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

Propagating subduction initiation of the Caroline Plate at the Mussau Trench

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 Earth Sciences 2025年第1期68卷 253-269页

作者： Chun-Feng LI Yongkang DENG Tao WU Dongdong DONG Guoliang ZHANG Jiazheng ZHANG Yutao LIU Yaqing LI Fugui TANG Lulu ZHANG Department of Marine Sciences Zhejiang University Laboratory of Marine Mineral Resources Laoshan Laboratory Key Lab of Marine Geology and Environment Institute of Oceanology Chinese Academy of Sciences Key Lab of Ocean and Marginal Sea Geology South China Sea Institute of Oceanology Chinese Academy of Sciences Science & Technology on Integrated Information System Lab Institute of Software Chinese Academy of Sciences

New seismic imaging from the Mussau Trench confirms that, under horizontal compression on an oceanic plate boundary, it is within the young and weak oceanic plate that a trench will develop, and it is the young plate, not so long after its birth, that starts to subduct toward the old plate. The Mesozoic Pacific Plate cannot easily bend, under the joint horizontal compression and vertical gravity pull, even with a pre-existing weak zone in place and with a large age offset across the plate boundary. The bending of the Caroline Plate near the northern end of the Mussau Trench started only after a long-time span of trench migration, and/or after a prolonged transition from initial compression to trench development. Highly contrasting trench deformation and sedimentary accretion between two parallel seismic sections support an evident migration of underthrusting or significant longitudinal heterogeneity along the trench. The swift transition from underthrusting to non-thrusting can be explained by a counter-clockwise rotation of the Caroline Plate. That miniature accretionary wedges develop even before the subduction initiates imply strong compression and uplifting before the underthrusting can kick-start. Rotation of the Caroline Plate have been halted as the Mussau Trench is seismically rather quiet and the Lyra Trough to the east shows relaxational extension.

关键词： Mussau Trench Subduction initiation Seismic reflection Caroline Plate

同方期刊数据库

AsyCo: an asymmetric dual-task co-training model for partial-label learning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2025年

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning (PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词：

A New Encryption Mechanism Supporting the Update of Encrypted Data for Secure and Efficient Collaboration in the Cloud Environment

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 813-834页

作者： Chanhyeong Cho Byeori Kim Haehyun Cho Taek-Young Youn Department of Cyber Security Dankook UniversityYongin16890Republic of Korea Department of software Soongsil UniversitySeoul07027Republic of Korea

With the rise of remote collaboration,the demand for advanced storage and collaboration tools has rapidly ***,traditional collaboration tools primarily rely on access control,leaving data stored on cloud servers vulnerable due to insufficient *** paper introduces a novel mechanism that encrypts data in‘bundle’units,designed to meet the dual requirements of efficiency and security for frequently updated collaborative *** bundle includes updated information,allowing only the updated portions to be reencrypted when changes *** encryption method proposed in this paper addresses the inefficiencies of traditional encryption modes,such as Cipher Block Chaining(CBC)and Counter(CTR),which require decrypting and re-encrypting the entire dataset whenever updates *** proposed method leverages update-specific information embedded within data bundles and metadata that maps the relationship between these bundles and the plaintext *** utilizing this information,the method accurately identifies the modified portions and applies algorithms to selectively re-encrypt only those *** approach significantly enhances the efficiency of data updates while maintaining high performance,particularly in large-scale data *** validate this approach,we conducted experiments measuring execution time as both the size of the modified data and the total dataset size *** show that the proposed method significantly outperforms CBC and CTR modes in execution speed,with greater performance gains as data size ***,our security evaluation confirms that this method provides robust protection against both passive and active attacks.

关键词： Cloud collaboration mode of operation data update efficiency

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho School of Computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and software Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the School of Biomedical Engineering of Southern Medical University(SMU-dataset),and The National institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

A Differential Evolution Flower Pollination Algorithm with Dynamic Switch Probability

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第4期28卷 737-747页

作者： LIU Jingsen LIU Li LI Yu institute of intelligent Network system Henan University College of software Henan University institute of Management Science and Engineering Henan University

For the shortcomings of the basic flower pollination algorithm, this paper proposes a differential evolution flower pollination algorithm with dynamic switch probability based on the Weibull *** new algorithm improved the convergence rate and precision. The switch probability is improved by Weibull distribution function combined with the number of iterations. It can balance the relationship between the global pollination and the local pollination to improve the overall optimization performance of the *** mutation operator is merged into the global pollination process to increase diversity of the population,enhance the ability of the algorithm’s global search and avoid premature convergence. In the process of local pollination, directed mutation and crossover operation of the differential evolution are incorporated, it makes the individual flower position update with the memory function, which can choose the direction of variation reasonably. The use of cross-operation can avoid new solutions crossing the boundary. Convergence rate is improved and the algorithm can approach the global optimal solution continuously. Theoretical analysis proved the convergence and time complexity of the improved algorithm. The simulation results based on the function optimization problem show that the improved algorithm has better performance of optimization, faster convergence speed and higher convergence accuracy.

关键词： Flower pollination algorithm Dynamic switch probability Random mutation operator Differential evolution Optimization accuracy Convergence rate

Multi-Scale Dilated Convolution Network for SPECT-MPI Cardiovascular Disease Classification with Adaptive Denoising and Attenuation Correction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 299-327页

作者： A.Robert Singh Suganya Athisayamani Gyanendra Prasad Joshi Bhanu Shrestha Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia School of Computing Sastra Deemed to be UniversityThanjavur613401Tamil NaduIndia Department of Artificial Intelligence&software Kangwon National UniversitySamcheok25913Republic of Korea Department of Information Convergence System Graduate School of Smart ConvergenceKwangwoon UniversitySeoul01897Republic of Korea

Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image *** denoising is done by a U-Net architecture that ensures effective image *** correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of ***,a novel multi-scale diluted convolution(MSDC)network is *** merges the features extracted in different scales and makes the model learn the features more *** scales of filters with size 3×3 are used to extract *** three steps are compared with state-of-the-art *** proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of *** proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.

关键词： SPECT-MPI CAD MSDC denoising attenuation correction classification

Function Projective Lag Synchronization of Chaotic Systems with Certain Parameters via Adaptive-impulsive Control

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2019年第2期16卷 238-247页

作者： Xiu-Li Chai Zhi-Hua Gan institute of Image Processing and Pattern Recognition Henan University institute of intelligent Network System School of SoftwareHenan University

A new method is presented to study the function projective lag synchronization(FPLS) of chaotic systems via adaptive-impulsive control. To achieve synchronization, suitable nonlinear adaptive-impulsive controllers are designed. Based on the Lyapunov stability theory and the impulsive control technology, some effective sufficient conditions are derived to ensure the drive system and the response system can be rapidly lag synchronized up to the given scaling function matrix. Numerical simulations are presented to verify the effectiveness and the feasibility of the analytical results.

关键词： Function projective lag synchronization (FPLS) adaptive-impulsive chaotic systems numerical simulation Lyapunov stability theory

维普期刊数据库

A buffer overflow detection and defense method based on RiSC-V instruction set extension

在线全文

学校读者我要写书评

暂无评论

Cybersecurity 2024年第2期7卷 28-43页

作者： Chang Liu Yan-Jun Wu Jing-Zheng Wu Chen Zhao intelligent software Research Center Institute of SoftwareChinese Academy of SciencesBejingChina University of Chinese Academy of Sciences BeijingChina State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijingChina

Buffer overflow poses a serious threat to the memory security of modern operating *** overwrites the con-tents of other memory areas by breaking through the buffer capacity limit,destroys the system execution environ-ment,and provides implementation space for various system attacks such as program control flow *** makes it a wide range of harms.A variety of security technologies have been proposed to deal with system security problems including buffer *** example,No eXecute(NX for short)is a memory management technology commonly used in Harvard *** can refuse the execution of code which residing in a specific memory,and can effectively suppress the abnormal impact of buffer overflow on control ***,in recent years,it has also been used in the field of system security,deriving a series of solutions based on NX technology,such as ExecShield,DEP,StackGuard,***,these security solutions often rely too much on the processor archi-tecture so that the protection coverage is insufficient and the accuracy is *** in the emerging system architecture field represented by RiSC-V,there is still a lack of effective solutions for buffer overflow *** the continuous rapid development of the system architecture,it is urgent to develop defense methods that are applicable to different system application environments and oriented to all executable memory spaces to meet the needs of system security ***,we propose BOP,A new system memory security design method based on RISC-V extended instructions,to build a RISC-V buffer overflow detection and defense system and deal with the buffer overflow threat in *** to this method,NX technology can be combined with program control flow analysis,and Nx bit mechanism can be used to manage the executability of memory space,so as to achieve a more granular detection and defense of buffer overflow attacks that may occur in RISC-V system

关键词： RISc-V Operating system security Buffer overflow Control flow hijacking Nx bit Xibop