检索结果-内蒙古大学图书馆

FDSR-INT: A Flexible On-Demand In-Band Telemetry Approach for Aerial Computing Networks

IEEE Internet of Things Journal 2025年第13期12卷 23257-23274页

作者： Xu, Jinghan Xu, Xiaolong Zhao, Juan Gao, Honghao Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing The School of Computer Science Nanjing210023 China Jinling Institute of Technology School of Computer Science Nanjing211169 China Shanghai University School of Computer Engineering and Science Shanghai200444 China Gachon University College of Future Industry Gyeonggi-Do 461-701 Korea Republic of

In-band network telemetry (INT) is a new network measurement technique that provides real-time, fine-grained packet-level network measurements. However, standard INT lacks the flexibility to perform configurable on-demand network measurements. In this work, we propose a flexible on-demand network measurement mechanism (FDSR-INT) based on a dual bitmap by combining the programmability of segment routing based on IPv6 (SRv6) and the telemetry efficiency of the INT to achieve customizable network measurements. By designing the dual bitmap, the telemetry information of personalized probe nodes is supported, and the telemetry efficiency is improved. SRv6 is employed to direct measurement probe packets, ensuring coverage of a specified set of network targets. Its inherent programmability enables INT to conduct customized per-hop network measurements. The designed flexible INT field structure, which appends traceability information along with telemetry information, reduces the information traceability overhead in the control plane and improves the network compatibility of the mechanism. We solve the optimal probing path by solving a traveler problem in an auxiliary graph and design a greedy pathcutting algorithm to maximize the number of nodes for single packet probing while satisfying the packet length constraints to improve the success rate of the probing task. Finally, we implemented FDSR-INT using P4 and verified its performance experimentally in the constructed *** integrated simulation dynamic environment. FDSR-INT saves 30% of the data plane bandwidth and 54% of the data plane bandwidth on *** interfaces compared with SONM-SR-INT, etc. Furthermore, it has low control plane processing overhead and probe path transmission overhead. © 2014 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Core-Competitiveness in Partially Observable Networked Market 24

Core-Competitiveness in Partially Observable Networked Marke...

引用

33rd ACM Web Conference, WWW 2024

作者： Li, Bin Hao, Dong School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China

ISBN: (纸本)9798400701719

In auction theory, a core is a stable outcome where no subgroup of participants can achieve better results for themselves. Core-competitive auctions aim to generate revenue that is achievable in a core. They are particularly important because they not only generate optimized revenue for the seller, but also provide an efficient and stable environment for participants. We generalize the design of core-competitive auctions to encompass partially observable networked markets (PONM). Unlike traditional auctions, which often deal with scenarios of limited trading activity, our approach to core-competitive auctions for PONM captures the nature of real-world transaction markets, which is a large linking world for the economic entities and commodities circulate among the entities in the market. Our generalizing the auction market to PONM can much improve the liquidity of the auction, and is especially meaningful for the web economics. Specifically, we quantify the upper and lower bounds of the minimum core revenue in PONM, and further prove that there does not exist any truthful auction for PONM which is efficient and core-competitive. Governed by this impossible result, we identify the criteria that the allocation rule for PONM should meet. Based on these criteria, we propose a new class of auction mechanisms for PONM that is individually rational, incentive-compatible, and core-competitive. © 2024 ACM.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

CBIR: a novel identification approach for college students in need based on consumer behavior psychology theory

引用

Neural Computing and Applications 2025年第6期37卷 4663-4677页

作者： Liu, Xinze Liu, Shixi Hu, Xiaojing Zhang, Yudong Fang, Xianwen School of Computer and Information Engineering Chuzhou University Chuzhou239000 China School of Computer Science and Engineering Southeast University Nanjing210096 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

The accurate identification of students in need is crucial for governments and colleges to allocate resources more effectively and enhance social equity and educational fairness. Existing approaches to identifying students in need rely on manual operations that include manually extracting consumption behavior information, statistical consumption characteristics and principal component analysis. However, this issue may lead to low prediction accuracy and inefficiency in identifying students in need. We design a three-stage framework to accurately identify college students in need from the perspective of consumer behavior psychology. The consumption behavior information is first obtained from the student consumption records using the consumption behavior clustering approach. The consumption behavior matrix is then built by extracting consumption and spatiotemporal information in different periods. Finally, a novel consumption behavior identification ResNeSt (CBIR) model is proposed to identify college students in need accurately. The experimental results on real datasets show that the CBIR model has higher prediction accuracy than the baseline models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

Motion path planning method based on map reference points

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Yu, Wenbin Fan, Cheng Zhang, Chengjun Chen, Yadang Li, Yangsong Zhang, Yifan Yin, Na Cen, Xiaolin School of Software Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China Wuxi Institute of Technology Nanjing University of Information Science and Technology Jiangsu Wuxi214000 China Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China School of Computer Science Northeastern University Boston02101 United States Computer Science and Engineering The University of New South Wales SydneyNSW02101 Australia

In recent years, significant progress has been made in the development of the Rapidly-exploring Random Trees (RRT) algorithm, a probabilistic sampling-based search approach. This algorithm effectively addresses complex challenges in path planning within high-dimensional spaces characterized by intricate constraints. However, the RRT algorithm faces certain limitations, including sluggish computational performance in handling intricate calculations, susceptibility to becoming trapped in confined path regions, and difficulties in generating randomized paths across a given map. To overcome these issues, this study introduces a motion path planning method based on map reference points. Initially, the algorithm selects strategic map reference points, followed by the utilization of an enhanced RRT algorithm for fundamental path selection. Real-world scenario data is collected to empirically evaluate the algorithm’s performance. The outcomes of the experiments reveal that, within the same experimental setting, the proposed method outperforms conventional motion path planning algorithms by effectively circumventing obstacles. Furthermore, it substantially reduces the resource wastage caused by global random sampling in the RRT algorithm, leading to expedited path planning and improved pathfinding success rates. Additionally, the proposed approach enhances the RRT algorithm’s adaptability to some extent, particularly in negotiating narrow passages and intricate environments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Domain-Adaptive Large Language Model With Refinement Framework For IoT Cybersecurity 17

A Domain-Adaptive Large Language Model With Refinement Frame...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Che, Xun Zheng, Yu Zhu, Minhao Li, Qianmu Dong, Xu Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Nari Group Corporation Nanjing China Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing China

ISBN: (纸本)9798350351637

To address the increasingly complex security challenges in Internet-of-Things (IoT) environments, Large Language Models (LLMs) have demonstrated effectiveness in enhancing device and data security, as well as improving the security and reliability overall IoT system. However, general LLMs struggle to effectively handle IoT security data. Therefore, developing IoT security domain-specific LLMs based on IoT-specific corpus and terminologies has become a key focus for enhancing cybersecurity defense capabilities. These areas of focus can be broadly categorized into three main directions: training from scratch, retrieval-augmented prompting, and instruction fine-tuning. Training from scratch is discouraged in cybersecurity due to its high computational and data requirements, making effective model training and convergence difficult given the scarcity of cybersecurity data. Retrieval-augmented prompting may suffer from incomplete or conflicting information, impacting the accuracy and reliability of the model. Conversely, instruction fine-tuning allows for the usage of domain-specific task instructions to adjust the model, achieving effective domain adaptation on limited datasets. However, inadequate or inaccurate instructions may degrade the generalization ability and performance. For these shortcomings, we propose a novel and robust fine-tuning framework to refine the original corpus and output a refined corpus for high-quality domain adaptation. Furthermore, we introduce two auxiliary strategies in the training phase to enhance efficiency and accuracy. Finally, our framework is evaluated across multiple task scenarios and demonstrates the best performance on most of them, which proves the effectiveness and efficiency of the model presented in this work. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

supported by the National Natural science Foundation of China(Nos.62172051,61772085,and 61877005)and Jiangsu Agriculture science and technology Innovation Fund(***(18)3054).

引用

Tsinghua science and technology 2023年第1期28卷 82-92页

作者： Jinghui Zhang Yuchen Wang Tianyu Huang Fang Dong Wei Zhao Dian Shen School of Computer Science and Engineering Southeast UniversityNanjing 211189China Hefei Comprehensive National Science Center Hefei 231299China School of Computer Science and Technology Anhui University of TechnologyHefei 230026China Department of Computer Science&Engineering The Chinese University of Hong KongHong Kong 999077China

Numerous neural network(NN)applications are now being deployed to mobile *** applications usually have large amounts of calculation and data while requiring low inference latency,which poses challenges to the computing ability of mobile ***,devices’life and performance depend on ***,in many scenarios,such as industrial production and automotive systems,where the environmental temperatures are usually high,it is important to control devices’temperatures to maintain steady *** this paper,we propose a thermal-aware channel-wise heterogeneous NN inference *** contains two parts,the thermal-aware dynamic frequency(TADF)algorithm and the heterogeneous-processor single-layer workload distribution(HSWD)*** on a mobile device’s architecture characteristics and environmental temperature,TADF can adjust the appropriate running speed of the central processing unit and graphics processing unit,and then the workload of each layer in the NN model is distributed by HSWD in line with each processor’s running speed and the characteristics of the layers as well as heterogeneous *** experimental results,where representative NNs and mobile devices were used,show that the proposed method can considerably improve the speed of the on-device inference by 21%–43%over the traditional inference method.

关键词： neural network inference mobile device temperature adjustment channel-wise parallelization

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Gaussian Localization Distillation for Optical Information guided SAR Object Detection

Cross-modal Gaussian Localization Distillation for Optical I...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Chao Luo, Lei Fang, Wenxuan Yang, Jian School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350368741

Synthetic Aperture Radar (SAR) images contain a dense clutter of objects that can be better characterized using bounding boxes with angles. However, accurately detecting the angles of objects remains challenging due to the imaging mechanism of SAR. To address this issue, we propose a novel knowledge distillation method called cross-modal Gaussian Localization Distillation (GaLD). It aims to improve SAR object detection performance by utilizing the angle information from optical images. Specifically, we convert the oriented bounding box into a Gaussian distribution and design a Gaussian Angle Distillation (GAD) loss function to align the angle information between optical and SAR images. In addition, to mitigate the negative impact of low-quality angle information on the network, we design an Adaptive Weighting Strategy (AWS) to guide the student network to prioritize high-quality angle information. The lack of high-quality oriented labels and objects in the OGSOD-1.0 dataset has hindered the progress in related fields. Therefore, we have added high-quality oriented labels and images to the OGSOD-1.0 dataset to construct a new dataset. Extensive experiments demonstrate the effectiveness and superiority of our proposed GaLD over existing methods. The dataset and code are available at: https://***/wchao0601/GaLD. © 2025 IEEE.

关键词： knowledge distillation object detection Remote sensing synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Residual diverse ensemble for long-tailed multi-label text classification

引用

science China(Information sciences) 2024年第11期67卷 92-105页

作者： Jiangxin SHI Tong WEI Yufeng LI National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of Education

Long-tailed multi-label text classification aims to identify a subset of relevant labels from a large candidate label set, where the training datasets usually follow long-tailed label distributions. Many of the previous studies have treated head and tail labels equally, resulting in unsatisfactory performance for identifying tail labels. To address this issue, this paper proposes a novel learning method that combines arbitrary models with two steps. The first step is the “diverse ensemble” that encourages diverse predictions among multiple shallow classifiers, particularly on tail labels, and can improve the generalization of tail *** second is the “error correction” that takes advantage of accurate predictions on head labels by the base model and approximates its residual errors for tail labels. Thus, it enables the “diverse ensemble” to focus on optimizing the tail label performance. This overall procedure is called residual diverse ensemble(RDE). RDE is implemented via a single-hidden-layer perceptron and can be used for scaling up to hundreds of thousands of labels. We empirically show that RDE consistently improves many existing models with considerable performance gains on benchmark datasets, especially with respect to the propensity-scored evaluation ***, RDE converges in less than 30 training epochs without increasing the computational overhead.

关键词： multi-label learning extreme multi-label learning long-tailed distribution multi-label text classification ensemble learning

来源：评论

学校读者我要写书评

暂无评论

A boundary evidence controlled level set inference method for nuclei instance segmentation in histopathology images

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Vatani, Amir Song, Jie Xiao, Liang School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

Periodic B-spline (PBS) has been a successfully used technique in histopathology image segmentation. However, it is limited when dealing with multi-instance objects in real-world biomedical applications. Moreover, its segmentation results are quite sensitive to the initial settings of the model and highly depend on the selection of control points. To address these issues and boost the canonical PBS to a new level of adaptive fitting, we present Level-Set B-Spline (LSBS), a novel definition of nuclear contour inference that employs B-splines under the energy minimization of a variational level set functional, which can promote each other. To this end, we adopt a two-stage approach: The first stage solves the marker detection and image segmentation problem and the second stage solves the joint modeling of the missing contour and the latent shape. To do so, we propose the use of modified concavity measurement and optimal boundary-to-marker association as an efficient basis for computing a periodic set of knots to drive the LSBS. For any probe image, our approach enables to analysis of free-lying and overlapping cell nuclei with weak boundaries. We demonstrated the superiority of the proposed LSBS by evaluating it on various datasets, including the challenging TCGA KIRC and Kumar nuclei, where the consistently state-of-the-art performances were achieved for comparison against state-of-the-art image analysis-based methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Heterophily in Spatial-Temporal Graphs for Multivariate Time-Series Forecasting

Leveraging Heterophily in Spatial-Temporal Graphs for Multiv...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Chen, Yuxin Lin, Fangru Huo, Jingyi Yan, Hui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350368741

Multivariate Time-Series (MTS) forecasting is challenging due to the complex spatial-temporal dependencies inherent in MTS data. Recent studies typically adopt spatial-temporal graph models to leverage this information. However, most of these approaches assume homophily in graphs and perform only immediate message passing, which limits their ability to fully capture spatial-temporal dependencies. In this paper, we propose a novel Dual-Path Spatial-Temporal Graph Neural Network (DPSTGNN). We first extract and cluster representative short-term series patterns from the MTS data. Then, by comparing historical series segments with the extracted representative patterns, we generate pattern attribution embeddings for nodes, enabling the construction of Homophily and Heterophily Spatial-Temporal Crossed Graphs (STCGs), which depict diverse node-wise relationships across different time segments. Finally, we introduce dilated spatial-temporal crossed graph convolutions on both types of STCGs to capture a wide range of spatial-temporal dependencies for enhanced MTS forecasting. Experiments on six real-world datasets demonstrate that our method outperforms state-of-the-art models. © 2025 IEEE.

关键词： Graph Neural Network Heterophily Multivariate Time-Series Forecasting

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：