检索结果-内蒙古大学图书馆

CloneRipples: predicting change propagation between code clone instances by graph-based deep learning

EMPIRICAL SOFTWARE ENGINEERING 2025年第1期30卷 1-31页

作者： Wu, Yijian Chen, Yuan Peng, Xin Hu, Bin Wang, Xiaochen Fu, Baiqiang Zhao, Wenyun Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China

Code clones are recognized as a code smell that may require additional effort for simultaneous changes of multiple clone instances during software maintenance. To alleviate quality threats caused by inconsistent changes in clone instances, it is essential to accurately and efficiently make the decisions of change propagation between code clone instances. Our exploratory study has revealed that a clone class can have both propagation-required changes and propagation-free changes and thus fine-grained change propagation decisions are required. Based on the findings, we propose a graph-based deep learning approach to predict the change propagation requirements of clone instances. We design a deep learning model that employs a Relational Graph Convolutional Network (R-GCN) to predict the clone change propagation requirement. In order to evaluate our approach, we construct a dataset that includes 24,672 pairs of matched changes and 38,041 non-matched changes based on 51 open-source Java projects. Experiment results show that the approach achieves high precision (83.1%), recall (81.2%), and F1-score (82.1%). We implemented an IntelliJ IDEA tool called CloneRipples to assist developers to decide the necessity of change propagation between code clone instances seamlessly in development environment. Manual inspection identified the chances for purifying the dataset by rectifying the data labels of non-matched changes. Extended experiments for various data purification strategies reveal feasible ways to improve the prediction effectiveness and generality.

关键词： Code clone Change propagation Consistent changes Clone dataset

来源：评论

学校读者我要写书评

暂无评论

LGAT: A novel model for multivariate time series anomaly detection with improved anomaly transformer and learning graph structures

引用

NEUROCOMPUTING 2025年 617卷

作者： Wen, Mi Chen, Zhehui Xiong, Yun Zhang, Yichuan Shanghai Univ Elect Power Coll Comp Sci & Technol Shanghai 201306 Peoples R China Fudan Univ Sch Comp Sci Shanghai Key Lab Data Sci Shanghai Peoples R China

Time series anomaly detection involves identifying data points in continuously collected datasets that deviate from normal patterns. Given that real-world systems often consist of multiple variables, detecting anomalies in multivariate datasets has become a key focus of current research. This challenge has wide-ranging applications across various industries for system maintenance, such as in water treatment and distribution networks, transportation, and autonomous vehicles, thus driving active research in the field of time series anomaly detection. However, traditional methods primarily address this issue by predicting and reconstructing input time steps, but they still suffer from problems of overgeneralization and inconsistency in providing high performance for reasoning about complex dynamics. In response, we propose a novel unsupervised model called LGAT, which can automatically learn graph structures and leverage an enhanced Anomaly Transformer architecture to capture temporal dependencies. Moreover, the model features anew encoder- decoder architecture designed to enhance context extraction capabilities. In particular, the model calculates anomaly scores for multivariate time series anomaly detection by combining the reconstruction of input time series with the model's computed prior associations and sequential correlations. This model captures inter- variable relationships and exhibit stronger context extraction abilities, making it more sensitive to anomaly detection. Extensive experiments on six common anomaly detection benchmarks further demonstrate the superiority of our approach over other state-of-the-art methods, with an improvement of approximately 1.2% across various metrics.

关键词： Multivariate times series Anomaly detection Graph neural networks Transformer

来源：评论

学校读者我要写书评

暂无评论

Research on Time-Sensitive Service Transmission Routing and Scheduling Strategies Based on Optical Interconnect Low Earth Orbit Mega-Constellations

引用

APPLIED sciENCES-BASEL 2025年第7期15卷

作者： Cao, Bingyao Fan, Xiwen Hong, Yiming Zhao, Qianqian Shanghai Univ Shanghai Inst Adv Commun & Data Sci Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200072 Peoples R China

The development of low-orbit satellite communication networks marks the beginning of a new era in global communication. However, in the context of large-scale LEO satellite communication scenarios, the traditional adjacent connection transmission method limits the advantages of low latency in optical communication. Multi-hop transmission increases the number of hops and propagation distance, thereby affecting time-sensitive business transmissions. Therefore, based on the design of optical interconnect parallel subnetworks, this paper proposes a scheduling strategy for time-sensitive business transmissions between LEO satellites. Firstly, this strategy integrates the gate control scheduling mechanism from Time-Sensitive Networking (TSN) transmission in the interconnect parallel subnetwork scenario. Secondly, considering issues like queuing after subnetwork division, excessive burden, and algorithm complexity, mathematical problem abstraction modeling is applied to subsequent route scheduling, with reinforcement learning used to solve the problem. Through simulation experiments, it has been observed that compared to SPF (Shortest Path First) and ELB (Equal Load Balance), this approach can effectively enhance the control capability of end-to-end latency for TSN services in long-distance transmissions within Low Earth Orbit mega-constellations. The integration of reinforcement learning decision algorithms also reduces the complexity compared to traditional constraint-solving algorithms, ensuring a certain level of practicality. Overall, this solution can enhance the communication efficiency and performance of time-sensitive services between satellite constellations. By integrating time-sensitive network transmission technologies into optically interconnected subnets, further exploration and realization of low-latency and controllable latency satellite communication networks can be pursued.

关键词： Low Earth Orbit constellation parallel subnetwork laser communication time-sensitive network gate scheduling transmission reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Network performance evaluation criterion model based on large connections for low latency in industrial 50G-PON network

引用

OPTICAL FIBER TECHNOLOGY 2025年 90卷

作者： Cao, Bingyao Zhao, Qianqian Hong, Yiming Fan, Xiwen Shanghai Univ Shanghai Inst Adv Commun & Data Sci Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200072 Peoples R China

In this paper, a new evaluation criterion model for user and service satisfaction is proposed. The application of 50G-PON networks in Industry 4.0 is explored to enhance user experience and network efficiency by integrating 50G-PON in Industry 4.0. Facing the demand for high-bandwidth and low-latency networks for robotic assembly, laser cutting, sensors, and other devices in production lines. We propose the MF-DWBA (Multi Factor Dynamic Wavelength Bandwidth Allocation) algorithm, which aims to enhance user experience and network efficiency in industrial environments. Then, a user satisfaction evaluation criterion based on reinforcement learning is constructed through a mathematical model, and the satisfaction value calculated by this model can accurately identify network performance bottlenecks and further enhance the resource scheduling efficiency in the production environment. In addition, a (4,M) service satisfaction evaluation criterion based on utility function is proposed, which makes the satisfaction assessment of different service types in industrial scenarios more comprehensive and can reflect the service priority between critical and non-critical devices. Finally, the calculated satisfaction values are compared with the actual user feedback, and the simulation results prove the accuracy and effectiveness of the proposed satisfaction model. This study provides an important reference and guidance for the optimization of large-connection 50G-PON networks, and also provides a feasible path to solve the problem of network performance optimization in the smart shop environment. The combination of this satisfaction model and the MF-DWBA algorithm not only meets the practical needs of smart factories, but also brings important inspirations to other industrial manufacturing entities for network applications in Industry 4.0.

关键词： 5OG-PON Industry 4.0 Evaluation criterion 4 evaluation criterion matrix (4 M) Large connections

来源：评论

学校读者我要写书评

暂无评论

A Critical-Set-Based Multi-Bit Successive Cancellation List Decoder for Polar Codes: Algorithm and Implementation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年第3期72卷 1472-1485页

作者： Cao, Shan Chen, Shan Jiang, Limin Jiang, Zhiyuan Shanghai Univ Shanghai Inst Adv Commun & Data Sci Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200444 Peoples R China Shanghai Univ Shanghai Inst Adv Commun & Data Sci Joint Int Res Lab Specialty Fiber Opt & Adv Commun Shanghai 200444 Peoples R China

With the evolution of wireless communication systems, there is a growing demand for high reliability and low latency in channel coding, particularly in 5G and beyond wireless systems used in applications such as autonomous driving and remote medical services. For the decoding of polar codes, the multi-bit successive cancellation list (MSCL) decoding technique was recently introduced to decrease the decoding latency by decoding several short inner codes in parallel, which preserves high reliability compared to the conventional successive cancellation list (SCL) decoding. However, as parallelism increases, the complexity of the decoding path sorting also increases significantly, which makes it resource-intensive for hardware implementation. To address this issue, this paper proposes a configurable critical-set-based multi-bit successive cancellation list (CS-MSCL) decoding algorithm, which first introduces critical sets to the MSCL decoding for the optimization of path pruning. Subsequently, an enhanced CS-MSCL algorithm is introduced for large list-size MSCL decoding, which can boost the error correction performance. Then, an area-efficient decoding architecture is introduced, which supports the cyclic redundancy check (CRC) and the CS-MSCL decoding compatible with the 5G standard. The proposed decoder is implemented in SMIC 40 nm CMOS technology with a parallelism degree of 8, which has a peak area efficiency of 4.64 Gbps/mm(2 )for list size 4 and 2.01 Gbps/mm(2) for list size 8. Compared to state-of-the-art SCL-based decoders, the normalized area efficiency is improved by 7.16% and 17.54% for list sizes 4 and 8, respectively.

关键词： Polar codes decoder decoder successive cancellation list decoding 5G 5G hardware implementation hardware implementation

来源：评论

学校读者我要写书评

暂无评论

An improved fast approximation to two-sided variable-order space-fractional diffusion equation and its preconditioning

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2025年 465卷

作者： Guo, Xiaofeng Pan, Jianyu Fudan Univ Sch Data Sci Shanghai Key Lab Con orary Appl Math Shanghai 200433 Peoples R China East China Normal Univ Sch Math Sci Key Lab MEA Minist Educ Shanghai 200241 Peoples R China East China Normal Univ Shanghai Key Lab PMMP Shanghai 200241 Peoples R China

For two-sided variable-order space-fractional diffusion equation, due to the impact of variable fractional order, the discretized stiffness matrix no longer holds Toeplitz-like structure, which brings great challenge to develop efficient solvers. To overcome the difficulty, a fast approximation scheme was proposed in Jia et al. (2021). The main aim of this paper is to propose an improved fast scheme by approximating the stiffness matrix via Chebyshev interpolation technique. Moreover, a block diagonal approximate inverse preconditioner is developed for the proposed scheme to accelerate the convergence of Krylov subspace iteration method. Both theoretical and numerical results demonstrate that the new fast scheme can attain desired solution accuracy with much fewer involved Toeplitz-like approximation terms and hence is evidently more efficient. The effectiveness of the developed preconditioner is also validated.

关键词： equation Chebyshev interpolation Fast approximation Toeplitz-like Preconditioning

来源：评论

学校读者我要写书评

暂无评论

A Gradual-Width High-Q Self-Resonant Coil Based on Coplanar Waveguide

引用

IEEE MICROWAVE AND WIRELESS TECHNOLOGY LETTERS 2025年第2期35卷 165-168页

作者： Yi, Zixuan Yang, Kaiyu Yang, Xue-Xia Li, Meiling Zeng, Dan Shanghai Univ Shanghai Inst Adv Commun & Data Sci Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200444 Peoples R China

Self-resonant (SR) coils with high quality factor Q play a critical role for wireless energy transmission systems. In this article, a new single-layered spiral SR coil is introduced based on coplanar waveguide, which consists of two gradual-width spiral copper traces. Compared with traditional equal-width coils, the proposed coil increases the conductive area at specific location. This design significantly reduces loss during the current transmission, further improving Q of the coil. The simulation and experimental tests have confirmed that the proposed coil exhibits an outstanding Q of 436 at a resonant frequency of 13.58 MHz, which is the highest Q of the same frequency and size at present, and indicates a good application prospect for future inductive power transfer (IPT) transmission system.

关键词： Loss parasitic capacitance self-resonant (SR) coil single-layer spiral coil Loss parasitic capacitance self-resonant (SR) coil single-layer spiral coil

来源：评论

学校读者我要写书评

暂无评论

DSF2-NAS: Dual-Stage Feature Fusion via Network Architecture Search for Classification of Multimodal Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 7207-7220页

作者： Feng, Shiyang Li, Zhaowei Zhang, Bo Chen, Tao Wang, Bin Fudan Univ Key Lab Informat Sci Electromagnet Waves MoE Shanghai 200433 Peoples R China Shanghai Artificial Intelligence Lab Multimodal Fdn Data Grp Shanghai 200232 Peoples R China

Recently, the classification of multimodal remote sensing images (RSIs) has garnered significant attention due to its ability to provide rich information for various scenes on Earth. Compared to traditional feature fusion methods used for the classification of multimodal RSIs, neural architecture search (NAS) is capable of identifying the optimal network structure for multimodal RSIs and downstream tasks. However, due to the diverse spatial resolutions, complex channel dimensions, and drastic foreground scale variations of multimodal RSIs, challenges arise when employing NAS methods for precise classification: 1) Due to the complementary and redundant nature between different modalities in RSIs, determining the features within each modality for fusion becomes quite challenging;2) the design of fusion operators does not take into account the spatial positions and channel relationships between different modalities of RSIs, making it difficult for the fused features to match downstream tasks. To address these issues, we propose a dual-stage feature fusion framework based on NAS, termed DSF2-NAS, for the classification of multimodal RSIs. It primarily consists of two components: the feature candidate search (FCS) module and the fusion operator search (FOS) module, which execute sequentially. In the FCS module, a feature distance-based regularization approach is proposed to ensure fusion using multimodal features with the highest complementarity. Meanwhile, in the FOS module, a series of fusion operators are designed, which are based on spatial positions, channel relationships, and self-attention mechanisms, aiming to better integrate multimodal features with complex spatial and channel information. The proposed method has been evaluated on various datasets of multimodal RSIs, and experimental results consistently show that this method achieves state-of-the-art performance across multiple classification metrics.

关键词： Fuses Transformers Feature extraction Computer architecture Accuracy Spatial resolution Neural architecture search Laser radar Synthetic aperture radar Sensors Classification multimodal neural architecture search (NAS) remote sensing images (RSIs)

来源：评论

学校读者我要写书评

暂无评论

IPFLSTM: Enhancing physics-informed neural networks with LSTM and Informer for efficient long-term prediction of dynamic multiphysics fields

引用

COMPUTATIONAL MATERIALS sciENCE 2025年 253卷

作者： Bai, Chen Qian, Quan Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Univ Mat Genome Inst Ctr Mat Informat & Data Sci Shanghai 200444 Peoples R China Shanghai Univ Key Lab Silicate Cultural Rel Conservat Minist Educ Shanghai Peoples R China Shanghai Univ Shanghai Inst Adv Commun & Data Sci Shanghai 200444 Peoples R China

Multi-physics coupling, such as in metal solidification, involves complex interactions among physical fields like heat transfer, fluid flow, and phase change. Traditional numerical simulation methods, though accurate, are computationally expensive and struggle with long-term predictions due to the fine resolution required to capture these coupled phenomena. Furthermore, emerging machine learning methods that represent these phenomena for simulation tasks are not subject to complex physical constraints, and are only confined to fitting their numerical distributions. To address these issues, we introduce an enhanced physics-informed neural network framework. First, we employ LSTM as a spatio-temporal coordinates projection layer to transform actual physical positional relationships into positional encodings within the Informer framework. Second, we incorporate a physics-informed function for network parameters adjustment, thereby leveraging the physical constrain and the Informer model's long-term dynamic prediction capability for final predictions. Experiments on the Cu-1wt.%Ag solidification process show that IPFLSTM reduces prediction L2 errors in velocity (u, v) and temperature fields by 56.8%, 51.74%, and 51.49% relative to PINNsFormer while cutting training time by 23.71%, outperforming traditional PINNs and their variants. This model offers a promising approach for simulating complex dynamic physical fields, addressing challenging boundary conditions, and extending to multi-scale, coupled systems in engineering applications.

关键词： Physics-informed neural networks Informer Metal solidification Sparse attention mechanism Multi-field simulation

来源：评论

学校读者我要写书评

暂无评论

Mitigating interference of microservices with a scoring mechanism in large-scale clusters

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-31页

作者： Yang, Dingyu Zheng, Kangpeng Qian, Shiyou Hua, Qin Zhang, Kaixuan Cao, Jian Xue, Guangtao Zhejiang Univ State Key Lab Blockchain & Data Secur Zheda Rd 18 Hangzhou 310007 Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn Dongchuan Rd 800 Shanghai 200240 Peoples R China Shanghai Key Lab Trusted Data Circulat & Governanc Dongchuan Rd 800 Shanghai 200240 Peoples R China

Co-locating latency-critical services (LCSs) and best-effort jobs (BEJs) constitute the principal approach for enhancing resource utilization in production clusters. Nevertheless, the co-location practice hurts the performance of LCSs due to resource competition, even when employing isolation technology. Through an extensive analysis of voluminous real trace data derived from two production clusters, we observe that BEJs typically exhibit periodic execution patterns and serve as the primary sources of interference to LCSs. Furthermore, despite occupying the same level of resource consumption, the diverse compositions of BEJs can result in varying degrees of interference on LCSs. Subsequently, we propose PISM, a proactive Performance Interference Scoring and Mitigating framework for LCSs through the optimization of BEJ scheduling. Firstly, PISM adopts a data-driven approach to establish a characterization and classification methodology for BEJs. Secondly, PISM models the relationship between the composition of BEJs on servers and the response time (RT) of LCSs. Thirdly, PISM establishes an interference scoring mechanism in terms of RT, which serves as the foundation for BEJ scheduling. We assess the effectiveness of PISM on a small-scale cluster and through extensive data-driven simulations. The experiment results demonstrate that PISM can reduce cluster interference by up to 41.5%, and improve the throughput of long-tail LCSs by 76.4%.

关键词： Microservices Cloud computing Scheduling Interference

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：