检索结果-内蒙古大学图书馆

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Liu, Defang Wang, Zhibo Pang, Xiaoyi Sun, Yunan Hu, Jiahui Sun, Peng Hu, Yuke Wuhan University School of Cyber Science and Engineering China Zhejiang University School of Cyber Science and Technology China Hunan University College of Computer Science and Electronic Engineering China

ISBN: (纸本)9798350331240

Large models like transformer models cannot be directly applied and trained at the network edge since edge devices are heterogeneous and often equipped with limited resources. To collaboratively train a large model at the network edge, existing works assign sub-models of the large model with proper sizes to each edge device, and adopt advanced technologies like knowledge distillation to aggregate their local models to update the large model. However, these methods assign sub-models in a coarse-grained manner and require a certain amount of edge devices to train the large model locally, thus cannot achieve efficient edge learning for large models in practice. In this paper, to make the utmost of edge devices to collaboratively train a large model faster and better, we propose a novel synchronous edge learning framework to achieve efficient large model training across heterogeneous resource-limited edge devices. Specifically, to reduce the waiting time in the training process while ensuring that every edge device can afford the local training, we design a capability-aware local model customization mechanism to granularly tailor personalized model structures for each edge device based on their memory and computing capabilities to make them have similar local training times. Then, to efficiently integrate the local training achievements of heterogeneous edge devices, we propose a layer augmentation-based heterogeneous model aggregation mechanism to align local models and quickly and effectively get the global update for the global large model. Besides, we propose a monument distillation-based model deployment mechanism to deploy the updated global large model at edge devices without the loss of learned knowledge. In this way, each edge device can fully contribute to the global large model training, thus achieving efficient edge learning for the large model. Experimental results demonstrate that our framework has better performance in accuracy and efficiency than the sta

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Batch Authentication Protocol Based on Small Exponent Test for Internet of Vehicles 19

A Batch Authentication Protocol Based on Small Exponent Test...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhang, Ruirui Xu, Zisang Xu, Jianbo Computer and Communication Engineer Institute Changsha University of Science and Technology Changsha China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China

ISBN: (纸本)9798350346558

Intelligent Transportation System (ITS) is a road transportation system that uses advanced technologies such as the Internet of Things (IoT), big data, and artificial intelligence (AI) to realize dynamic real-time information interaction between people, vehicles and roads. As an indispensable part of the ITS, the Internet of Vehicles (IoV) has received extensive attention from many researchers. Since vehicles entering the range of RSU communication need to be authenticated. Therefore, in a high vehicle traffic flow environment, it is easily to form a computation or communication bottleneck at the RSU. To solve the above problems, some researchers have proposed many batch authentication protocols. However, on the one hand, Some proposed batch authentication protocols use computationally expensive bilinear pairing operations. On the other hand, some proposed protocols do not consider the existence of semi-trusted vehicle nodes. Therefore, this paper proposes a batch authentication protocol based on the small exponent test for IoV. In the protocol, the RSU will not send any authentication secret parameters to the proxy vehicle, thus eliminating the security risk of semi-trusted nodes leaking secret parameters. Meanwhile, the proposed protocol is based on the small exponent test method, which reduces the computation cost while ensuring security. Finally, the proposed protocol is proved to be secure by mathematical derivation, and the performance analysis results also show that the proposed protocol has lower communication cost. © 2022 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Feature Dual Supervision Model for the Searches of Online Advertising Audiences

引用

Scientific Programming 2023年第1期2023卷

作者： Ni, Haipeng Wang, Zhixi School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

Online advertising has become one of the most important strategies used by companies. They get the valuable results from Internet marketing and communication strategies. Therefore, it is necessary to study the click-through rate (CTR) model to search the potential audiences in online advertising. The advertisers desire to search for potential candidates through a large number of queries for audiences in programmatic advertising. Facing such a large corpus, the most common method is that using two-tower model to learn user's queries and ad representations, and then the similarity function is applied to match the feature representation to get the potential audiences related to the ad. However, in the process of feature extraction, there is a lack of information interaction between the two towers, resulting in the loss of details in the representation. In order to alleviate the lack of information interaction between the networks in the two-tower model during feature extraction. In this paper, we propose a novel model named Feature Dual Supervision Model (FDSM), which integrates by Feature Expression Unit (FEU) and Feature Supervision Unit (FSU). The FEU is used to extract ads or users features, and FSU generates a weight vector to supervise the working process of the FEU. In addition, we propose a feature cross-layer with bridge connections in FDSM to achieve effective feature interaction between ad and user representations. Finally, we conduct experiments on the Tencent Lookalike and MovieLens datasets. The experimental results indicate that the FDSM model outperforms other state-of-the-art CTR prediction models in audience expansion. © 2023 Haipeng Ni and Zhixi Wang.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Application Deployment in Mobile Edge Computing Environment Based on Microservice Chain 25

Application Deployment in Mobile Edge Computing Environment ...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Li, Haiyan Tang, Bing Xu, Wei Guo, Feiyan Zhang, Xiaoyuan Hunan University of Science and Technology School of Computer Science and Engineering Hunan Laboratory for Service Computing and Novel Software Technology Xiangtan411201 China

ISBN: (纸本)9781665405270

Mobile edge computing (MEC) has become an extremely hot topic in recent years. Mobile edge cloud relies on storage and computing resources on network edge to provide users with delay-sensitive services. However, the transmission delay among microservices and the load of the servers tend to increase due to improper service placement and unreasonable resource allocation under MEC. In this paper, an edge service placement strategy based on an improved fast non-domination sorted genetic algorithm is proposed. First, a microservice placement optimization model is built with the goal of minimizing the average transmission delay and the load balance degree. Then, a genetic algorithm-based microservice placement approach called GA-MSP using improved NSGA-II is studied under the premise that a single service instance is deployed only on one container. The experiments show that the proposed GA-MSP approach is able to achieve low delay and load balance effectively, and ultimately deploy services based on the resulting sets after convergence, which outperforms several other existing representative methods. © 2022 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

TGeoYOLO: Leveraging Multi-Scale Features and Enhanced Loss for Remote Sensing Detection

TGeoYOLO: Leveraging Multi-Scale Features and Enhanced Loss ...

引用

Edge Computing and Scalable Cloud (EdgeCom), IEEE International Conference on

作者： Wei Du Meiguo Ke Kai Jin Shu Tan Dacheng He Kuan-Ching Li College of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Lens Technology Co. Ltd. Xiangtan China

ISBN: (数字)9798350377132

ISBN: (纸本)9798350377149

As remote sensing technology advances, precise target detection using satellite imagery has become a critical area of research in military and industrial applications. Traditional target detection methods face unique challenges when processing remote sensing images, such as high resolution, complex backgrounds, and detection of small objects. In this paper, we propose TGeoYOLO, which is built upon modifications to the YOLOv8 model. First, we introduce a Multiscale Perceptive (MP) module. Second, we enhance the algorithm with an Enhanced Focal Loss (EFL) function to improve the accuracy and robustness of detecting small objects in remote sensing images. Specifically, the MP module effectively utilizes multiscale features to provide appropriate receptive fields for targets of various sizes. The EFL function optimizes for the localization errors and small object issues prevalent in remote sensing imagery. Experimental results demonstrate that TGeoYOLO performs exceptionally well on the NWPU and VisDrone datasets, achieving improvements of $1.3 \%$ and $1.6 \%$ in detection accuracy over the original YOLOv8 model.

关键词： Location awareness Accuracy Image resolution Image edge detection Object detection Robustness Satellite images

来源：评论

学校读者我要写书评

暂无评论

Intelligent ADHD Detection Using Explainable Multimodal Fusion Model 4

Intelligent ADHD Detection Using Explainable Multimodal Fusi...

引用

4th IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Tsai, Ho-Jung Wu, Hsiao-Kuang Chen, Chun-Chuan Yeh, Chen-Hsin Chu, Tzu-Yueh Yeh, Shih-Ching National Central University Department of Computer Science and Information Engineering Taiwan National Central University Department of Biomedical Sciences and Engineering Taiwan Hunan University College of Computer Science and Electrical Engineering China

ISBN: (纸本)9798350363586

Deep learning has been proved to diagnose Attention Deficit/Hyperactivity Disorder (ADHD) accurately, but it has raised concerns about trustworthiness because of the lack of explainability. Fortunately, the development of explainable artificial intelligence (XAI) offers a solution to this problem. In this study, we employed a VR-based GO/NOGO task with distractions, capturing participants' eye movement, head movement, and electroencephalography (EEG) data. We used the collected data to train an explainable multimodal fusion model. Besides classifying between ADHD and normal children, the proposed model also generates explanation heatmaps. The heatmaps provide the importance of specific variables and timestamps in the EEG data to help us analyze the patterns captured by the model. According to our observations, the model identified specific time intervals that related to specific event-related potentials (ERPs) components. The heatmaps also demonstrate that the impacts of distractions vary between not only the GO and NOGO events but also ADHD and normal children. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Recent Transformers in Image,Video and Diffusion Models

引用

computers, Materials & Continua 2024年第7期80卷 37-60页

作者： Dinh Phu Cuong Le Dong Wang Viet-Tuan Le College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China Faculty of Information Technology Yersin University of Da LatDa Lat66100Vietnam Faculty of Information Technology Ho Chi Minh City Open UniversityHo Chi Minh City722000Vietnam

Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks(CNNs).The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention *** study aims to provide a comprehensive survey of recent transformerbased approaches in image and video applications,as well as diffusion *** begin by discussing existing surveys of vision transformers and comparing them to this ***,we review the main components of a vanilla transformer network,including the self-attention mechanism,feed-forward network,position encoding,*** the main part of this survey,we review recent transformer-based models in three categories:Transformer for downstream tasks,Vision Transformer for Generation,and Vision Transformer for *** also provide a comprehensive overview of recent transformer models for video tasks and diffusion *** compare the performance of various hierarchical transformer networks for multiple tasks on popular benchmark ***,we explore some future research directions to further improve the field.

关键词： Transformer vision transformer self-attention hierarchical transformer diffusion models

来源：评论

学校读者我要写书评

暂无评论

Semi-closed synthesis of nitrogen and oxygen Co-doped mesoporous carbon for selective aqueous oxidation

引用

Green Energy & Environment 2022年第1期7卷 43-52页

作者： Chen Xing Daihui Yang Yan Zhang Tian Sun Junfei Duan Hussein A.Younus Shiguo Zhang College of Materials Science and Engineering Hunan Province Key Laboratory for Advanced Carbon Materials and Applied TechnologyHunan UniversityChangsha410082China School of Materials Science and Engineering Changsha University of Science and TechnologyChangsha410004China Chemistry Department Faculty of ScienceFayoum UniversityFayoum63514Egypt

Heteroatom-doped meso/micro-porous carbon materials are conventionally produced by harsh carbonization under an inert atmosphere involving specific precursors,hard/soft templates,and heteroatom-containing ***,we report a facile synthesis of N and O co-doped meso/micro-porous carbon(NOMC)by template-free carbonization of a small-molecule precursor in a semi-closed *** semi-closed carbonizaiton process yields hydrophilic NOMCs with large surface area in a high *** porous structure as well as the elemental composition of NOMCs can be modulated by changing the holding time at a particular *** as metal-free heterogeneous catalysts can selectively oxidize benzyl alcohol and its derivatives into aldehydes/ketones with>85%conversion in aqueous solution,which is much higher than that of the control sample obtained in tube furnace(21%conversion),mainly due to their high N content,high percentage of pyridinic N,and large surface *** presence of O-containing moieties also helps to improve the hydrophilicity and dispersion ability of catalysts and thus facilitates the mass transfer process during aqueous *** NOMC catalysts also dispayed excellent activity for a wide range of substrates with a selectivity of>99%.

关键词： Semi-closed carbonization Nitrogen and oxygen doping Mesoporous carbon Metal-free catalyst Selective aqueous oxidation

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Multi-Task Deep Learning for WiFi Fingerprint Database Construction in Building-Scale Localization

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Wang, Chun Luo, Juan Yin, Luxiu Li, Chuang Huang, Wenbin Liang, Wei Li, Kuan-Ching Hunan Normal University College of Information Science and Engineering China Hunan University College of Computer Science and Electronic Engineering China Hunan University of Science and Technology School of Computer Science and Engineering China Nanjing University of Information Science and technology School of Computer Science China

WiFi-based indoor positioning has emerged as a crucial technology for enabling smart consumer electronic applications, particularly in large-scale buildings. The construction of WiFi fingerprint databases using received signal strength (RSS) is foundational due to its widespread deployment. However, achieving high positioning accuracy typically requires labor-intensive and time-consuming site surveys. While recent crowdsourcing methods have facilitated the collection of numerous RSS samples, these samples frequently lack labels and reliability in multi-scale building *** this paper, we design a novel semi-supervised and multi-task mean-teacher model (MTMT-DNN) to annotate crowdsourcing unlabeled multi-scale fingerprint samples. This method enables the construction of a comprehensive fingerprint database without requiring intensive manual effort or compromising positioning accuracy. Our key idea is to first develop a multi-task Deep Neural Network (MT-DNN) for simultaneously annotating building, floor, and intra-floor coordinate labels by leveraging their complementary information. Then we employ the mean-teacher semi-supervised learning to leverage additional unlabeled fingerprint data for further improving the annotating performance and reducing intensive manual effort. Finally, we train the MTMT-DNN model by developing two multi-task loss functions and ensuring consistency between them, thereby enhancing the reliability of the annotated crowdsourced fingerprints. We conducted real-world experiments in a 20,000 m2 site encompassing three multi-story buildings. The results demonstrate that our proposed method significantly reduces the workload of manually collecting labeled fingerprint samples. With only 20% of labeled fingerprints collected, we achieve 99% average annotation accuracy for building and floor labels and an average coordinates annotation error within 4 m. © 1975-2011 IEEE.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

High-Precision Intelligent Dynamic Scheduling Algorithm and Application During Service of Wind Turbine Group 18th

High-Precision Intelligent Dynamic Scheduling Algorithm and ...

引用

18th Annual Conference of China Electrotechnical Society, ACCES 2023

作者： Zhao, Qiaohong Zhou, Zhou Song, Xiaoping Zhang, Jingjing Zhou, Wuxi Liu, Qiao Liu, Jie Zhan, Jun Hebei Vocational College of Rail Transportation Shijiazhuang050000 China Hunan Institute of Engineering Xiangtan411104 China Harbin Electric Corporation Wind Power Co. Ltd Xiangtan411102 China College of Computer Science National University of Defense Technology Changsha410000 China

ISBN: (纸本)9789819714193

The problem of low control accuracy is common in the new energy power system, especially with the increase of the installed capacity of wind turbines and the increase in the number of controlled wind turbines, the higher requirements for the whole field control strategy, the more obvious the problem of low control accuracy. In response to the above problems,, after analyzing the two fundamental reasons for the large control error of wind turbine group, Firstly, this paper optimizes the closed-loop control of the entire wind farm by using the improved PID (Proportion Integration Differentiation) controller, and eliminates the error caused by line loss. Secondly, aiming at the problem of large error caused by obvious oscillation in the small power section in the wind turbine group control process, the sliding step theory is proposed, and in the process of small power section control, the wind turbines with the least amount of intelligent allocation participates in the control, thereby reducing the oscillation and error, and finally, the actual open-loop and closed-loop control data of multiple wind turbine group are analyzed. The actual field results show that after using the algorithm in this paper, the whole field control accuracy of the wind turbine group can reach within 1%, which effectively solves the problem of low control accuracy of the whole field of the large-capacity wind turbine group, The frequency stability of wind farm grid connection has been improved step-by-step. © Beijing Paike Culture Commu. Co., Ltd. 2024.

关键词： Controllers

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：