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

A Sentence Retrieval Generation Network Guided Video Captioning

引用

computers, Materials & Continua 2023年第6期75卷 5675-5696页

作者： Ou Ye Mimi Wang Zhenhua Yu Yan Fu Shun Yi Jun Deng College of Computer Science and Technology Xi’an University of Science and TechnologyXi’an710054China College of Safety and Engineering Xi’an University of Science and TechnologyXi’an710054China

Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input *** contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video *** address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this ***,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data *** features are decoded to generate textual sentences that conform to video content for sentence ***,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual *** candidate sentences are screened out through similarity ***,a novel GPT-2 network model is constructed based on GPT-2 network *** model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language *** proposed method in this paper is compared with several existing works by *** results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT *** can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.

关键词： Video captioning encoder-decoder sentence retrieval external corpus RS GPT-2 network model

来源：评论

学校读者我要写书评

暂无评论

Evolutions of Microstructure and Mechanical Properties in Mg-5Li-1Zn-0.5Ag-0.5Zr-xGd Alloy

引用

Acta Metallurgica Sinica(English Letters) 2023年第2期36卷 215-228页

作者： Bing-Yu Qian Rui-Zhi Wu Jian-Feng Sun Jing-Huai Zhang Le-Gan Hou Xiao-Chun Ma Jia-Hao Wang Hai-Ting Hu Key Laboratory of Superlight Materials&Surface Technology Ministry of EducationHarbin Engineering UniversityHarbin150001China College of Materials Science and Engineering Heilongjiang University of Science and TechnologyHarbin150022China

The evolution of the microstructure and mechanical properties of alloy system with nominally composition Mg-5Li-1Zn-0.5Ag-0.5Zr-xGd(x=0,1.2,2.4,3.6,4.8,6)is evaluated based on computational phase diagram and corresponding experimental *** results show that grains are significantly refined with the increase of Gd *** main phases of as-cast alloys areα-Mg,β-Li,AgLi_(2)Mg,and Mg_(3)*** the increase of Gd content,the amounts of Mg_(3)Gd phase andβ-Li phase have been *** the Gd content exceeds 3.6 wt%,Mg_(3)Gd phase precipitates in a form of the network at the grain *** precipitation ofβ-Li can be attributed to the competitive dissolution of Zn,Gd,and Li in ***,γ″is formed after the addition of Gd,which grows and transforms intoγ′with the increase of Gd *** solidification process,stacking faults are formed by solid transformation of partialα-Mg and Mg_(3)***,with the synergistic effect of Mg_(3)Gd,β-Li,andγ″(orγ′),as the Gd content increasing,the tensile strength of the alloy first increases,then decreases,and the elongation *** the content of Gd is 4.8 wt%,the ultimate tensile strength and yield strength reach the maximum values of 227 MPa and 139 MPa,and the elongation is 18.1%,respectively.

关键词： Mg-Li-Zn-Gd alloy Phase diagram Microstructure evolution Mechanical properties

来源：评论

学校读者我要写书评

暂无评论

FedQT: A Federated Learning Model Compression Algorithm Based on Quicksort and Top Avg Pruning

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第1期9卷 225-238页

作者： Zhang, Jin-Quan Xu, Hui-Xin Ma, Yun-Shen Ni, Li-Na College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

With the advent of the fourth industrial revolution, data ushered in explosive growth. Federated learning can protect users’ privacy and raw data from being known by third parties. Its client data is only trained locally and will not be uploaded to the server. However, the need to continuously transmit between the server and the client in federated learning increases communication overhead and communication delay, and the consumption of resources is very large. In order to improve the communication efficiency of the federation, we proposed an FedQT federated learning model compression algorithm based on pruning and quantization. Firstly, the fast sorting is used to preprocess the trained parameters. Secondly, the middle part of the processed parameters is averaged to obtain the pruning threshold avg(ω). Then, according to the obtained new threshold standard, the model performs Top Avg pruning based on median comparison. Finally, the k − means algorithm is used to cluster the parameters for further compression. In the simulation experiment, FedQT is compared with uncompressed and other compression algorithms, and the time complexity is analyzed. It is proved that FedQT can compress the trained model parameters to improve its communication efficiency while reducing the time overhead. The model can be compressed by more than one thousand times, and the model accuracy can be maintained above 97%, which is enough to prove that FedQT algorithm has good performance in the compression framework of federated learning. © 2024.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

CMDCF: an effective cross-modal dense cooperative fusion network for RGB-D SOD

引用

Neural Computing and Applications 2024年第23期36卷 14361-14378页

作者： Jia, XingZhao Zhao, WenXiu Wang, YuMei DongYe, ChangLei Peng, YanJun College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

The success of vision transformer demonstrates that the transformer structure is also suitable for various vision tasks, including high-level classification tasks and low-level dense prediction tasks. Salient object detection (SOD) is a pixel-level dense prediction task that simulates the most salient objects in human visual recognition scenarios. In recent years, depth images have been widely used for salient object detection. Compared with RGB SOD, the key point of RGB-D SOD is the effective fusion of depth information. As RGB-D SOD requires extracting depth features and fusing cross-modal information, additional computation is involved. However, except for lightweight models, most RGB-D SOD methods tend to obtain better prediction maps by consuming more computational resources. We propose a cross-modal dense cooperative fusion net, which provides state-of-the-art performance with less computation and parameters. We take advantage of the ability of the transformer structure to model long sequence dependencies to extract saliency features from RGB images. Since there is less information in the depth image than in the RGB image, it is not necessary to use the same structure in the depth stream. For the sake of reducing parameters and computation, we consider the asymmetric architecture. It is enough to meet our needs that deep features extracted by lightweight MobileV2Net. Our decoder can perform dense cooperative fusion of cross-modal information while decoding features. It can both effectively fuse cross-modal information and save computation. Comprehensive experiments on multiple benchmark datasets for RGB-D SOD show that compared with SOTA methods, our method performs much better with less computation and parameters. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on Microservice Identification technology Based on API Correlation 29th

Research on Microservice Identification Technology Based on ...

引用

29th International Conference on Computational and Experimental Engineering and sciences, ICCES 2023

作者： Sun, Yang Lu, Dan Han, Qilong Yu, Cheng College of Computer Science and Technology Harbin Engineering University Harbin150009 China

ISBN: (纸本)9783031425141

Microservices are a new approach to software architecture design that enables complex monolithic applications to be constructed as a set of independent and loosely coupled chunks of services. A critical step in migrating monolithic architectures to microservices-based systems is the identification of the microservices contained in the target application. At this stage, most monolithic applications are highly cohesive and tightly coupled, which makes microservice decomposition difficult. Traditional microservice identification methods rely heavily on a priori knowledge or the intuitive experience of designers. Different identification methods require different data sources as a basis for extracting microservices, making it difficult to develop a uniform specification. This paper proposes a method to automatically identify microservices from a single system through the study of RESTful APIs, by introducing API topic semantic information similarity and response message information similarity as the criteria for microservice classification. The system consists of three parts: (1) Bert-whitening (Su et al., Whitening sentence representations for better semantics and faster retrieval, 2021) and Jaccard’s algorithm (Bennett et al., Proceedings of KDD cup and workshop, San Jose, CA, 2007) were used to calculate the overall similarity of the API, including the candidate topic similarity and the response message similarity. (2) constructing an API similarity graph with APIs as nodes and the overall similarity as the weight. (3) Spectral clustering algorithm is used to calculate scores and identify candidate microservices based on contour coefficients. A comparison with existing microservice classification methods proves the superiority of the method through experiments on six microservice open source projects and the results of the impact of hyperparameters on the quality of the experiments. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance issue monitoring, identification and diagnosis of SaaS software:a survey

引用

Frontiers of computer science 2025年第1期19卷 71-95页

作者： Rui WANG Xiangbo TIAN Shi YING College of Mining and Safety Engineering Shandong University of Science and TechnologyQingdao 266590China School of Computer Science Wuhan UniversityWuhan 430072China

SaaS (Software-as-a-Service) is a service model provided by cloud computing. It has a high requirement for QoS (Quality of Software) due to its method of providing software service. However, manual identification and diagnosis for performance issues is typically expensive and laborious because of the complexity of the application software and the dynamic nature of the deployment environment. Recently, substantial research efforts have been devoted to automatically identifying and diagnosing performance issues of SaaS software. In this survey, we comprehensively review the different methods about automatically identifying and diagnosing performance issues of SaaS software. We divide them into three steps according to their function: performance log generation, performance issue identification and performance issue diagnosis. We then comprehensively review these methods by their development history. Meanwhile, we give our proposed solution for each step. Finally, the effectiveness of our proposed methods is shown by experiments.

关键词： SaaS software performance log generation performance issue identification performance issue diagnosis

来源：评论

学校读者我要写书评

暂无评论

An improved LOS Guidance and Sail-Rudder Cooperative Controller for the Path Tracking of Unmanned Sailboats

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第10期9卷 1-14页

作者： Qin, Hongde Xu, Peilong Zhang, Fumin Xue, Yifan Science and Technology on Underwater Vehicle Laboratory Harbin Engineering University Harbin China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay China

Unmanned sailboats are driven only by wind, making them good platforms for the synchronous observation of air-sea interfaces over a large range. Compared with traditional unmanned ships, the unmanned sailboat involves simultaneous sail and rudder control for path tracking in unpredictable marine environments. The system is characterized by strong coupling and nonlinearity, creating challenges for the design of controllers. This paper combines line-of-sight (LOS) guidance with the introduction of a sideslip angle observer and model predictive control. A high-precision path tracking strategy suitable for cooperative sail and rudder control for unmanned sailboats is proposed. First, considering the lateral error easily caused by the large sideslip angle of sailboats, a full-path fixed-time guidance strategy with double fixed-time sideslip angle observers (DFSO) is proposed. Second, different from the previous strategy of decoupling the sail and rudder to control the speed and heading, the proposed cooperative control framework uses Lyapunov-based model predictive control (LMPC). The sailing speed and heading angle are both accounted for in the objective function, and the stability is verified by Lyapunov theory. Finally, the feasibility and superiority of this proposed method are confirmed by numerical simulation experiments involving the path tracking of a four degree of freedom sailboat model integrated with wind and waves in an ocean environment. IEEE

关键词： Model predictive control

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

Metaphor Detection with Context Enhancement and Curriculum Learning

Metaphor Detection with Context Enhancement and Curriculum L...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Jia, Kaidi Li, Rongsheng College of Computer Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798891761148

Metaphor detection is a challenging task for natural language processing (NLP) systems. Previous works failed to sufficiently utilize the internal and external semantic relationships between target words and their context. Furthermore, they have faced challenges in tackling the problem of data sparseness due to the very limited available training data. To address these two challenges, we propose a novel model called MiceCL. By leveraging the difference between the literal meaning of the target word and the meaning of the sentence as the sentence external difference, MiceCL can better handle the semantic relationships. Additionally, we propose a curriculum learning framework for automatically assessing difficulty of the sentence with a pre-trained model. By starting from easy examples and gradually progressing to more difficult ones, we can ensure that the model will not deal with complex data when its ability is weak so that to avoid wasting limited data. Experimental results demonstrate that MiceCL achieves competitive performance across multiple datasets, with a significantly improved convergence speed compared to other models. Our model is available at https://***/Evilxya/***. © 2024 Association for Computational Linguistics.

关键词： Curricula

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：