025, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Incorporating Improved Sinusoidal Threshold-based Semi-supervised Method and Diffusion Models for Osteoporosis Diagnosis

Incorporating Improved Sinusoidal Threshold-based Semi-super...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wenchi Ke Hu Chen Yi Zhang Xiong Deng College of Computer Science Sichuan University China Key Laboratory of Data Protection and Intelligent Management Sichuan University China Computer Science Department Stevens Institute of Technology USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Osteoporosis is a common skeletal disease that seriously affects patients’ quality of life. Traditional osteoporosis diagnosis methods are expensive and complex. The semi-supervised model based on diffusion model and class threshold sinusoidal decay proposed in this paper can automatically diagnose osteoporosis based on patient’s imaging data, which has the advantages of convenience, accuracy, and low cost. Unlike previous semi-supervised models, all the unlabeled data used in this paper are generated by the diffusion model. Compared with real unlabeled data, synthetic data generated by the diffusion model show better performance. In addition, this paper proposes a novel pseudo-label threshold adjustment mechanism, Sinusoidal Threshold Decay, which can make the semi-supervised model converge more quickly and improve its performance. Specifically, the method is tested on a dataset including 749 dental panoramic images, and its achieved leading detect performance and produces a 80.10% accuracy.

关键词： Training Osteoporosis Accuracy Imaging Signal processing Diffusion models Data models Speech processing Synthetic data Diseases

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：