检索结果-内蒙古大学图书馆

Class-conditional domain adaptation for semantic segmentation

Computational Visual Media 2024年第5期10卷 1013-1030页

作者： Yue Wang Yuke Li James H.Elder Runmin Wu Huchuan Lu School of Information and Communication Engineering Dalian University of TechnologyDalian 116024China School of Computer Science Wuhan UniversityWuhan 430072China Department of Electrical Engineering and Computer Science York UniversityToronto M3J 1P3Canada Department of Computer Science the University of Hong KongHong Kong 999077China

Semantic segmentation is an important sub-task for many ***,pixel-level ground-truth labeling is costly,and there is a tendency to overfit to training data,thereby limiting the generalization *** domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain(including less expensive synthetic domain)to be adapted to a novel target *** conventional approach involves automatic extraction and alignment of the representations of source and target domains *** limitation of this approach is that it tends to neglect the differences between classes:representations of certain classes can be more easily extracted and aligned between the source and target domains than others,limiting the adaptation over all ***,we address:this problem by introducing a Class-Conditional Domain Adaptation(CCDA)*** incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and ***,they measure the segmentation,shift the domain in a classconditional manner,and equalize the loss over *** results demonstrate that the performance of our CCDA method matches,and in some cases,surpasses that of state-of-the-art methods.

关键词： domain adaptation generative adversarial networks semantic segmentation cityscapes

来源：评论

学校读者我要写书评

暂无评论

Autonomous trajectory tracking control method for an agricultural robotic vehicle

引用

International Journal of Agricultural and Biological engineering 2024年第1期17卷 215-224页

作者： Jin Yan Wenguang Zhang Yong Liu Wei Pan Xiaoyu Hou Zhiyu Liu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Information Engineering Xuzhou University of TechnologyXuzhou 221018JiangsuChina National Key Laboratory of Transient Physics Nanjing University of Science and TechnologyNanjing 210094China School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing 210094China

To address the nonlinearities and external disturbances in unstructured and complex agricultural environments,this paper investigates an autonomous trajectory tracking control method for agricultural ground ***,this paper presents the design and implementation of a lightweight,modular two-wheeled differential drive vehicle equipped with two drive wheels and two caster *** vehicle comprises drive wheel modules,passive wheel modules,battery modules,a vehicle frame,a sensor system,and a control ***,a novel robust trajectory tracking method was proposed,utilizing an improved pure pursuit ***,an Online Particle Swarm Optimization Continuously Tuned PID(OPSO-CTPID)controller was introduced to dynamically search for optimal control gains for the PID *** results demonstrate the superiority of the improved pure pursuit algorithm and the OPSO-CTPID control *** validate the performance,the vehicle was integrated with a seeding and fertilizing machine to realize autonomous wheat seeding in an agricultural *** outcomes reveal that the vehicle of this study completed a seeding operation exceeding 1 km in *** proposed method can robustly and smoothly track the desired trajectory with an accuracy of less than 10 cm for the root mean square error(RMSE)of the curve and straight lines,given a suitable set of parameters,meeting the requirements of agricultural *** findings of this study hold significant reference value for subsequent research on trajectory tracking algorithms for ground-based agricultural robots.

关键词： trajectory tracking autonomy control agricultural robotic vehicle online PSO continuously tuned PID dynamic pure pursuit algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Offloading Optimization in MEC and Vehicular-Fog Systems: A Distributed-TD3 Approach

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第11期25卷 16897-16909页

作者： Wakgra, Frezer Guteta Kar, Binayak Tadele, Seifu Birhanu Shen, Shan-Hsiang Khan, Asif Uddin The Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei106 Taiwan The School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar751024 India

The emergence of 5G networks has enabled the deployment of a two-tier edge and vehicular-fog network. It comprises Multi-access Edge Computing (MEC) and Vehicular-Fogs (VFs), strategically positioned closer to Internet of Things (IoT) devices, reducing propagation latency compared to cloud-based solutions and ensuring satisfactory quality of service (QoS). However, during high-traffic events like concerts or athletic contests, MEC sites may face congestion and become overloaded. Utilizing offloading techniques, we can transfer computationally intensive tasks from resource-constrained devices to those with sufficient capacity, for accelerating tasks and extending device battery life. In this research, we consider offloading within a two-tier MEC and VF architecture, involving offloading from MEC to MEC and from MEC to VF. The primary objective is to minimize the average system cost, considering both latency and energy consumption. To achieve this goal, we formulate a multi-objective optimization problem aimed at minimizing latency and energy while considering given resource constraints. To facilitate decision-making for nearly optimal computational offloading, we design an equivalent reinforcement learning environment that accurately represents the network architecture and the formulated problem. To accomplish this, we propose a Distributed-TD3 (DTD3) approach, which builds on the TD3 algorithm. Extensive simulations, demonstrate that our strategy achieves faster convergence and higher efficiency compared to other benchmark solutions. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Classification of Request-Based Mobility Load Balancing in Fog Computing

引用

computer Systems science & engineering 2023年第7期46卷 137-151页

作者： D.Deepa K.R.Jothi School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India

Every day,more and more data is being produced by the Internet of Things(IoT)*** data differ in amount,diversity,veracity,and *** of latency,various types of data handling in cloud computing are not suitable for many time-sensitive *** users move from one site to another,mobility also adds to the *** placing computing close to IoT devices with mobility support,fog computing addresses these *** efficient Load Balancing Algorithm(LBA)improves user experience and Quality of Service(QoS).Classification of Request(CoR)based Resource Adaptive LBA is suggested in this *** technique clusters fog nodes using an efficient K-means clustering algorithm and then uses a Decision Tree approach to categorize the *** decision-making process for time-sensitive and delay-tolerable requests is facilitated by the classification of *** does the operation based on these *** MobFogSim simulation program is utilized to assess how well the algorithm with mobility features *** outcome demonstrates that the LBA algorithm’s performance enhances the total system performance,which was attained by(90.8%).Using LBA,several metrics may be examined,including Response Time(RT),delay(d),Energy Consumption(EC),and *** the on-demand provisioning of necessary resources to IoT users,our suggested LBA assures effective resource usage.

关键词： Mobility load balancing classification clustering IoT devices

来源：评论

学校读者我要写书评

暂无评论

Interpreting Randomly Wired Graph Models for Chinese NER

引用

computer Modeling in engineering & sciences 2023年第1期134卷 747-761页

作者： Jie Chen Jiabao Xu Xuefeng Xi Zhiming Cui Victor S.Sheng The School of Electronic and Information Engineering SuzhouUniversity of Science and TechnologySuzhouChina The School of Computer Science Texas Tech UniversityTexasUSA

Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)***,most existing approaches only focus on improving the performance of models but ignore their *** this work,we propose a Randomly Wired Graph Neural Network(RWGNN)by using graph to model the structure of Neural Network,which could solve two major problems(word-boundary ambiguity and polysemy)of ***,we develop a pipeline to explain the RWGNNby using Saliency Map and Adversarial *** results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.

关键词： Named entity recognition graph neural network saliency map random graph network interpretation

来源：评论

学校读者我要写书评

暂无评论

Attentive Large Kernel Network with Mixture of Experts for Video Deblurring

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5575-5588页

作者： Zhang, Chaopeng Xiong, Ruiqin Fan, Xiaopeng Zhao, Debin Peking University Institute of Digital Media School of Electronic Engineering and Computer Science Beijing100871 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Peng Cheng Laboratory Shenzhen519055 China

Video deblurring is a fundamental problem in low-level vision, and many methods have employed designs based on CNNs and transformers. Traditional CNNs often require deeper architectures to achieve a larger receptive field, which may not be optimal for spatially non-uniform blurs and intense motion blurs. While transformers offer a large receptive field, their quadratic complexity due to attention designs typically imposes a significant computational burden. In addressing these issues, we present an Attentive Large Kernel Network with Mixture of Experts (ALK-MoE). In ALK-MoE, an attentive large kernel backbone network is proposed. On one hand, it inherently extends the network's receptive field through its large kernel design. On the other hand, it addresses the quadratic complexity of attention by employing a sophisticated attention design, thus maintaining its ability to capture long-range dependencies. Furthermore, to achieve more precise and robust alignment of inter-frame features using optical flow for better utilization of clear frames, a mixture of experts model is proposed. It involves integrating optical flow updates between different experts in a residual manner. Our ablation experiments and experiments on multiple datasets indicate that ALK-MoE achieves comparable or superior performance compared to Transformer-based methods, with lower complexity. © 1991-2012 IEEE.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning 24th

Multiple-Round Aggregation of Abstract Semantics for Secur...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Zhang, Jiao Li, Xiong Liang, Wei School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9789819615445

Federated Learning (FL) provides a valuable framework that allows for the collaborative training of models across distributed networks while maintaining the privacy of the data involved. The concept of secure aggregation is crucial in preserving both the privacy and integrity of data within FL systems. However, the deployment of secure aggregation encounters significant barriers. Conventional secure aggregation methods are primarily designed for single-round operations, which can become prohibitively expensive in scenarios that require multiple rounds. Additionally, these methods often struggle in large-scale environments characterized by heterogeneous data and models. This paper introduces the Multiple-Round Aggregation of Abstract Semantics (MRAAS), a novel scheme designed to address the aforementioned limitations in secure aggregation within heterogeneous FL environments. The MRAAS scheme enhances security and reduces the need for extensive data exchanges by aggregating abstracted model semantics instead of raw model gradients, facilitating secure, multiple rounds of aggregation. Key innovations of MRAAS include an advanced abstraction technique, robustness against participant drop-out, and the use of recyclable secrets. These innovations collectively enhance system resilience and reduce the necessity for frequent cryptographic renewals. Our theoretical evaluations focus on the security features of MRAAS. Empirical validations conducted through comparative analyses utilizing two public datasets confirm the superiority of MRAAS. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Game-Theoretic Approach for Integrated Sensing and Computation Offloading in Vehicular Edge Networks: A Utility Maximization Design

引用

IEEE Internet of Things Journal 2025年第13期12卷 23694-23708页

作者： Wang, Lina Wu, Weihong Dai, Minghui Zh, Haijun University of Science and Technology Beijing department of Communication Engineering China Donghua University School of Computer Science and Technology Shanghai China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing China

In recent years, with the rapid development of the Internet of Vehicles (IoVs) and the widespread application of integrated sensing and communication (ISAC) in the IoVs, the integrated sensing and computation offloading in vehicular edge networks has attracted widespread attention from academia and industry. Due to the generation of a large number of latencysensitive tasks from vehicles’ real-time sensing of road conditions, coupled with the rise of other computing-intensive vehicle applications, the current computing capabilities of the onboard devices cannot meet the diverse demands of vehicular users. Therefore, it is necessary to combine the computing resources around the vehicle to complete computing tasks. With the goal of maximizing the difference between gain and consumption, this paper studies the integrated sensing and computation offloading involving roadside units (RSUs) and vehicle platoon in vehicular edge networks. Specifically, we first consider that mobile vehicles can simultaneously offload computing tasks to RSU and vehicle platoon via non-orthogonal multiple access (NOMA) technology, and construct a multi-objective optimization problem with the goal of maximizing the utility of the three parties. Then, we construct a game model among ISAC vehicle, RSU, and vehicle platoon based on the Stackelberg game. By seeking the equilibrium of the game, the optimal offloading and pricing strategy are derived, while the utility of the three parties is maximized. Finally, the simulation results show that the proposed scheme is superior to other traditional schemes, and each party in the game obtains its optimal strategy. © 2014 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Remote Interference Source Localization: A Multi-UAV-Based Cooperative Framework

引用

Chinese Journal of Electronics 2022年第3期31卷 442-455页

作者： WU Guangyu GU Jiangchun Department of Computer Science and Technology University of Science and Technology of China School of Communication Engineering Army Engineering University of PLA

Interference source localization with high accuracy and time efficiency is of crucial importance for protecting spectrum resources. Due to the flexibility of unmanned aerial vehicles(UAVs), exploiting UAVs to locate the interference source has attracted intensive research interests. The off-the-shelf UAV-based interference source localization schemes locate the interference sources by employing the UAV to keep searching until it arrives at the target. This obviously degrades time efficiency of localization. To balance the accuracy and the efficiency of searching and localization, this paper proposes a multi-UAV-based cooperative framework alone with its detailed scheme, where search and remote localization are iteratively performed with a swarm of UAVs. For searching, a low-complexity Q-learning algorithm is proposed to decide the direction of flight in every time interval for each UAV. In the following remote localization phase, a fast Fourier transformation based location prediction algorithm is proposed to estimate the location of the interference source by fusing the searching result of different UAVs in different time intervals. Numerical results reveal that in the proposed scheme outperforms the stateof-the-art schemes, in terms of the accuracy, the robustness and time efficiency of localization.

关键词： unmanned aerial vehicles low-complexity Q-learning algorithm path planning fast Fourier transforms remote interference source localization multi-robot systems UAV swarm mobile robots remote localization location prediction algorithm aerospace robotics autonomous aerial vehicles learning (artificial intelligence) fast Fourier transformation cooperative communication spectrum resources radiofrequency interference mobile radio flight direction multiUAV-based cooperative framework

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Deep Learning QoS Prediction Model Based on Temporal Context and Feature Fusion

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1232-1244页

作者： Zhang, Peiyun Fan, Jiajun Chen, Yutong Huang, Wenjun Zhu, Haibin Zhao, Qinglin Nanjing University of Information Science & Technology Engineering Research Center of Digital Forensics of Ministry of Education School of Computer Science Nanjing210044 China Nipissing University Department of Computer Science and Mathematics North BayONP1B 8L7 Canada Macau University of Science and Technology School of Computer Science and Engineering Taipa999078 China

Existing end-to-end quality of service (QoS) prediction methods based on deep learning often use one-hot encodings as features, which are input into neural networks. It is difficult for the networks to learn the information that is conducive to prediction. Aiming at the above problem, an end-to-end deep learning QoS prediction model based on a temporal context and feature fusion is proposed. In the proposed model, three blocks are designed for QoS prediction. Firstly, a user-service encoding conversion block is designed to convert the one-hot encodings of users and services into the latent features of users and services, which can make full use of the data in sparse matrices. Then a time feature extraction block is designed to extract time features based on the time-varying characteristics of QoS values. Finally, the time features are fused with the latent features of users and services to predict QoS values. The experimental results show that on existing datasets, the proposed model has better prediction accuracy than other advanced methods in response time and throughput. © 2025 IEEE.

关键词： Prediction models

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：