检索结果-内蒙古大学图书馆

IEEE International Conference on Information Communication and Signal Processing (ICICSP)

作者： Jiayi Xu Wendong Huang Yang Zhao Jihong Pei Xuan Yang Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University College of Electronics and Information Engineering Shenzhen China Shenzhen University College of Electronics and Information Engineering Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

In contemporary society, the analysis and utilisation of big data is of paramount importance. However, traditional feature extraction methods frequently encounter the curse of dimensionality when dealing with high-dimensional data, which is no longer able to adapt to the current needs of practical applications. The manifold learning method, which is capable of effectively extracting features of high-dimensional data, ne-cessitates the resolution of the problem of how to choose an appropriate local neighbourhood. Consequently, this paper proposes an Adaptive neighborhood Locality Preserving Projection (LAPP) based on the Locality Preserving Projection (LPP). TThis method combines two neighborhood selection method. To achieve an adaptive radius selection for local neighborhoods of sample points based on the distance characteristics between sample points. The LAPP proposed in this paper markedly reduces the dimensionality reduction and enhances the computational efficiency while maintaining a certain degree of accuracy.

关键词： Manifolds Accuracy High dimensional data Signal processing Big Data Feature extraction Computational efficiency Manifold learning Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing Low-Latency and High-Reliability Data Forwarding for In-Vehicle Time-Sensitive Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Sun, Haitong Zhang, Haijun Guan, Wanqing Liu, Xiangnan Ma, Hui Leung, Victor C.M. Hebei Key Laboratory of Space-Air-Ground Intelligent Communication China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing100083 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden Department of Computer Science and Software Engineering Shenzhen University Shenzhen518061 China

To satisfy the low delay, low jitter, and high success rate requirements for in-vehicle networks, IEEE 802.1 Task Group proposed Time-Sensitive Networking (TSN), which has aroused increasing attention in managing time-critical services in networks. This paper resolves the following issue: how to minimize the worst-case response time (WCRT) of frame forwarding in TSN under no-wait scenarios to guarantee low-latency transmission, stability, and high success rate for in-vehicle TSN networks? Currently, some work resolves this problem by leveraging integer linear programming, and others apply heuristic methods to avoid the time complexity problem, but the success rate is affected since they are prone to get trapped in local optima. To reach a balance between time-complexity and success rate, a scheme named Frame Dynamic Priority Scheduling Mechanism (FDPSM) is proposed, where the frame dynamic priority levels are set up and frames are scheduled accordingly. The target is to maximize the success rate and minimize the WCRT for in-vehicle networks. We evaluate the proposed mechanism from aspects such as traffic forwarding time, size of windows, number of hops, and the network load, together with success rate and the simulation results demonstrate the advantages of the FDPSM for in-vehicle TSN networks. © 2025 IEEE. All rights reserved,

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning

arXiv

引用

arXiv 2025年

作者： Tao, Zelin Deng, Hao Liu, Mingqing Zhang, Lijun Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai201804 China College of Electronic and Information Engineering Tongji University Shanghai201804 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai201804 China

Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training. However, these methods face challenges of prediction bias, stemming from deviations in parameter update directions during task transitions. This paper identifies parameter variation imbalance as a critical factor contributing to prediction bias in ER-based OCL. Specifically, using the proposed parameter variation evaluation method, we highlight two types of imbalance: correlation-induced imbalance, where certain parameters are disproportionately updated across tasks, and layer-wise imbalance, where output layer parameters update faster than those in preceding layers. To mitigate the above imbalances, we propose the Parameter Variation Balancing Framework (PVBF), which incorporates: 1) a novel method to compute parameter correlations with previous tasks based on parameter variations, 2) an encourage-and-consolidate (E&C) method utilizing parameter correlations to perform gradient adjustments across all parameters during training, 3) a dual-layer copy weights with reinit (D-CWR) strategy to slowly update output layer parameters for frequently occuring sample categories. Experiments on short and long task sequences demonstrate that PVBF significantly reduces prediction bias and improves OCL performance, achieving up to 47% higher accuracy compared to existing ER-based methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery

arXiv

引用

arXiv 2024年

作者： Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones. Recently, Knowledge Distillation (KD) has shown promising potential for maintaining satisfactory accuracy while significantly compressing models in general object detection. Considering the advantages of KD, this paper presents the first attempt to adapt it to object detection on drone imagery and addresses two intrinsic issues: (1) low foreground-background ratio and (2) small instances and complex backgrounds, which lead to inadequate training, resulting insufficient distillation. Therefore, we propose a task-wise Lightweight Mutual Lifting (Light-ML) module with a Centerness-based Instance-aware Distillation (CID) strategy. The Light-ML module mutually harmonizes the classification and localization branches by channel shuffling and convolution, integrating teacher supervision across different tasks during back-propagation, thus facilitating training the student model. The CID strategy extracts valuable regions surrounding instances through the centerness of proposals, enhancing distillation efficacy. Experiments on the VisDrone, UAVDT, and COCO benchmarks demonstrate that the proposed approach promotes the accuracies of existing state-ofthe- art KD methods with comparable computational requirements. Codes will be available upon acceptance. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Concrete Structural Crack Damage Classification Using Nonlinear Dimension Reduction and Broad Learning System

Concrete Structural Crack Damage Classification Using Nonlin...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Bingshu Wang Jia Lin Xiaodong Zhuang Guanghui Zhang C.L. Philip Chen School of Software Northwestern Polytechnical University Xi'an China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China School of Computer Science and Technology Shandong University Qingdao China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy.

关键词： Training Learning systems Dimensionality reduction Accuracy Artificial neural networks Feature extraction Road safety Cybernetics Principal component analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

A Study of Data Augmentation for Imbalance Problem in Network Traffic

A Study of Data Augmentation for Imbalance Problem in Networ...

引用

Blockchain Technology and Information Security (ICBCTIS), International Conference on

作者： Xu Wang Shimin Sun Li Han School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong University Tianjin China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China

The complexity and diversity of smart grid systems increase the likelihood of anomalies in communications between devices in the system, and how these anomalies are detected is critical to the security of the grid system. However, the distribution of traffic types in the grid is often highly unbalanced, with the total amount of normal traffic data often far outweighing the anomalous data. This imbalance compromises the effectiveness of the detection model and poses a significant threat to the overall security of the grid. This paper improves on traditional conditional generation adversarial neural networks and designs a new approach to overcome this obstacle and enhance the security of smart grid systems. In the generator part, the spatial features of the data are captured by convolutional neural networks, and the temporal features of the data are captured by gated recurrent units. By integrating these two components into the generative network, we can generate synthetic data with both temporal and spatial features, thus enhancing the minority class samples. By incorporating the augmented minority data into the training process, the proposed approach enables the detection model to understand the distribution of features of the minority anomaly samples more accurately. This improved learning accuracy translates into improved model performance, resulting in higher detection rates for previously under-represented anomalies. In addition, our approach effectively addresses the inherent bias towards traffic types with higher flows typically observed in asymmetric datasets, thus providing a more equitable and comprehensive security solution for smart grid systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Source Code Summarization in the Era of Large Language Models

Source Code Summarization in the Era of Large Language Model...

引用

International Conference on software engineering (ICSE)

作者： Weisong Sun Yun Miao Yuekang Li Hongyu Zhang Chunrong Fang Yi Liu Gelei Deng Yang Liu Zhenyu Chen College of Computing and Data Science Nanyang Technological University Singapore Singapore State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering University of New South Wales Sidney Australia School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798331505691

ISBN: (纸本)9798331505707

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of coderelated tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLMbased code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs' model settings (including top_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs' abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types (e.g., procedural and object-oriented programming languages). Finally, we unexpectedly find that CodeLlamaInstruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code design rationale and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of LLMs.

关键词： computer languages Codes Systematics Source coding Large language models Object oriented modeling software Prompt engineering Object oriented programming software engineering

来源：评论

学校读者我要写书评

暂无评论

Aerial-terrestrial Image Feature Matching: An Evaluation of Recent Deep Learning Methods

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Wang, Hui Yu, Jiangxue Jiang, San Zhang, Dejin Li, Qingquan China University of Geosciences School of Computer Science Wuhan430074 China Shenzhen University Guangdong Key Laboratory of Urban Informatics Shenzhen518060 China Ministry of Education Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Wuhan430074 China Shenzhen University MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area Shenzhen518060 China

3D reconstruction of complex urban areas is becoming increasingly important in various applications. To achieve precise and complete 3D reconstruction, current approaches aim to combine aerial and terrestrial images. The main challenge is achieving reliable feature matching of aerial and terrestrial images under large viewing angles and varying scene illuminations. Traditional hand-crafted methods experience a significant decline in matching performance. In this context, deep learning-based feature matching methods have developed rapidly and gained extensive attention. However, their performance in handling challenging large-angle aerial-terrestrial datasets still needs to be evaluated. To assess their performance for aerial-terrestrial images, this study has reviewed and evaluated four types of recent deep learning-based feature matching networks and selected four sets of aerial-terrestrial datasets for experimental tests. Extensive experiments and evaluations have been conducted in terms of feature matching and image orientation based on SfM (Structure from Motion). The results demonstrate that GNN (Graph Neural Networks)-based methods and detectorfree methods exhibit significant advantages in feature matching of aerial-terrestrial datasets, which can generate effective and correct matches for aerial-terrestrial images with large scale and viewpoint differences. In particular, the combination of SuperPoint and LightGlue achieves the best performance, which can generate approximately ten times the number of aerial-terrestrial feature matches when compared with SIFT. In addition, all images can be registered in the SfM reconstruction using its matching results. However, the precision of deep learning-based methods is still inferior to the classical hand-crafted method in SfM reconstruction. Thus, there is still significant room for improvement to enhance their performance further. © 2008-2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Human-in-the-loop online just-in-time software defect prediction

arXiv

引用

arXiv 2023年

作者： Liu, Xutong Zhou, Yufei Tang, Yutian Qian, Junyan Zhou, Yuming The State Key Laboratory for Novel Software Technology Nanjing University China The School of Computer Science and Engineering School of Software Guanxi Normal University China The School of Computing Science University of Glasgow United Kingdom

Online Just-In-Time software Defect Prediction (O-JIT-SDP) uses an online model to predict whether a new software change will introduce a bug or not. However, existing studies neglect the interaction of software Quality Assurance (SQA) staff with the model, which may miss the opportunity to improve the prediction accuracy through the feedback from SQA staff. To tackle this problem, we propose Human-In-The-Loop (HITL) O-JIT-SDP that integrates feedback from SQA staff to enhance the prediction process. Furthermore, we introduce a performance evaluation framework that utilizes a k-fold distributed bootstrap method along with the Wilcoxon signed-rank test. This framework facilitates thorough pairwise comparisons of alternative classification algorithms using a prequential evaluation approach. Our proposal enables continuous statistical testing throughout the prequential process, empowering developers to make real-time decisions based on robust statistical evidence. Through experimentation across 10 GitHub projects, we demonstrate that our evaluation framework enhances the credibility of model evaluation, and the incorporation of HITL feedback elevates the prediction performance of online JIT-SDP models. These advancements hold the potential to significantly enhance the value of O-JIT-SDP for industrial applications. © 2023, CC BY-NC-ND.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Prepartition: Load Balancing Approach for Virtual Machine Reservations in a Cloud Data Center

引用

Journal of computer Science & Technology 2023年第4期38卷 773-792页

作者：田文洪徐敏贤周光耀吴逵须成忠 Rajkumar Buyya School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu 610054China Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Department of Computer Science University of VictoriaVictoriaBCV8W 3P6Canada State Key Laboratory of Internet of Things for Smart City University of MacaoMacao 999078China School of Computing and Information Systems University of MelbourneMelbourne 3010Australia

Load balancing is vital for the efficient and long-term operation of cloud data *** virtualization,post(reactive)migration of virtual machines(VMs)after allocation is the traditional way for load balancing and consoli***,it is not easy for reactive migration to obtain predefined load balance objectives and it may interrupt services and bring ***,we provide a new approach,called Prepartition,for load *** partitions a VM request into a few sub-requests sequentially with start time,end time and capacity demands,and treats each sub-request as a regular VM *** this way,it can proactively set a bound for each VM request on each physical machine and makes the scheduler get ready before VM migration to obtain the predefined load balancing goal,which supports the resource allocation in a fine-grained *** with real-world trace and synthetic data show that our proposed approach with offline version(PrepartitionOff)scheduling has 10%–20%better performance than the existing load balancing baselines under several metrics,including average utilization,imbalance degree,makespan and Capacity_*** also extend Prepartition to online load *** results show that our proposed approach also outperforms state-of-the-art online algorithms.

关键词： cloud computing physical machine(PM) virtual machine(VM) reservation load balancing Prepartition

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：