检索结果-内蒙古大学图书馆

Neural Machine Translation by Fusing Key information of Text

computers, Materials & Continua 2023年第2期74卷 2803-2815页

作者： Shijie Hu Xiaoyu Li Jiayu Bai Hang Lei Weizhong Qian Sunqiang Hu Cong Zhang Akpatsa Samuel Kofi Qian Qiu Yong Zhou Shan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Science and Technology on Altitude Simulation Laboratory Sichuan Gas Turbine Establishment Aero Engine Corporation of ChinaMianyang621000China School of Power and Energy Northwestern Polytechnical UniversityXi’an710072China School of Computer Science Southwest Petroleum UniversityChengdu610500China Department of Chemistry Physics and Atmospheric SciencesJackson State UniversityJacksonMS 39217USA

When the Transformer proposed by Google in 2017,it was first used for machine translation tasks and achieved the state of the art at that *** the current neural machine translation model can generate high quality translation results,there are still mistranslations and omissions in the translation of key information of long *** the other hand,the most important part in traditional translation tasks is the translation of key *** the translation results,as long as the key information is translated accurately and completely,even if other parts of the results are translated incorrect,the final translation results’quality can still be *** order to solve the problem of mistranslation and missed translation effectively,and improve the accuracy and completeness of long sentence translation in machine translation,this paper proposes a key information fused neural machine translation model based on *** model proposed in this paper extracts the keywords of the source language text separately as the input of the *** the same encoding as the source language text,it is fused with the output of the source language text encoded by the encoder,then the key information is processed and input into the *** incorporating keyword information from the source language sentence,the model’s performance in the task of translating long sentences is very *** order to verify the effectiveness of the method of fusion of key information proposed in this paper,a series of experiments were carried out on the verification *** experimental results show that the Bilingual Evaluation Understudy(BLEU)score of the model proposed in this paper on theWorkshop on Machine Translation(WMT)2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test *** experimental results show the advantages of the model proposed in this paper.

关键词： Key information transformer fusion neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection

arXiv

引用

arXiv 2025年

作者： Wang, Zengran Zhang, Yanan Chen, Jiaxin Huang, Di State Key Laboratory of Complex and Critical Software Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China

To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution. However, traditional active learning approaches solely rely on a small amount of labeled data to train an initial model for data selection, overlooking the potential of leveraging the abundance of unlabeled data. Recently, attempts to integrate semi-supervised learning (SSL) into AL with the goal of leveraging unlabeled data have faced challenges in effectively resolving the conflict between the two paradigms, resulting in less satisfactory performance. To tackle this conflict, we propose a Synergistic Semi-Supervised Active Learning framework, dubbed as S-SSAL. Specifically, from the perspective of SSL, we propose a Collaborative PseudoScene Pre-training (CPSP) method that effectively learns from unlabeled data without introducing adverse effects. From the perspective of AL, we design a Collaborative Active Learning (CAL) method, which complements the uncertainty and diversity methods by model cascading. This allows us to fully exploit the potential of the CPSP pre-trained model. Extensive experiments conducted on KITTI and Waymo demonstrate the effectiveness of our S-SSAL framework. Notably, on the KITTI dataset, utilizing only 2% labeled data, S-SSAL can achieve performance comparable to models trained on the full dataset. The code has been released at https://***/LandDreamer/S SSAL. Copyright © 2025, The Authors. All rights reserved.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

DapperFL: domain adaptive federated learning with model fusion pruning for edge devices 24

DapperFL: domain adaptive federated learning with model fusi...

引用

Proceedings of the 38th International Conference on Neural information Processing systems

作者： Yongzhe Jia Xuyun Zhang Hongsheng Hu Kim-Kwang Raymond Choo Lianyong Qi Xiaolong Xu Amin Beheshti Wanchun Dou State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computing Macquarie University Australia School of Information and Physical Sciences University of Newcastle Australia Department of Information Systems and Cyber Security University of Texas at San Antonio USA College of Computer Science and Technology China University of Petroleum (East China) China School of Computer and Software Nanjing University of Information Science and Technology China

ISBN: (纸本)9798331314385

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://***/jyzgh/DapperFL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human-UAV Collaborative Task Scheduling for 360° Video Generating in Intelligent Transportation 8

Human-UAV Collaborative Task Scheduling for 360° Video Gene...

引用

8th International Conference on Virtual Reality, ICVR 2022

作者： Yuan, Zhiwei Tang, Hong Wang, Pengfei Yan, Zhaohong Zhou, Dongsheng Zhang, Qiang Wei, Xiaopeng School of Computer Science and Technology Dalian University of Technology Dalian116024 China Science and Technology on Electronic Information Control Laboratory Chengdu610036 China School of Software Engineering Dalian University Dalian116622 China

ISBN: (数字)9781665479110

ISBN: (纸本)9781665479110

With the rapid development of virtual reality technology, 360° video has been widely adopted in intelligent transportation, e.g., traffic monitoring, virtual driving, etc. Therefore, it is necessary to recruit workers and unmanned aerial vehicles (UAVs) to complete the task of video recording. However, we can not guarantee the quality of video recording by only employing workers or UAVs alone. Due to the real-Time nature of traffic, task scheduling for 360 video generating is a major challenge in intelligent transportation. In this paper, we propose a human-UAV collaborative 360° video recording task scheduling framework from the perspective of crowdsensing. We build a point of interest (POI) model according to the characteristics of urban intelligent transportation to determine the locations of the video recording tasks and the number of camera stands. We introduce the relay UAV as the video streaming data transmission node to ensure the quality of video transmission and design the route planning algorithm of the relay UAV to guide the route planning of the camera UAV to ensure recording task synchronization. Meanwhile, workers are introduced into the route planning algorithm of camera UAVs to compete for tasks. The simulation experiments of the urban environment show that our proposed framework outperforms worker-mode and UAV-mode under the same environmental settings. © 2022 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Improving VGG-Style Convnet for JPEG Steganalysis

Improving VGG-Style Convnet for JPEG Steganalysis

引用

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

作者： Zhuofan Yang Qiushi Li Shenghai Luo Shunquan Tan Bin Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Shenzhen Key Laboratory of Media Security Shenzhen University China

The steganalysis of JPEG images is a crucial area of research. Deep-learning based steganalysis methods have achieved superior detection performance. All methods for JPEG steganalysis rely on residual networks. Although the incorporation of residual connections has enhanced detection performance, it has also led to a notable increase in computational complexity. Furthermore, most of these methods are not complete end-to-end models. In their approaches, traditional hand-crafted filters are employed for image preprocessing. To avoid relying on residual connections and prior knowledge, we propose an end-to-end VGG-style ConvNet. During training, the model utilizes a multi-branch architecture, while it is transformed into a VGG-style ConvNet through structural reparameterization during inference. We conduct extensive experiments on ALASKA KAGGLE dataset and ALASKA II dataset, demonstrating that the proposed method achieves state-of-the-art results in the JPEG domain comparable to other CNN-based steganalyzers such as UCNet and EfficientNet, with clearly better convergence capacity and lower model complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Based ROI Enhancement Approaches for Palmprint Recognition

Super-Resolution Based ROI Enhancement Approaches for Palmpr...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Hüseyin Furkan Macan Özkan Bіngöl Salih Türk Murat Ekіncі Department of Management Information Systems Gumushane University Gümüşhane Turkey Department of Software Engineering Gumushane University Gümüşhane Turkey Department of Computer Engineering Karadeniz Technical University Trabzon Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

The sizes of regions of interest (ROI) obtained from images captured by cameras in palmprint recognition may vary depending on the camera specifications and the position of the hand. The regions of interest that recognition systems can use are typically rescaled through interpolation techniques and then defined as inputs to the system. In such cases, there may be some loss of biometric data. This study aims to enhance the quality of the palmprint ROI images, which are critical for palmprint recognition systems. To achieve this, various super-resolution techniques were employed to reconstruct low-resolution ROI images to the target sizes while preserving the distinctiveness of their biometric features. This approach is designed to optimize recognition accuracy and improve data reliability in palmprint recognition processes.

关键词： Interpolation Image recognition Accuracy Palmprint recognition Superresolution Cameras Reliability engineering Data processing Artificial intelligence Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

SMART: Serverless Module Analysis and Recognition Technique for Managed Applications

SMART: Serverless Module Analysis and Recognition Technique ...

引用

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Adi Ashkenazi Edita Grolman Aviad Elyashar Dudu Mimran Oleg Brodt Yuval Elovici Asaf Shabtai Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Israel Cyber Labs@BGU Ben-Gurion University of the Negev Israel Department of Computer Science Shamoon College of Engineering Beer-Sheva Israel

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

Serverless Function-as-a-Service (FaaS) environments enable developers to build and run cloud applications without the need to manage the underlying servers and computing infrastructure, allowing them to focus on implementing the application logic. Such environments contain numerous functions and dynamic resources, e.g., APIs and databases, making it challenging to gain insight and context of internal events i.e., recognize modules. Module in a serverless application is a set of functions and resources, that represents a functional unit that shares logical context. This paper presents SMART, a method for automatic analysis and recognition of modules for managed serverless applications. The proposed method creates an event-based graph by analyzing the standard serverless logs that document events involving the application’s functions and resources and utilizes well-known community detection algorithms (such as Louvain), with graph centrality metrics (such as degree centrality) to recognize the modules. SMART enables high-level visibility of the application’s structure and logical context which can facilitate security analysis and contribute to improved decision-making of incident response handlers, who typically do not have direct access to the application’s design and code, which can lead to challenges in fully understanding the system’s intricacies. We focused on the popular Amazon Web Services (AWS) Lambda serverless computing platform and evaluated the proposed method on three different demo applications (Airline Booking, VOD, and E-commerce). We compared SMART’s performance to four overlapping community detection algorithms and showed that it outperformed them in the task of module recognition, with a maximum improvement of 61% on the omega index metric compared to the Speaker-Listener Label Propagation algorithm. In addition, we demonstrate that the use of large language models (LLMs) with the knowledge gained by SMART can enrich security analysis insights.

关键词： Measurement Web services Serverless computing computer architecture Security Indexes Electronic commerce Detection algorithms Standards Airline industry

来源：评论

学校读者我要写书评

暂无评论

Business Scenario Driven Reinforcement Learning Testing Method

Business Scenario Driven Reinforcement Learning Testing Meth...

引用

software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter), ACIS International Winter Conference on

作者： Lizhi Cai Jin Wang Shanghai Key Laboratory of Computer Software Testing and Evaluating School of Information Science and Engineering East China University of Science and Technology Shanghai China

Reinforcement learning has been successfully applied in software testing, but the existing testing methods cannot perform effective testing according to the characteristics of applications, and using outdated interactive experience during training, resulting in inefficient testing. In this paper, we propose BSDRTesting. Firstly, the demonstration experience of human users is collected according to the functional scenarios and business logic of each application, and combining reinforcement learning and imitation learning to maximize rewards while imitating user behavior, experience replay aims to sample experiences from the agent's self-exploration and expert demonstrations to improve sampling efficiency. At the same time, according to the input rules, the black-box testing method is used to fully test the input events, and finally an experience filtering mechanism is proposed, and the reward value and TD-Error are used as the basis for priority sampling. The experimental results on 10 open source applications show BSDRTesting has achieved significant improvements in code coverage and branch coverage compared with existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Communication-efficient and Decentralized Federated Minimax Optimization

Communication-efficient and Decentralized Federated Minimax ...

引用

Annual Allerton Conference on Communication, Control, and Computing

作者： Sajjad Ghiasvand Amirhossein Reisizadeh Mahnoosh Alizadeh Ramtin Pedarsani Department of Electrical and Computer Engineering University of California Santa Barbara CA USA Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA

ISBN: (数字)9798331541033

ISBN: (纸本)9798331541040

As distributed learning applications like Federated Learning, the Internet of Things (IoT), and Edge Computing expand, addressing their limitations becomes crucial. We approach decentralized learning across a network of communicating clients or nodes, focusing on two primary challenges: data heterogeneity and adversarial robustness. To address these, we introduce a decentralized minimax optimization method incorporating two key components: local updates and gradient tracking. Minimax optimization serves as a fundamental tool for adversarial training, ensuring robustness. Local updates are vital in Federated Learning (FL) to alleviate the communication bottleneck, while gradient tracking is necessary to demonstrate convergence amid data heterogeneity. Our analysis of the proposed algorithm, Dec-Fed Track, in nonconvex-strongly-concave minimax optimization demonstrates its convergence to a stationary point. Additionally, numerical experiments support our theoretical results.

关键词： Training computer aided instruction Federated learning Distance learning Optimization methods Focusing Robustness Internet of Things Convergence Edge computing

来源：评论

学校读者我要写书评

暂无评论

Bacterial population dynamics and biosafety assessment in a closed Bioregenerative Life Support System during the “Lunar Palace 365” experiment

引用

Science China Life Sciences 2025年第7期68卷 2137-2149页

作者： Yuming Fu Yueying Lu Jianlou Yang Hong Liu Key Laboratory of Biomechanics and Mechanobiology (Beihang University) Ministry of Education Key Laboratory of Innovation and Transformation of Advanced Medical Devices Ministry of Industry and Information Technology National Medical Innovation Platform for Industry-Education Integration in Advanced Medical Devices (Inte rdiscipline of Medicine and Engineering) School of Biological Science and Medical Engineering Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University International Joint Research Center of Aerospace Biotechnology & Medical Engineering Beihang University School of Sport Management Shan Dong Sport University Innovation Center for Medical Engineering & Engineering Medicine Hangzhou International Innovation Institute Beihang University

Our study investigates the dynamic variation of bacterial populations within the Bioregenerative Life Support System(BLSS), a critical component for sustainable habitats in extraterrestrial environments supporting human survival. We utilized the ground-based BLSS test platform, referred to as “Lunar Palace 1”(LP1), to examine bacterial dynamics in an ecosystem integrating plant production, human cultivation, and equipment maintenance. Our findings reveal distinct bacterial compositions among crew members and functional areas within the LP1 system while preserving temporal stability across the 370-day experiment. Importantly, we observed a low abundance of potential pathogens, minimal antibiotic resistance, and negligible impact of the isolated bacterial strains on equipment materials, suggesting favorable biosafety attributed to plant integration. Our work enhances the understanding of microbial communities in BLSS and underscores the importance of incorporating green plants to bolster environmental biosafety and sustainability in long-term space exploration missions.

关键词： bacterial community dynamics Bioregenerative Life Support System biosafety antibiotic resistance genes biodegradation

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：