检索结果-内蒙古大学图书馆

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Fan, Yunlong Yang, Zhiheng Li, Baixuan Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9789819601219

Transformers have significantly improved Neural Machine Translation (NMT) models, accompanied by the inherent space complexity of O(n2). While recent approaches aim to be parameter-efficient, they often exhibit limited generalization capabilities with fewer parameters and decreased performances in longer sentences. To this end, we propose two methods, Syntax-enhanced Contrastive Learning (Syn-CL) and JS divergence-based Regularized Dropout (JSR-Drop) for the cross-layer parameter-sharing Transformer (baseline) in NMT. In Syn-CL, we add the corresponding target-to-source instances for the same batch in an extra bidirectional training phase, and minimize the distances of syntax-enhanced representation between the bilingual sentence-pair while maximizing the ones among others. In JSR-Drop, we refine the regularized dropout strategy with JS divergence, and improve generalization capabilities by reducing Transformers’ inconsistencies between training and inference introduced by dropout. Extensive experiments on six NMT tasks, IWSLT2014 (German↔English) and IWSLT2017 (English↔French and English↔Romanian), show an average BLEU score of 37.55, surpassing the vanilla Transformer and the baseline up to 1.75 BLEU, and outperforming models with 1.5×, 2.0× parameters in translating long sentences. Our code is available at https://***/Anon1214/EnPeNMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Associative Task Computation Offloading for Industrial Internet of Things 16

Associative Task Computation Offloading for Industrial Inter...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Jiang, Fan Zhang, Hang Liu, Lei Wang, Chaowei Xian University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Xi'an China Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9798350390643

In this paper, we propose a computational offloading strategy tailored for multiple industrial equipment (IE) within an Industrial Internet of Things (IIoT) framework. Our primary focus is on addressing the computational offloading problem, specifically by modeling the associative relationship between tasks as a Directed Acyclic Graph (DAG). Initially, we transform the DAG task offloading problem into a Markov decision process (MDP). Subsequently, to derive the optimal offloading decision, we propose a novel approach termed DAG Task offloading with Message Passing Neural network (MPNN) and Double Deep Q-network (DAGTO-MAD). The proposed algorithm aims to min-imize the completion time of the task set. Moreover, we enhance the performance of the MPNN by adapting it to extract structural information from the DAG more efficiently. Simulation results demonstrate that our proposed algorithm achieves a shorter completion time compared to existing offloading algorithms across various environments. Additionally, our algorithm exhibits robust convergence and versatility, highlighting its effectiveness in real-application scenarios. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ding, Lichao Zhao, Jing Lu, Kai Hao, Zenghao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Secrecy Communications for Wireless-Powered Full-Duplex Cooperative NOMA Systems: A User Selection and Friendly Jamming Approach

Secrecy Communications for Wireless-Powered Full-Duplex Coop...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023

作者： Ren, Yuan Ren, Jing Zhang, Xuewei Lu, Guangyue Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security School of Communications and Information Engineering Xi'an710121 China

ISBN: (纸本)9798350345407

This paper studies the secure communications of a wireless-powered full-duplex cooperative non-orthogonal multiple access (CoNOMA) system with a source node, a group of near users, a far user and an external eavesdropper. In particular, the eavesdropper intends to wiretap the transmitted signals from the source. Two of the near users are picked up, served as a wireless-powered relay and a wireless friendly jammer, respectively. We propose a user selection and cooperative jamming based secure transmission scheme. Specifically, the source transmits a superimposed signal to the selected near user. The selected near user, who is employed as a relay, can harvest energy from the radio frequency signals and decode the information simultaneously. The harvested energy are then utilized to forward the signal to the far user. The jammer also collects energy from the source, and emits artificial noise by using the harvested energy to confuse the eavesdropper. Based on the proposed scheme, the closed-form expression for secrecy outage probability (SOP) and effective secrecy throughput (EST) are derived. The correctness of our theoretical analysis is verified by Monte-Carlo simulations, and the superiority of the proposed scheme in improving the system secure performance is also validated. © 2023 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Access Control Model for E-Medical Systems 2

Privacy-Preserving Access Control Model for E-Medical System...

引用

2nd International Conference on Big Data and Privacy Computing, BDPC 2024

作者： Cai, Rongsheng Chen, Lanxiang Zhu, Yizhao City University of Macau Faculty of Data Science 999078 China College of Computer and Cyber Security Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou China

ISBN: (纸本)9798350307597

With the high speed development of information technology, the healthcare system increasingly relies on cloud servers for data storage and complex computation, patient data privacy issues stem from healthcare systems' vulnerability to breaches, despite data encryption emphasis, insufficient focus on preventing unauthorized access risks compromises patient information confidentiality. Consequently, the need to protect privacy within the healthcare system has gained significant attentions. However, existing research primarily concentrates on data encryption processes, but there is comparatively less attention given to addressing potential privacy leaks concerning data visitors. In this paper, we propose a privacy-preserving access control model for healthcare cloud data visitors. Our model combines the RBAC (Role-Based Access Control) model with the PSI (Private Set Intersection) technique to ensure the privacy and security of data visitors. The performance analysis of our proposed solution demonstrates its relative efficiency and practicality when applied to E-medical systems. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning of Rechargeable UAVs for AoS Minimization in IoT networks 16

Trajectory Planning of Rechargeable UAVs for AoS Minimizatio...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Liu, Yunchao Lin, Suling Gong, Jie School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9798350390643

Freshness of information is a critical issue for real-time Internet of Things (IoT) applications. Unmanned aerial vehicles (UAVs), due to their high flexibility and low cost, are widely deployed in time-sensitive IoT scenarios. In this article, we explore the trajectory planning problem in rechargeable-UAV-aided IoT networks. To accurately measure the freshness of information, we introduce Age of information (AoI) and Age of Synchronization (AoS). AoI is utilized to plan the UAVs' trajectories for accessing sensors (SNs) and reduce the average AoS of the system. UAVs can recharge at charging stations to maintain energy above a certain threshold. We formulate a Markov decision process with the objective of minimizing the average AoS under the energy constraint. To adjust the dynamic environment, we propose a multi-agent deep reinforcement learning method to jointly optimize the UAVs' flight trajectories and battery recharging. Simulation results demonstrate that the proposed algorithm can significantly reduce the total average AoS under the energy constraint. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multi-Party Machine Learning Based on Trusted Execution Environment and GPU Accelerator 12

Privacy-Preserving Multi-Party Machine Learning Based on Tru...

引用

12th IEEE International Conference on information and Communication networks, ICICN 2024

作者： Tian, Haibo Ren, Shuangyin Chen, Chao School of Computer Science and Engineering Sun Yat-Sen University Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9798350355802

In multi-party machine learning scenarios involving sensitive data, safeguarding user and model privacy holds utmost importance. Current approaches often disclose model parameters to expedite training, but this poses significant privacy concerns. This paper introduces MOML (Matrix Outsourcing for multi-party Machine Learning), a framework for multi-party learning that relies on outsourced matrix multiplication. MOML harnesses the power of both TEE (Trusted execution environment) and GPU (Graphics Processing Unit), effectively offloading inefficient matrix operations from TEE to GPU, thereby enhancing training efficiency without compromising privacy. At the heart of MOML lies an enhanced matrix multiplication outsourcing algorithm, tailored for GPU computing and integrity checks. Rigorous tests conducted on the MNIST and CIFAR-10 datasets reveal remarkable performance improvements with MOML. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algorithm 12

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algori...

引用

12th International Conference on Advanced Cloud and Big Data, CBD 2024

作者： Ding, Yi Guo, Naixuan Meng, Haitao School of Information Engineering Yancheng Institute of Technology Yancheng China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration China

ISBN: (纸本)9798331511074

Gesture recognition has been widely used in many situations, such as human-computer interaction, virtual reality and smart home. To meet the current demands for accuracy and speed in gesture recognition, this paper proposes an improved algorithm based on YOLOv8, referred to as YOLOv8-GR. By replacing the original YOLOv8 detection head with a Dynamic Head, we integrate scale-aware, spatial-aware, and task-aware attention mechanisms within a unified framework. To enhance context information capture, the SPPF (Spatial Pyramid Pooling - Fast) module is optimized to a modified SPPF-LSKA (Large Separable Kernel Attention) module. In addition, we employ the EIoU loss function for more accurate evaluation of object detection results. To evaluate our algorithm, we integrate a gesture dataset in complex and diverse scenarios through network and field shooting annotations. Compared to the original YOLOv8, the proposed YOLOv8-GR achieves a 22.5% improvement in mAP50 and a 10.0% improvement in mAP50-95 on our dataset. We also compare YOLOv8-GR with the MobileNetv2-based SSD, which is a kind of one-stage object detection algorithm. While maintaining similar recognition accuracy, the computational cost of YOLOv8-GR is 9.9 GFLOPs, which is 15.8% of SSD, and our algorithm can be deployed on Raspberry Pi 4B. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

m2Vib: 2D Vibration Measurement Using a Single mmWave Radar 30

m2Vib: 2D Vibration Measurement Using a Single mmWave Radar

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Wang, Haolin Xu, Wei Li, Zezhao Yang, Yanni Huang, Zhijian Shandong University School of Computer Science and Technology Qingdao China National Key Laboratory of Science and Technology on Information System Security China

ISBN: (纸本)9798331515966

Two-dimensional vibration measurement is essential for monitoring structure and machine health, especially providing more information than those 1D solutions. However, most existing 2D vibration monitoring methods require multi-dimension sensors, which can be costly for large-scale deployment. In this paper, we propose m^2 Vib, the first work that can realize accurate 2D vibration measurement using a single mmWave radar. Our system is achieved by creating a virtual radar with non-line-of-sight (NLoS) signals from a nearby reflector (e.g., wall) to offer the 2nd-dimension vibration observations. We further establish a geometric model to unveil the relationship between 2D vibration displacement and mmWave signal. Such an idea still encounters challenges from significantly attenuated NLoS signals and low-resolution geometric parameters from the commercial mmWave radar. Thus, we design a new retroreflector to enhance NLoS signals and advanced signal processing methods to obtain fine-grained geometric parameters. Extensive experimental results show that we can achieve sub-mm level 2D vibration measurement with an average vibration displacement error of 62.2 um and frequency error of 0.01 Hz in the X-axis and Y-axis. © 2024 IEEE.

关键词： Vibration measurement

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalability for efficiently processing this huge amount of data.

关键词： Learning systems

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：