检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Yanyue Lai, Yilong Wang, Zhenglin Li, Pengfei Zhou, Deyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King's College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9782493814104

As in the existing opinion summary data set, more than 70% are positive texts, the current opinion summarization approaches are reluctant to generate the negative opinion summary given the input of negative opinions. To address such sentiment bias, two approaches are proposed through two perspectives: model-specific and model-agnostic. For the model-specific approach, a variational autoencoder is proposed to disentangle the input representation into sentiment-relevant and sentiment-irrelevant components through adversarial loss. Therefore, the sentiment information in the input is kept and employed for the following decoding which avoids interference of content information with emotional signals. To further avoid relying on some specific opinion summarization frameworks, a model-agnostic approach based on counterfactual data augmentation is proposed. A dataset with a more balanced emotional polarity distribution is constructed using a large pre-trained language model based on some pairwise and mini-edited principles. Experimental results show that the sentiment consistency of the generated summaries is significantly improved using the proposed approaches, while their semantics quality is unaffected. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Impact of Different network Parameters on Federated Learning Performance in Vehicular networks

Impact of Different Network Parameters on Federated Learning...

引用

Radio Frequency and Antenna Technologies (iWRF&AT), IEEE International Workshop on

作者： Tuliga Busqin Celimuge Wu Yangfei Lin Zhaoyang Du Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350384765

ISBN: (纸本)9798350384772

This paper presents an in-depth examination of Federated Learning (FL) effectiveness in Vehicular Ad-Hoc networks (VANETs) through systematic experimentation of road simulations. The paper methodically investigates the influence of various factors, such as communication range, client selection, vehicle density, and speed on FL performance within VANET systems. The findings emphasize that an increased communication range not only reduces communication overhead but also greatly enhances FL performance. Moreover, strategic client selection and optimal vehicular densities emerge as critical determinants for ensuring high-quality data and system efficiency. Remarkably, variations in vehicle speed are shown to have a minimal impact on FL performance, suggesting that vehicular speed has relatively limited effects on communication - efficiency. This paper offers a detailed understanding of the factors that affect FL performance in VANET systems, providing practical recommendations to optimize vehicular network systems.

关键词： Knowledge engineering Analytical models Systematics Federated learning Roads Vehicular ad hoc networks Transportation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security and Flexibility in Smart Locker Systems: A Multi-Authentication Approach with IoT Integration

Enhancing Security and Flexibility in Smart Locker Systems: ...

引用

Learning and Technology Conference (L&T)

作者： Mohammed Balfaqih Department of Computer and Network Engineering University of Jeddah Jeddah Saudi Arabia

The past decade has witnessed the widespread integration of the Internet of Things (IoT) in the evolution of smart locker systems. However, many existing systems rely on a single authentication method, limiting their adaptability. These systems fail to account for potential unavailability of the chosen authentication method due to issues such as lost access cards, damaged cameras, or malfunctioning devices. Furthermore, the vulnerability of relying on a single authentication method, without considering dual-authentication approaches, poses a security risk, as unauthorized access could occur through eavesdropping or code interception. This paper addresses these shortcomings by introducing a smart locker system that incorporates multiple authentication methods, including dual authentication (utilizing both phone number and One Time Password (OTP)), fingerprint recognition, face recognition, and emergency code. Leveraging IoT technology, the system offers a range of authorization methods to grant access permission. The dual authentication method serves as the foundational security layer, significantly enhancing the locker’s overall security. The system is developed, implemented, and rigorously evaluated under various scenarios. The outcomes demonstrate superior performance compared to existing systems, particularly in terms of accuracy and flexibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Directed Spanning Trees for Enhanced Tolerance to Multiple Link Failures in SDN

Optimizing Directed Spanning Trees for Enhanced Tolerance to...

引用

OptoElectronics and Communications Conference, OECC

作者： Hieu Tran The Nattapong Kitsuwan Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan

This paper utilizes integer linear programming to construct directed spanning trees for optimal network resilience to multiple link failures. By minimizing the number of trees, it significantly reduces the required fl... 详细信息

ISBN: (数字)9798350308396

ISBN: (纸本)9798350308402

关键词： Costs network topology Process control Integer linear programming Control systems Robustness Hardware Topology Complexity theory Resilience

来源：评论

学校读者我要写书评

暂无评论

Rapid Autonomy Transfer in Reinforcement Learning with a Single Pre- Trained Critic 36

Rapid Autonomy Transfer in Reinforcement Learning with a Sin...

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Karim, Muhammad Faraz Deng, Yunjie Niu, Luyao Ramasubramanian, Bhaskar Alexiou, Michail Sahabandu, Dinuka Poovendran, Radha Mertoguno, Sukarno Georgia Institute of Technology AtlantaGA United States University of Washington Network Security Lab Department of Electrical and Computer Engineering SeattleWA United States Western Washington University Electrical and Computer Engineering BellinghamWA United States Kennesaw State University MariettaGA United States

ISBN: (纸本)9798331527235

Reinforcement learning (RL) is a well-studied framework to solve complex decision-making problems in unknown environments. The actor-critic model in RL facilitates autonomy transfer by allowing agents to iteratively update their policies using ongoing dynamic evaluations of value functions via a critic. In this paper, we examine the impact of using different pretrained critics on the performance of actor-critic algorithms. First, in any single given environment, we show that a pretrained critic can be effective in reducing the duration of an initial training phase, thereby accelerating convergence by a factor of up to 2×. In this setting, we identify the critical range of the number of episodes for which a critic will need to be trained in order for it to be an effective pretrained critic. Second, we show that a critic trained in one environment enables transfer of autonomy by aiding learning of behaviors in a different, yet related environment. We carry out extensive experiments on a bipedal locomotion task in the MuJoCo physics engine to verify our hypotheses. Our results in this paper mark the first step towards demonstrating the role and impact of pretrained critics to achieve rapid autonomy transfer for complex reinforcement learning tasks while minimizing costs associated with retraining in new environments. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Miniature Automatic Driving Vehicle Controlled by Camera Image Processing

Design of Miniature Automatic Driving Vehicle Controlled by ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Akira Kojima Department of Computer and Network Engineering Hiroshima City University Hiroshima Japan

We are developing a miniature self-driving car for the design contest at ICCE2024, which will be driven automatically by image processing of camera images. Our implementation uses a AMD/Xilinx SoC FPGA as the central controller. The hardware of the programmable logic part of the SoC FPGA is used for object detection in the camera image and PWM control of the motors. Other processes are software-controlled by the processor of the SoC FPGA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LQ-GNN: a Graph Neural network Model for Response Time Prediction of Microservice-based Applications in the Computing Continuum

引用

IEEE Transactions on Parallel and Distributed Systems 2025年

作者： Richart, Matias Gorricho, Juan-Luis Baliosian, Javier Contreras, Luis M. Muniz, Alejandro Serrat, Joan University of the Republic Computer Science Department School of Engineering Uruguay Polytechnic University of Catalonia Department of Network Engineering Barcelona Spain Telefonica CTIO Madrid Spain

To address the challenges posed by the deployment of microservices of future end-user applications in the cloud continuum, a performance prediction model working together with a network elasticity controller will be needed. With that aim, this work introduces Layered Queuing-Graph Neural networks (LQ-GNN), a novel Machine Learning (ML) approach to develop a generalized performance prediction model for microservice-based applications. Unlike previous works focused on individual applications, our proposal aims for a versatile model applicable to any microservice-based application, integrating the Layered Queueing network (LQN) modeling with Graph Neural networks (GNN). LQ-GNN allows to efficiently estimate the response time of applications under different resource allocations and placements on the computing continuum. The obtained evaluation results indicate that the proposed model achieves a prediction error below 10% when considering different evaluation scenarios. Compared to existing methodologies, our approach balances prediction accuracy and computational efficiency, making it viable for real-time deployments. Consequently, ML-based performance prediction can significantly enhance the resource management and elasticity control of microservice-based architectures, leading to more resilient and efficient systems. © 1990-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-Attribute Conditional Handover in LEO Satellite networks

Performance Evaluation of Multi-Attribute Conditional Handov...

引用

2023 VTS Asia Pacific Wireless Communications Symposium, APWCS 2023

作者： Lee, Won-Jae Lee, Jongtae Kim, Jae-Hyun Ajou University Department of Artificial Intelligence Convergence Network Suwon16499 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

ISBN: (纸本)9798350316803

Recently, low earth orbit (LEO) satellite has been attracting attention for communication. It supports higher link quality and reduces propagation delay compared with geostationary orbit (GEO) satellite. However, a single LEO satellite can not support continuous service due to small coverage and fast velocity. Therefore, LEO satellite constellation is needed. Handover (HO) scheme is important to support continuous service. However, the HO scheme is made for terrestrial network (TN). It is hard to apply HO scheme to Non-TN (NTN). We propose multi-attribute HO scheme for the NTN. The proposed HO scheme considers signal strength and time-of-stay (ToS). Simulation results show that the HO scheme based on multi-attribute is adjusted in NTN. © 2023 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Location-based Conditional Handover Scheme using LEO Satellites 14

Performance Evaluation of Location-based Conditional Handove...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Lee, Jongtae Lee, Wonjae Kim, Jae-Hyun Ajou University Department of Artificial Intelligence Convergence Network Suwon16499 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

ISBN: (纸本)9798350313277

The high velocity of LEO satellites can result in frequent handover (HO) in non-terrestrial networks (NTN). In a satellite environment, due to the high altitude, the signal strength variation between the cell center and the cell edge is very small. As a result, when using the signal strength-based HO, there are challenges in selecting an appropriate cell during HO. To address this issue, we proposed a location-based conditional HO (CHO) approach instead of the signal strength-based method. This approach uses the distance between the reference location of the cell and the user equipment (UE) to make HO decisions. This allows the UE to choose a suitable cell. Additionally, through an analysis based on the variation of signal strength with the UE's position within the cell and the distance change between the UE and the cell center, the distance offset is determined. Simulation results demonstrate that the proposed approach, when compared to the conventional method, can reduce radio link failure (RLF) and HO failure (HOF). © 2023 IEEE.

关键词： handover LEO satellites mobility non-terrestrial networks

来源：评论

学校读者我要写书评

暂无评论

DataJudge: Cross-Chain Data Consistency Verification Based on Extended Merkle Hash Tree 24th

DataJudge: Cross-Chain Data Consistency Verification Based o...

引用

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

作者： Xu, Yuwei Zeng, Junyu Cao, Jie Dai, Shengjiang Xiang, Qiao Cheng, Guang School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Nanjing China Department of Electrical and Computer Engineering Queen’s University Kingston Canada School of Informatics Xiamen University Xiamen China

ISBN: (纸本)9789819615414

Consortium blockchains, with their decentralized characteristics, have found widespread applications across various industries. However, this also forms isolated data islands. These data islands have become obstacles to data sharing between industries, and the issue of cross-chain data consistency verification remains unresolved. Current mainstream cross-chain technologies solve asset transfer issues through complex transaction steps, thus failing to meet the need for efficient data transmission. Existing research has proposed solutions for cross-chain data consistency verification, but two major issues remain. Firstly, these schemes do not consider data changes or support data dynamic operations. Secondly, these schemes involve a significant amount of complex computations, leading to slow efficiency. To address the above issues, we propose DataJudge, a cross-chain data consistency verification scheme based on an extended Merkle hash tree. This scheme not only verifies cross-chain data consistency but also effectively fills the gap in existing schemes regarding dynamic operations. Additionally, we modify the paillier homomorphic encryption. To improve efficiency, we do not introduce many complex computations. Furthermore, the extended Merkle hash tree structure enhances efficiency. Finally, we implement a prototype system and evaluate it. The results demonstrate that DataJudge can effectively verify cross-chain data consistency and outperform existing schemes such as DCIV and BeDCV. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data consistency

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：