检索结果-南通市图书馆

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

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

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

FedCLCC:A personalized federated learning algorithm for edge cloud collaboration based on contrastive learning and conditional computing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Defence technology(防务技术) 2025年第1期43卷 80-93页

作者： Kangning Yin Xinhui Ji Yan Wang Zhiguo Wang School of Information and software Engineering University of Electronic Science and Technology of ChinaChengdu611731China institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Federated learning(FL)is a distributed machine learning paradigm for edge cloud *** can facilitate data-driven decision-making in tactical scenarios,effectively addressing both data volume and infrastructure challenges in edge ***,the diversity of clients in edge cloud computing presents significant challenges for *** federated learning(pFL)received considerable attention in recent *** example of pFL involves exploiting the global and local information in the local *** pFL algorithms experience limitations such as slow convergence speed,catastrophic forgetting,and poor performance in complex tasks,which still have significant shortcomings compared to the centralized *** achieve high pFL performance,we propose FedCLCC:Federated Contrastive Learning and Conditional *** core of FedCLCC is the use of contrastive learning and conditional *** learning determines the feature representation similarity to adjust the local *** computing separates the global and local information and feeds it to their corresponding heads for global and local *** comprehensive experiments demonstrate that FedCLCC outperforms other state-of-the-art FL algorithms.

关键词： Federated learning Statistical heterogeneity Personalized model Conditional computing Contrastive learning

Classifying extended,localized and critical states in quasiperiodic lattices via unsupervised learning

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2025年第1期34卷 422-427页

作者： Bohan Zheng Siyu Zhu Xingping Zhou Tong Liu School of Computer Science and technology School of SoftwareNanjing University of Posts and TelecommunicationsNanjing 210023China institute of Quantum Information and technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Department of Applied Physics School of ScienceNanjing University of Posts and TelecommunicationsNanjing 210003China

Classification of quantum phases is one of the most important areas of research in condensed matter *** this work,we obtain the phase diagram of one-dimensional quasiperiodic models via unsupervised ***,we choose two advanced unsupervised learning algorithms,namely,density-based spatial clustering of applications with noise(DBSCAN)and ordering points to identify the clustering structure(OPTICS),to explore the distinct phases of the Aubry–André–Harper model and the quasiperiodic p-wave *** unsupervised learning results match well with those obtained through traditional numerical ***,we assess similarity across different algorithms and find that the highest degree of similarity between the results of unsupervised learning algorithms and those of traditional algorithms exceeds 98%.Our work sheds light on applications of unsupervised learning for phase classification.

关键词： quantum phase quasiperiodic machine learning

Molecular dynamics simulation:The key to reveal the enrichment mechanisms of helium

在线全文

学校读者我要写书评

暂无评论

Science China Earth Sciences 2025年第2期68卷 643-645页

作者： Wenhui LIU Department of Geology Northwest UniversityXi’an 710069China Petroleum Exploration and production Research institute SINOPECBeijing 102206China

In recent years,helium and its enrichment mechanisms have been the frontier and attractive research in the field of geological resources(Liu et al.,2024).In the earliest geosciences,noble gases and their isotopes,including helium,were used as tracers for geochronology and geological processes due to their chemical inertness and *** attention has been paid to the isotope composition in geological bodies.

关键词： attractive frontier gases

同方期刊数据库

Absorption mechanism of SO_(3)on various alkaline absorbents in the presence of SO_(2)

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2025年第3期149卷 268-277页

作者： Junxiang Guo Jin Xiong Yuran Li Jirigele Qinggele Tingyu Zhu Shougang Group Research institute of technology Beijing 100043China Beijing Key Laboratory of Green Recyclable Process for Iron&Steel production technology Beijing 100043China CAS Key Laboratory of Green Process and Engineering Institute of Process EngineeringInnovation Academy for Green ManufactureChinese Academy of SciencesBeijing 100190China WISDRI City Environment Protection Engineering Limited Company Wuhan 430205China

Sulfur trioxide(SO_(3))as a condensable particle matter has a significant influence on atmospheric visibility,which easily arouses formation of *** is imperative to control the SO_(3)emission from the industrial flue *** commonly used basic absorbents,including Ca(OH)_(2),MgO and NaHCO_(3)were selected to explore the effects of temperature,SO_(2)concentration on the SO_(3)absorption,and the reaction mechanism of SO_(3)absorption was further *** suitable reaction temperature for various absorbents were proposed,Ca(OH)_(2)at the high temperatures above 500°C,MgO at the low temperatures below 320°C,and NaHCO_(3)at the temperature range of 320–500°*** competitive absorption between SO_(2)and SO_(3)was found that the addition of SO_(2)reduced the SO_(3)absorption on Ca(OH)_(2)and NaHCO_(3),while had no effect on *** order of the absorption selectivity of SO_(3)follows MgO,NaHCO_(3)and Ca(OH)_(2)under the given conditions in this *** absorption process of SO_(3)on NaHCO_(3)follows the shrinking core model,thus the absorption reaction continues until NaHCO_(3)was exhausted with the utilization rate of nearly 100%.The absorption process of SO_(3)on Ca(OH)_(2)and MgO follows the grain model,and the dense product layer hinders the further absorption reaction,resulting in low utilization of about 50%for Ca(OH)_(2)and *** research provides a favorable support for the selection of alkaline absorbent for SO_(3)removal in application.

关键词： Alkali absorbent Sulfur trioxide Selectivity Shrinking core model Grain model

Controllable chaos in the coupled waveguide-optomechanical system with phase shifter

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第04期Mechanics & Astronomy) .卷 30-38页

作者： Deng-Wei Zhang Pei-Qi Qin Li-Li Zheng Zhi-Ming Zhan Xin-You Lü Department of Mathematics and Physics Luoyang Institute of Science and Technology School of Computer and Information Engineering School of Software Luoyang Institute of Science and Technology School of Artificial Intelligence Jianghan University School of Physics Huazhong University of Science and Technology

We theoretically investigate chaotic dynamics in an optomechanical system composed of a whispering-gallery-mode(WGM) microresonator and a sensor. We find that tuning the optical phase using a phase shifter and modifying the coupling strength via a unidirectional waveguide(IWG) can induce chaotic motion. The underlying reason for this phenomenon is that adjusting the phase and coupling strength via the phase shifter and IWG bring the system close to an exceptional point(EP), where field localization dynamically enhances the optomechanical nonlinearity, leading to the generation of chaotic motion. In addition, due to the sensitivity of chaos to phase in the vicinity of the EP, we propose a theoretical scheme to measure the optical phase perturbations using chaos. Our work may offer an alternative approach to chaos generation with current experimental technology and provide theoretical guidance for optical signal processing and chaotic secure communication.

关键词：

Understanding and probing progression of localized corrosion on inner walls of steel pipelines:an overview

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2025年第1期32卷 1-18页

作者： Ming-yu Wang Hai-yuan Yao Yong-fei Liu Ye-sen Zhu Wan-bin Chen Yun-ze Xu Yi Huang School of Naval Architecture and Ocean Engineering Dalian University of TechnologyDalian 116024LiaoningChina China National Offshore Oil Corporation Research institute Co. Ltd.Beijing 100028China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentDalian University of TechnologyDalian 116024LiaoningChina

Corrosion poses a major threat to the safety of transportation ***,it is crucial to have an in-depth understanding of corrosion mechanisms in pipeline steels for the effective management of pipeline *** research on corrosion mechanisms relies on the use of efficient and reliable corrosion monitoring and analysis *** advancements in corrosion monitoring techniques specifically designed for the localized corrosion monitoring were aimed to be introduced,and a comprehensive overview of recent progress in understanding the localized corrosion mechanisms in pipeline steels was *** on the different corrosive environments encountered,the localized corrosion issues inside pipelines are classified into two categories:localized corrosion primarily influenced by electrochemical processes and localized corrosion controlled by both electrochemical and mechanical ***,a thorough analysis of the synergistic effects between micro-cell and macro-cell currents,as well as the interplay of mechanics and electrochemistry is ***,recommendations for future research on the mechanisms of internal localized corrosion in pipelines are provided.

关键词： Pipeline steel Localized corrosion Corrosion type Corrosion monitoring Corrosion mechanism

Evaluating complementaries among urban water,energy,infrastructure,and social Sustainable Development Goals in China

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2025年第3期149卷 585-597页

作者： Ke Yu Yifan Song Jin Lin Shen Qu School of Management and Economics Beijing Institute of TechnologyBeijing 100081China Center for Energy&Environmental Policy Research Beijing Institute of TechnologyBeijing 100081China

Urban areas’performance in water,energy,infrastructure,and socio-economic sectors is intertwined and measurable through Sustainable Development Goals(SDGs)6–*** synergy among these is critical for *** study constructs an indicator framework that reflects progress towards these urban SDGs in *** indicate underperformance in SDGs 8–11,suggesting the need for transformative *** network analysis,the research reveals complementarities among these ***,the SDG space divides into socio-economic and ecological clusters,with SDG 6(Clean Water and Sanitation)central to ***,SDG 8(Decent Work and Economic Growth)and SDG 9(Industry,Innovation,and Infrastructure)act as bridges,while greater synergies exist between SDG 12(Responsible Consumption and production)and SDG 13(Climate Action).An in-depth view at the indicator-level shows a core-periphery structure,emphasizing indicators like SDG 6.2(Wastewater Treatment Rate)and SDG 6.6(Recycled Water production Capacity per capita)as *** study confirms the urban SDG space’s stability and predictiveness,underscoring its value in steering well-aligned policy decisions for sustainable growth.

关键词： Sustainable development goals Synergy Urban development Policy decisions

Palaeowind reconstruction from Lower Cretaceous wavedominated depositional records of the Tanan Depression,Northeast Asia

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Oceanology and Limnology 2025年第1期43卷 41-56页

作者： Xinyu XUE Zaixing JIANG Chao LIU Li WANG Huanyu XIE Lizhou SONG Ming SU School of Marine Science Sun Yat-sen UniversityZhuhai 519083China School of Energy Resources China University of Geosciences(Beijing)Beijing 100083China Sinopec Matrix Corporation Qingdao 266000China Daqing Oilfield production technology institute Daqing 163453China

Palaeowind regime is an important component for reconstructing palaeoclimate and understanding ancient global *** applied the beach-ridge thickness technique(BTT)and the longshore-bar thickness technique(LTT)to reconstruct the Early Cretaceous palaeowind velocities based on depositional records of Tanan Depression in Northeast *** thickness of beach ridges and nearshore bars is the most important parameter for applying the BTT and the LTT *** identified 22 beach ridges and 23 nearshore bars based on drilling cores and wireline-log data in the Tanan *** velocities calculated by using the LTT method ranged from 10.84 to 13.66 m/s,showing a narrower range than those calculated by using the BTT method(7.58–15.93 m/s).We further analyzed the underlying factors causing the difference between the results derived from these two methods based on the sedimentary process of the beach ridge and the nearshore *** reconstructed wind regime was assumed to be the summer monsoon originating from the Mongol-Okhotsk Ocean before it had been completely enclosed,which provides valuable insight into the understanding of the atmospheric circulation in Northeast Asia during the Early Cretaceous.

关键词： palaeowind beach ridge nearshore bar Early Cretaceous East Asia Summer Monsoon