检索结果-内蒙古大学图书馆

Improving Machine Translation Formality with Large Language Models

computers, Materials & Continua 2025年第2期82卷 2061-2075页

作者： Murun Yang Fuxue Li School of Computer Science and Engineering Northeastern UniversityShenyang110819China College of Electrical Engineering Yingkou Institute of TechnologyYingkou115014China

Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a formal translation style. The second approach employs an LLM as a reward model for scoring translation formality, and then uses reinforcement learning algorithms to fine-tune the NMT model to maximize the reward score, thereby enhancing the formality of the generated translations. Considering the substantial parameter size of LLMs, we also explore methods to reduce the computational cost of INMTF. Experimental results demonstrate that INMTF significantly outperforms baselines in terms of translation formality and translation quality, with an improvement of +9.19 style accuracy points in the German-to-English task and +2.16 COMET score in the Russian-to-English task. Furthermore, our work demonstrates the potential of integrating LLMs within NMT frameworks to bridge the gap between NMT outputs and the formality required in various real-world translation scenarios.

关键词： Neural machine translation formality large language model text style transfer style evaluation reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DeepSwarm:towards swarm deep learning with bi-directional optimization of data acquisition and processing

引用

Frontiers of computer science 2025年第3期19卷 125-127页

作者： Sicong LIU Bin GUO Ziqi WANG Lehao WANG Zimu ZHOU Xiaochen LI Zhiwen YU School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’an 710072China School of Data Science City University of Hong KongHong Kong 999077China College Of Computer Science And Technology Harbin Engineering UniversityHarbin 150001China

1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves privacy,enhances responsiveness,and saves ***,current ondevice DL relies on predefined patterns,leading to accuracy and efficiency *** is difficult to provide feedback on data processing performance during the data acquisition stage,as processing typically occurs after data acquisition.

关键词： drone swarm classification efficient local data processing data processing deep learning dl device deep learning bi directional optimization iot devices swarm deep learning

来源：评论

学校读者我要写书评

暂无评论

Orbit-Orbit Interaction in Spatiotemporal Optical Vortex

引用

engineering 2025年第2期45卷 44-51页

作者： Jian Chen Jie Zhao Xi Shen Dewei Mo Cheng-Wei Qiu Qiwen Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore

While spin-orbit interaction has been extensively studied,few investigations have reported on the interaction between orbital angular momenta(OAMs).In this work,we study a new type of orbit-orbit coupling between the longitudinal OAM and the transverse OAM carried by a three-dimensional(3D)spatiotemporal optical vortex(STOV)in the process of tight *** 3D STOV possesses orthogonal OAMs in the x-y,t-x,and y-t planes,and is preconditioned to overcome the spatiotemporal astigmatism effect.x,y,and t are the axes in the spatiotemporal *** corresponding focused wavepacket is calculated by employing the Debye diffraction theory,showing that a phase singularity ring is generated by the interactions among the transverse and longitudinal vortices in the highly confined *** Fourier-transform decomposition of the Debye integral is employed to analyze the mechanism of the orbit-orbit *** is the first revelation of coupling between the longitudinal OAM and the transverse OAM,paving the way for potential applications in optical trapping,laser machining,nonlinear light-matter interactions,and more.

关键词： Spatiotemporal optical vortex Orbital angular momentum Momentum interaction Highly confined wavepacket Diffraction

来源：评论

学校读者我要写书评

暂无评论

AN ITERATIVE TWO-GRID METHOD FOR STRONGLY NONLINEAR ELLIPTIC BOUNDARY VALUE PROBLEMS

引用

Journal of Computational Mathematics 2025年第3期43卷 673-689页

作者： Jiajun Zhan Lei Yang Xiaoqing Xing Liuqiang Zhong School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao SAR 999078China School of Mathematical Sciences South China Normal UniversityGuangzhou 510631China

We design and analyze an iterative two-grid algorithm for the finite element discretizations of strongly nonlinear elliptic boundary value problems in this *** propose an iterative two-grid algorithm,in which a nonlinear problem is first solved on the coarse space,and then a symmetric positive definite problem is solved on the fine *** main contribution in this paper is to establish a first convergence analysis,which requires dealing with four coupled error estimates,for the iterative two-grid *** also present some numerical experiments to confirm the efficiency of the proposed algorithm.

关键词： Iterative two-grid method Convergence Strongly nonlinear elliptic problems

来源：评论

学校读者我要写书评

暂无评论

Federated Synergy: Hierarchical Multi-Agent Learning for Sustainable Edge Computing in IIoT

引用

IEEE Access 2025年 13卷 68311-68322页

作者： Benila, S. Devi, K. Vellore Institute of Technology Chennai Campus School of Computer Science and Engineering Tamil Nadu 600127 India

The Industrial Internet of Things (IIoT) presents significant challenges in task offloading, resource allocation, and energy efficiency, necessitating intelligent, scalable, and adaptive solutions. This paper introduces the Hierarchical Multi-Agent Federated Actor-Critic (HMAFAC) algorithm. This novel approach integrates hierarchical reinforcement learning with multi-agent federated learning to enhance decision-making in dynamic edge computing environments. It employs multi-agent reinforcement learning to optimize resource allocation and task offloading by leveraging local Actor-Critic models on IoT edge devices. A Deep Q-Network (DQN) agent manages task offloading decisions based on real-time system states, ensuring efficient task execution. To maintain data privacy and reduce communication overhead, federated learning aggregates model updates at the edge server, eliminating the need for raw data exchange. Additionally, a hierarchical framework enables adaptive scheduling, allowing flexible computational scaling from edge to cloud servers based on task complexity and network conditions. By effectively reducing latency and energy consumption, enhancing system adaptability, and maintaining computational efficiency, HMAFAC overcomes key limitations of existing IIoT frameworks. Simulation results validate its superior performance compared to baseline methods regarding resource utilization, energy conservation, and model convergence. These findings establish HMAFAC as a robust and scalable framework for optimizing IIoT applications in distributed and resource-constrained environments. Future work will further explore advanced federated learning techniques, enhanced privacy mechanisms, and real-world deployment in industrial systems to improve efficiency and scalability. © 2013 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Software Defect Prediction Method Using a Multivariate Heterogeneous Hybrid Deep Learning Algorithm

引用

computers, Materials & Continua 2025年第2期82卷 3251-3279页

作者： Qi Fei Haojun Hu Guisheng Yin Zhian Sun College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Information Technology Research Department Jiangsu Automation Research InstituteLianyungang222062China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China

Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.

关键词： Software defect prediction multiple heterogeneous data graph convolutional network models based on adjacency and spatial topologies CNN-BiLSTM TabNet

来源：评论

学校读者我要写书评

暂无评论

Edge-aware Feature Aggregation Network for Polyp Segmentation

引用

Machine Intelligence Research 2025年第1期22卷 101-116页

作者： Tao Zhou Yizhe Zhang Geng Chen Yi Zhou Ye Wu Deng-Ping Fan PCA Lab Key Laboratory of Intelligent Perception and Systems for High-dimensional Information of Ministry of EducationSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094China School of Computer Science and Engineering Northwestern Polytechnical University(NPU)Xi’an710129China School of Computer Science and Engineering Southeast UniversityNanjing211189China Computer Vision Lab ETH ZürichZürich8092Switzerland

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and *** this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp ***,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer ***,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale ***,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual ***,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation *** results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and *** implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet.

关键词： Colorectal cancer polyp segmentation edge-aware guidance module scale-aware convolution module cross-level fusion module

来源：评论

学校读者我要写书评

暂无评论

HDD-Net: Haar Dual Domain Network for Ring Artifacts Correction

IEEE Transactions on Computational Imaging

引用

IEEE Transactions on Computational Imaging 2025年 11卷 399-409页

作者： Wu, Xuelong Wang, Junsheng Zhao, Qingjie Beijing Institute of Technology School of Mechanical Engineering Beijing100081 China Beijing Institute of Technology Advanced Research Institute for Multidisciplinary Science School of Materials Science and Engineering Beijing100081 China Beijing Institute of Technology School of Computer Science Beijing100081 China

Ring artifacts are common artifacts in X-ray Computed Tomography (XCT) scans and have a significant impact on subsequent feature/phase extractions due to the small grayscale gradients in XCT volume data of bulk materials. This paper proposes the Haar Dual Domain Network for correcting ring artifacts. By utilizing the Haar wavelet decomposition on images containing ring artifacts in both the image and projection domains, the ring artifacts are preliminarily separated, facilitating their removal by neural networks while preserving microstructure features such as low-contrast phase boundaries. By constructing a feature fusion network, the information from both 2D slices and 3D projection volume data has been fully integrated to eliminate ring artifacts while preserving the edges of every feature. The effectiveness of the Haar wavelet transform and fusion network has been validated by ablation experiments, proving the application of HDD-Net to large volume of XCT data. © 2015 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Auto-3D-house Design from Structured User Requirements

引用

Machine Intelligence Research 2025年第2期22卷 368-385页

作者： Minkui Tan Qi Chen Zixiong Huang Qi Wu Yuanqing Li Jiaqiu Zhou School of Software Engineering South China University of TechnologyGuangzhou 510006China Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide SA 5005Australia School of Automation Science and Engineering South China University of TechnologyGuangzhou 510006China

We study the task of automated house design,which aims to automatically generate 3D houses from user ***,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user *** address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,*** the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of *** addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary ***,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline ***,we render 3D houses according to the given style requirements in a rule-based *** on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.

关键词： Automated house design user requirements understanding outline processing layout generation graph feature generation.

来源：评论

学校读者我要写书评

暂无评论

A Trust-Based Computation Offloading Framework in Mobile Cloud-Edge Computing Networks

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5370-5385页

作者： Wang, Jianhui Li, Zhetao Liu, Haolin Qiu, Tie Luo, Hongbin Jinan University College of Information Science and Technology Guangzhou510632 China Xiangtan University School of Computer Science Xiangtan411105 China Tianjin University School of Computer Science and Technology College of Intelligence and Computing Tianjin300350 China Beihang University School of Computer Science and Engineering Beijing100191 China

Cloud service centers (CSCs) can purchase edge computation resources to improve service quality in mobile cloud-edge computing networks. However, edge servers (ESs) are owned by different entities, and dishonest entities may launch computational forgery attacks, i.e., the ES falsely reports its idle computation resources to win more tasks for increased revenue. Most existing approaches ignore the threat of dishonest ESs. To address the challenges, we design a Trust-based Computation Offloading (TCO) framework. First, we construct the problem for minimizing the difference between the CSC's cost and the expected revenue (DCER), which is a mixed-integer nonlinear programming problem. Second, we develop a trust-based computation offloading method that quickly finds a good solution by decomposing the problem. Finally, a two-tier trust evaluation method was proposed to obtain accurate trust values. Experimental results indicate that TCO's comprehensive performance surpasses the benchmarks and significantly enhances computation offloading reliability with a lower performance loss. Notably, tasks are preferentially offloaded to honest ESs to ensure their revenue and promote ESs’ honesty under the TCO framework. Additionally, compared with no trust mechanisms, TCO reduces the service timeout count in an interval by 34.37% - 73.80% with a performance loss of only 1.42% - 4.10%. © 2002-2012 IEEE.

关键词： Cloud platforms

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：