检索结果-内蒙古大学图书馆

Deep learning-based software engineering: progress,challenges, and opportunities

science china(Information sciences) 2025年第1期68卷 57-144页

作者： Xiangping CHEN Xing HU Yuan HUANG He JIANG Weixing JI Yanjie JIANG Yanyan JIANG Bo LIU Hui LIU Xiaochen LI Xiaoli LIAN Guozhu MENG Xin PENG Hailong SUN Lin SHI Bo WANG Chong WANG Jiayi WANG Tiantian WANG Jifeng XUAN Xin XIA Yibiao YANG Yixin YANG Li ZHANG Yuming ZHOU Lu ZHANG School of Journalism and Communication Sun Yat-sen University School of Software Technology Zhejiang University School of Software Engineering Sun Yat-sen University School of Software Dalian University of Technology School of Computer Science and Technology Beijing Institute of Technology Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of EducationSchool of Computer Science Peking University State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences School of Computer Science Fudan University State Key Laboratory of Complex & Critical Software Environment (CCSE) School of Software Beihang University School of Computer and Information Technology Beijing Jiaotong University School of Computer Science and Technology Harbin Institute of Technology School of Computer Science Wuhan University Huawei Technologies

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i

关键词： deep learning software engineering software benchmark software artifact representation survey

来源：评论

学校读者我要写书评

暂无评论

Unique composite architecture of phosphor-in-glass film coated on different heat-conducting substrates for high-brightness laser lighting

引用

Journal of Advanced Ceramics 2025年第2期14卷 151-158页

作者： Xin Liu Mingxiang Chen Jiuzhou Zhao Hongjin Zhang Yang Peng Qing Wang State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China School of Aerospace Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Energy and Power Engineering Huazhong University of Science and TechnologyWuhan 430074China

In the development of static luminescent materials with remarkable optical-thermal performance and low cost, next-generation high-brightness laser lighting faces a key challenge. Herein, a unique composite architecture of Y3Al5O_(12):Ce^(3+) (YAG) phosphor-in-glass film coated on different heat-conducting substrates (PiGF@HCSs), i.e., PiGF@sapphire, PiGF@Al_(2)O_(3), PiGF@AlN, and PiGF@BN–AlN composites, was designed and prepared by a simple film printing and low-temperature sintering technology. The heat-conducting substrates significantly affect the luminescence saturation and phosphor conversion of PiGF@HCSs, allowing substrates with higher thermal conductivity (TC) to have a higher laser power density (LPD) and higher reflectivity to enable higher luminous efficacy (LE). As a consequence, PiGF@sapphire realizes a luminous flux (LF) of 2076 lm@12 W/mm^(2), which is higher than those of PiGF@Al_(2)O_(3) (1890 lm@15 W/mm^(2)) and PiGF@AlN (1915 lm@24 W/mm^(2)), whilePiGF@BN–AlN enables a maximum LF of 3058 lm@21 W/mm^(2). Furthermore, the LE of PiGF@BN–AlN reaches 194 lm/W, which is 1.6 times that of PiGF@AlN, while those of PiGF@sapphire and PiGF@Al_(2)O_(3) are 192 and 150 lm/W, respectively. The working temperature of PiGF@AlN is only 93.3℃ under LPD of 9 W/mm^(2), while those of PiGF@sapphire, PiGF@Al_(2)O_(3), and PiGF@BN–AlN increase to 193.8, 133.6, and 117℃, respectively. These findings provide guidance for commercial applications of PiGF@HCS converters in high-brightness laser lighting and displays.

关键词： luminescent materials phosphor-in-glass film(PiGF) heat-conducting substrate(HCS) laser lighting optical-thermal performances

来源：评论

学校读者我要写书评

暂无评论

Knowledge Probabilization in Ensemble Distillation: Improving Accuracy and Uncertainty Quantification for Object Detectors

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 221-233页

作者： Yang, Yang Wang, Chao Gong, Lei Wu, Min Chen, Zhenghua Li, Xiang Chen, Xianglan Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China 138632 Singapore East China Normal University School of Data Science and Engineering Shanghai200062 China

Ensemble object detectors have demonstrated remarkable effectiveness in enhancing prediction accuracy and uncertainty quantification. However, their widespread adoption is hindered by significant computational and storage demands, limiting their feasibility in resource-constrained settings. To overcome this, researchers have focused on distilling the knowledge from ensemble object detectors into a single model. In this article, we introduce probabilization based ensemble distillation (ProbED), an innovative ensemble distillation framework that consolidates knowledge from multiple object detectors into a single, resource-efficient model. Unlike traditional ensemble distillation methods that average the outputs of subteachers, ProbED captures comprehensive outcome distributions from all subteachers, providing a more nuanced approach to knowledge transfer. ProbED employs knowledge probabilization to achieve a sophisticated and refined aggregation of teacher knowledge, including feature knowledge, semantic knowledge, and localization knowledge, resulting in dual improvements in prediction accuracy and uncertainty quantification for the student model. In particular, ProED's novel knowledge probabilization-based approach to aggregating teacher knowledge is inspired by our empirical observations, which demonstrate that knowledge probabilization excels in effectively representing uncertainty, improving prediction, and facilitating robust knowledge transfer. Furthermore, we introduce a random smoothing perturbation technique to modify inputs within ProbED, further enhancing the distillation process. Extensive experiments highlight ProbED's ability to significantly enhance the prediction accuracy and uncertainty quantification of various object detectors, demonstrating its superior performance compared to other state-of-the-art techniques. © 2024 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

A bio-inspired optical imaging method for robotic perception in turbid water

引用

science china(Technological sciences) 2025年第1期68卷 75-77页

作者： Xudong SUN Yafeng LI Peng LIN Xiaodi SHANG Xianping FU School of Information Science and Technology Dalian Maritime UniversityDalian 116026China College of Computer Science and Technology Qingdao UniversityQingdao 266071China

In the realm of underwater robotics,optical imaging plays a pivotal role in many scientific *** to the effects of absorption and scattering,images captured in turbid water are severely ***,enhancing the quality of underwater optical images stands paramount in ensuring the continued advancement and efficacy of underwater robots across its multifarious applications.

关键词： underwater optical continued

来源：评论

学校读者我要写书评

暂无评论

Defending Federated Learning System from Poisoning Attacks via Efficient Unlearning

引用

computers, Materials & Continua 2025年第4期83卷 239-258页

作者： Long Cai Ke Gu Jiaqi Lei School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China

Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concerns regarding their vulnerability to potential *** attacks turn into a major menace to federated learning on account of their concealed property and potent destructive *** altering the local model during routine machine learning training,attackers can easily contaminate the global *** detection and aggregation solutions mitigate certain threats,but they are still insufficient to completely eliminate the influence generated by ***,federated unlearning that can remove unreliable models while maintaining the accuracy of the global model has become a *** some existing federated unlearning approaches are rather difficult to be applied in large neural network models because of their high computational ***,we propose SlideFU,an efficient anti-poisoning attack federated unlearning *** primary concept of SlideFU is to employ sliding window to construct the training process,where all operations are confined within the *** design a malicious detection scheme based on principal component analysis(PCA),which calculates the trust factors between compressed models in a low-cost way to eliminate unreliable *** confirming that the global model is under attack,the system activates the federated unlearning process,calibrates the gradients based on the updated direction of the calibration *** on two public datasets demonstrate that our scheme can recover a robust model with extremely high efficiency.

关键词： Federated learning malicious client detection model recovery machine unlearning

来源：评论

学校读者我要写书评

暂无评论

Towards Lifelong Learning of Large Language Models: A Survey

引用

ACM Computing Surveys 2025年第8期57卷 1-35页

作者： Zheng, Junhao Qiu, Shengjie Shi, Chengming Ma, Qianli School of Computer Science and Engineering South China University of Technology Guangzhou China

As the applications of large language models (LLMs) expand across diverse fields, their ability to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods with static datasets are inadequate for coping with the dynamic nature of real-world information. Lifelong learning, or continual learning, addresses this by enabling LLMs to learn continuously and adapt over their operational lifetime, integrating new knowledge while retaining previously learned information and preventing catastrophic forgetting. Our survey explores the landscape of lifelong learning, categorizing strategies into two groups based on how new knowledge is integrated: Internal Knowledge, where LLMs absorb new knowledge into their parameters through full or partial training, and External Knowledge, which incorporates new knowledge as external resources such as Wikipedia or APIs without updating model parameters. The key contributions of our survey include: (1) introducing a novel taxonomy to categorize the extensive literature of lifelong learning into 12 scenarios;(2) identifying common techniques across all lifelong learning scenarios and classifying existing literature into various technique groups;(3) highlighting emerging techniques such as model expansion and data selection, which were less explored in the pre-LLM era. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Automated Approach to Discovering Software Refactorings by Comparing Successive Versions

引用

IEEE Transactions on Software Engineering 2025年第5期51卷 1358-1380页

作者： Liu, Bo Liu, Hui Niu, Nan Zhang, Yuxia Li, Guangjie Jiang, He Jiang, Yanjie University of Cincinnati Department of Electrical Engineering and Computer Science CincinnatiOH United States National Innovation Institute of Defense Technology Beijing China School of Software Dalian University of Technology Dalian China Beijing Institute of Technology School of Computer Science and Technology Beijing China Peking University School of Computer Science Beijing China

Software developers and maintainers frequently conduct software refactorings to improve software quality. Identifying the conducted software refactorings may significantly facilitate the comprehension of software evolution, and thus facilitate software maintenance and evolution. Besides that, the identified refactorings are also valuable for data-driven approaches in software refactoring. To this end, researchers have proposed a few approaches to identifying software refactorings automatically. However, the performance (especially precision) of such approaches deserves substantial improvement. To this end, in this paper, we propose a novel refactoring detection approach, called REEXTRACTOR+. At the heart of REEXTRACTOR+ is a reference-based entity matching algorithm that matches coarse-grained code entities (e.g., classes and methods) between two successive versions, and a context-aware statement matching algorithm that matches statements within a pair of matched methods. We evaluated REEXTRACTOR+ on a benchmark consisting of 400 commits from 20 real-world projects. The evaluation results suggested that REEXTRACTOR+ significantly outperformed the state of the art in refactoring detection, reducing the number of false positives by 59.6% and improving recall by 19.2%. We also evaluated the performance of the proposed matching algorithms that serve as the cornerstone of refactoring detection. The evaluation results suggested that the proposed algorithms excel in matching code entities, substantially reducing the number of mistakes (false positives plus false negatives) by 67% compared to the state-of-the-art approaches. © 2025 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

A Path-Based Topology-Agnostic Fault Diagnosis Strategy for Multiprocessor Systems

引用

IEEE Transactions on computers 2025年第6期74卷 1886-1896页

作者： Chen, Lin Feng, Hao Wu, Jiong Hainan University School of Computer Science and Technology Haikou570100 China

Fault diagnosis technology is a method for locating faulty processors in multiprocessor systems, and it plays a crucial role in ensuring system stability, security and reliability. A widely used approach in this technology is the system-level strategy, which determines processor status by interpreting the set of test results between adjacent processors. Among them, the PMC and MMmodels are two commonly employed methods for generating these results. The diversity and complexity of network topologies in systems constrain existing algorithms to specific topologies, while the limitations of fault diagnosis strategies lead to reduced fault tolerance. In this paper, we present a novel path-based method to tackle the fault diagnosis problems in various networks according to the PMC and MM models. Firstly, we introduce the algorithm for partitioning the path into subpaths based on these models. To ensure that at least one subpath is diagnosed as fault free, we derive the relationship between the fault bound T and the path length N. Then, building on methods for recognizing the subpath states, we have developed fault diagnosis algorithms for both the PMC and MM models. The simulation results show that our proposed algorithms can quickly and accurately diagnose faults in multiprocessor systems. © 1968-2012 IEEE.

关键词： Multiprocessing systems

来源：评论

学校读者我要写书评

暂无评论

Disentangled Multi-Graph Convolution for Cross-Domain Recommendation

引用

ACM Transactions on Knowledge Discovery from Data 2025年第3期19卷 1-28页

作者： Gao, Yibo Liu, Zhen Yang, Xinxin Lu, Sibo Yuan, Yafan School of Computer Science and Technology Beijing Jiaotong University Beijing China

Data sparsity poses a significant challenge for recommendation systems, prompting the research of Cross-Domain Recommendation (CDR). CDR aims to leverage more user-item interaction information from source domains to improve the recommendation performance in the target domain. However, a major challenge in CDR is the identification of transferable features. Traditional CDR methods struggle to distinguish between the various features of users, including domain-invariant features that are effective for feature transfer and domain-specific features that are detrimental to cross-domain information transfer. In this article, we aim to disentangle domain-invariant features and domain-specific features and effectively utilize these different features. This enables effective domain-to-domain information transfer by only transferring domain-invariant features while still considering the role of domain-specific features within their respective domains. Based on the superiority of graph structural feature learning and disentangled represent learning, we propose - a model that learns Disentangled user feature representations and constructs a Multi-Graph network for bidirectional knowledge transfer of shared features for CDR. Specifically, we designed two regularization terms to disentangle domain-invariant features and domain-specific features. Subsequently, we established a multi-graph convolutional network to enhance domain-specific features within single-domain graphs and transfer domain-invariant features across cross-domain graphs. Our approach also includes designing feature constraints to enhance the combination of features derived from different graphs and to uncover potential correlations among them. Extensive experiments on real-world datasets have demonstrated that our model significantly outperforms state-of-the-art CDR approaches. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

14-Bit SAR ADC with on-Chip Digital Bubble Sorting Calibration technology

引用

Chinese Journal of Electronics 2025年第1期34卷 125-136页

作者： Hua Fan Zhuorui Chen Tongrui Xu Franco Maloberti Qi Wei Quanyuan Feng School of Integrated Circuit Science and Engineering(Exemplary School of Microelectronics) University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chongqing Institute of Microelectronics Industry Technology University of Electronic Science and Technology of China Department of Electrical Computer and Biomedical Engineering University of Pavia Department of Precision Instrument Tsinghua University Institute of Microelectronics Southwest Jiaotong University

This article designs a 14-bit successive approximation register analog-to-digital converter（SAR ADC）.A novel digital bubble sorting calibration method is proposed and applied to eliminate the effect of capacitor mismatch on the linearity of the SAR ADC. To reduce the number of capacitors, a hybrid architecture of a high 8-bit binary-weighted capacitor array and a low 6-bit resistor array is adopted by the digital-to-analog（DAC）. The common-mode voltage VCM-based switching scheme is chosen to reduce the switching energy and area of the DAC. The time-domain comparator is employed to obtain lower power consumption. Sampling is performed through a gate voltage bootstrapped switch to reduce the nonlinear errors introduced when sampling the input signal. Moreover, the SAR logic and the whole calibration is totally implemented on-chip through digital integrated circuit（IC） tools such as design compiler, IC compiler, etc. Finally, a prototype is designed and implemented using 0.18 μm bipolar-complementary metal oxide semiconductor（CMOS）-double-diffused MOS 1.8 V CMOS technology. The measurement results show that the SAR ADC with on-chip bubble sorting calibration method achieves the signal-to-noise-and-distortion ratio of 69.75 dB and the spurious-free dynamic range of 83.77 dB.

关键词： Semiconductor device measurement Capacitors Linearity Switches Calibration System-on-chip Frequency measurement Time-domain analysis Sorting Signal to noise ratio

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：