检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Yin Li Anmin Fu Yuqing Zhang National Computer Network Intrusion Protection Center University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

The ICS protocols undertake critical functions in industrial control systems, by enabling real-time data exchange, data acquisition, parameter configuration, status monitoring, fault diagnosis, command issuance and execution. It serves as the foundation for the collaborative operations of all components in industrial control systems. With the development of internet technology, industrial control systems, which were originally physically isolated, have become new targets for hackers. However, due to the high level of privatization of ICS protocols and their complex workflow, existing methods are insufficient in detecting vulnerabilities in these protocols. This paper proposes a black-box fuzzing test method based on sensing the program runtime feedback. By collecting run-time statistics, including CPU utilization, memory utilization, disk I/O, and message interaction, our method is able to determine whether the program has triggered a new execution path, thus improving the efficiency of the fuzzing procedure. We evaluated our prototype on five open-source ICS protocol programs and discovered six reported vulnerabilities, among which five could cause the industrial control programs to become unresponsive or crash.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ranking Aggregation with Interactive Feedback for Collaborative Person Re-identification 33

Ranking Aggregation with Interactive Feedback for Collaborat...

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Huang, Ji Liang, Chao Zhang, Yue Wang, Zhongyuan Zhang, Chunjie National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong University Beijing100044 China

Person re-identification (re-ID) aims to retrieve the same person from a group of networking cameras. Ranking aggregation (RA), a method to aggregates multiple ranking results, can further improve the retrieval accuracy in re-ID tasks. Existing RA work can be generally divided into unsupervised methods and fully-supervised methods. Unsupervised methods lack external supervision, can hardly achieve the optimal results. In contrast, fully-supervised methods need massive labeling data for training, which is prohibitively expensive in the practical application. This paper studies interactive RA (IRA) to address the above challenges in existing RA research. The core idea is to utilize a small amount of supervisory information, obtained from users' relevance feedback, to supervise RA method to produce better re-ranking results. Compared with unsupervised methods, IRA introduces supervisory information and thus has better aggregation accuracy. Compared with fully-supervision methods, the supervisory information of IRA is more readily available, and can be targeted to specific queries. Particularly, we propose two IRA implementations, based on ranking positions and scores respectively, to adapt to diverse application scenarios, where rankers only give rankings, or rankers give similarity scores. Experiments on three public re-ID datasets have shown that IRA significantly outperforms the-state-of-art unsupervised baselines, and achieves similar accuracy with less labeling cost than the fully-supervised RA method. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

TupleChain: Fast Lookup of OpenFlow Table with Multifaceted Scalability

arXiv

引用

arXiv 2024年

作者： Li, Yanbiao Ren, Neng Wang, Xin Chen, Yuxuan Zhang, Xinyi Guo, Lingbo Xie, Gaogang Computer Network Information Center Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering Stony Brook University Stony BrookNY United States

OpenFlow switches are fundamental components of software defined networking, where the key operation is to look up flow tables to determine which flow an incoming packet belongs to. This needs to address the same multi-field rule-matching problem as legacy packet classification, but faces more serious scalability challenges. The demand of fast on-line updates makes most existing solutions unfit, while the rest still lacks the scalability to either large data sets or large number of fields to match for a rule. In this work, we propose TupleChain for fast OpenFlow table lookup with multifaceted scalability. We group rules based on their masks, each being maintained with a hash table, and explore the connections among rule groups to skip unnecessary hash probes for fast search. We show via theoretical analysis and extensive experiments that the proposed scheme not only has competitive computing complexity, but is also scalable and can achieve high performance in both search and update. It can process multiple millions of packets per second, while dealing with millions of on-line updates per second at the same time, and its lookup speed maintains at the same level no mater it handles a large flow table with 10 million rules or a flow table with every entry having as many as 100 match fields. Copyright © 2024, The Authors. All rights reserved.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

MedX-Net: Hierarchical Transformer with Large Kernel Convolutions for 3D Medical Image Segmentation

MedX-Net: Hierarchical Transformer with Large Kernel Convolu...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Lin Lu Qingzhi Zou Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Due to the exceptional performance of Transform-ers in 2 $D$ medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%.

关键词： Image segmentation Solid modeling Visualization Three-dimensional displays Current transformers Multilayer perceptrons Convolutional neural networks Kernel Synapses Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

FGLNoRe: Federated Graph Learning on Non-IID RF Fingerprints for Building-Floor Positioning

FGLNoRe: Federated Graph Learning on Non-IID RF Fingerprints...

引用

International Conference on Electronics Information and Emergency Communication

作者： Zhenhuang Huang Bo Gao Ke Xiong Engineering Research Center of Network Management Technology for High-Speed Railway of Ministry of Education School of Computer Science and Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China

ISBN: (数字)9798350361896

ISBN: (纸本)9798350361902

In recent years, deep learning has revolutionized indoor positioning based on radio frequency fingerprints. Furthermore, federated learning has been introduced to address the challenges of data sharing without compromising location privacy in indoor positioning. In the context of federated learning, there is the inherent heterogeneity among fingerprint data from diverse mobile clients. Moreover, federated learning approaches overlook the underlying spatial correlations among access points (APs). Therefore, we need to improve model aggregation techniques and integrate graph learning techniques into federated learning to effectively learn from heterogeneous and spatially correlated APs. This paper proposes the FGLNoRe algorithm (Federated Graph Learning via Normalized Averaging with Regularization), a federated graph learning method for fingerprinting-based building-floor positioning in large-scale three-dimensional scenarios. The method introduces federated graph learning via normalized averaging with regularization to integrate federated learning with graph convolutional network (GCN). Extensive experiments on a real Wi-Fi fingerprint dataset validate that our method achieves a building-floor positioning classification accuracy of 0.85 in the presence of high-level data heterogeneity.

关键词： Radio frequency Learning systems Deep learning Data privacy Accuracy Federated learning Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Spatial Mode Dispersion for Strongly-Coupled Multicore Fiber Submarine Transmission

On the Impact of Spatial Mode Dispersion for Strongly-Couple...

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Sun, Lin Chen, Bin Liu, Gordon Ning Cai, Yi Li, Zhaohui Lu, Chao Shen, Gangxiang Soochow University Suzhou Key Laboratory of Advanced Optical Communication Network Technology School of Electronic and Information Engineering Suzhou215006 China Hefei University of Technology School of Computer Science and Information Engineering Hefei China Sun Yat-Sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips School of Electronics and Information Technology Guangzhou511400 China The Hong Kong Polytechnic University Photonics Research Center Department of Electrical and Information Engineering Kowloon Hung Hom Hong Kong

Strongly-coupled multicore fibers exhibit the improved tolerance to fiber non-linearity. Their potentials in optical submarine communications are investigated with considering the coupling length and spatial mode disp... 详细信息

ISBN: (纸本)9781957171180

关键词： Submarines

来源：评论

学校读者我要写书评

暂无评论

ED-YOLO: A Deep Learning and Edge Detection Based Turnout Switch Gap Monitor Method

ED-YOLO: A Deep Learning and Edge Detection Based Turnout Sw...

引用

International Conference on Electronics Information and Emergency Communication

作者： Qinghao Tian Yuping Lu Yeshen Li Ke Xiong Engineering Research Center of Network Management Technology for High-Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China

ISBN: (数字)9798350361896

ISBN: (纸本)9798350361902

A real-time monitoring method for turnout switch gaps based on deep learning and edge detection, named EDYOLO, is proposed to accurately monitor the fastening status of turnouts by identifying the scale readings of the turnout extension indicator rods. The difference between these readings and the baseline scale is calculated to obtain the distance of the switch indicator gaps. To transmit data from embedded clients deployed at the turnout edge to a remote monitoring center server, the system integrates two wireless communication technologies: 4G and LoRa. Additionally, Bluetooth communication technology is integrated to allow railway administrators to configure the embedded clients conveniently using handheld terminals. A prototype is implemented based on Raspberry Pi, and experimental results show that the maximum error of the proposed system in gap monitoring is less than 0.1 millimeters. Furthermore, the server can poll and remotely collect gap data from at least 60 clients per minute.

关键词： Wireless communication Deep learning YOLO Image edge detection Switches Real-time systems Rail transportation

来源：评论

学校读者我要写书评

暂无评论

Graph-Powered Reinforcement Learning for Intelligent Task Offloading in Vehicular networks

Graph-Powered Reinforcement Learning for Intelligent Task Of...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Ihsan Ullah Hyun-Kyo Lim Yeong-Jun Seok Naeem Ul Islam Chang-Hun Ji Youn-Hee Han Advanced Technology Research Center KOREA TECH Cheonan South Korea Quantum Network Research Center KISTI Daejeon South Korea Computer Science and Engineering KOREA TECH Cheonan South Korea Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Future Convergence Engineering KOREA TECH Cheonan South Korea

In vehicular edge computing, task offloading optimization is crucial for balancing computational demands with minimizing delays and costs. However, the dynamic nature of the vehicular environment, including vehicle mobility, network topology, and available computing resources, poses significant challenges. This paper presents a task offloading scheme that enables vehicles to dynamically decide between local task execution and offloading to nearby vehicles, edge servers, or the cloud. Our objective is to optimize task offloading by minimizing cost and delay. We integrate graph convolutional networks with deep reinforcement learning to optimize task offloading decisions and achieve our goal. The Graph Convolutional network is integrated with Deep Reinforcement Learning to enhance network representation and decision efficiency of agent. The optimization problem is formally formulated within the framework of a Markov Decision Process. Simulation results demonstrate the superiority of proposed scheme, which achieves cost-efficiency by maximizing resource utilization, minimizing costs, and optimizing task offloading while reducing task rejection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional classification via stacked dependency exploitation

引用

Science China(Information Sciences) 2020年第12期63卷 104-117页

作者： Bin-Bin JIA Min-Ling ZHANG School of Computer Science and Engineering Southeast University College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of EducationChina Collaborative Innovation Center of Wireless Communications Technology

Multi-dimensional classification(MDC) aims to build classification models for multiple heterogenous class spaces simultaneously, where each class space characterizes the semantics of an object w.r.t. one specific dimension. Modeling dependencies among class spaces plays a key role in solving MDC tasks, where most approaches work by assuming directed acyclic graph(DAG) structure or random chaining structure over class spaces. Different from existing probabilistic strategies, a deterministic strategy named Seem for dependency modeling is proposed in this paper via stacked dependency exploitation. In the first-level, pairwise dependencies are considered which can be modeled more reliably than modeling full dependencies among all class spaces by DAG or chaining structure. In the second-level, the class label of unseen instance *** class space is determined by adaptively stacking predictive outputs from first-level pairwise *** results show that stacked dependency exploitation leads to superior performance against stateof-the-art MDC approaches.

关键词： machine learning multi-dimensional classification class dependencies deterministic strategy stacked dependency exploitation

来源：评论

学校读者我要写书评

暂无评论

Bi-Causal: Group Activity Recognition via Bidirectional Causality

Bi-Causal: Group Activity Recognition via Bidirectional Caus...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Youliang Zhang Wenxuan Liu Danni Xu Zhuo Zhou Zheng Wang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University of Technology National University of Singapore

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Current approaches in Group Activity Recognition (GAR) predominantly emphasize Human Relations (HRs) while often neglecting the impact of Human-Object Inter-actions (HOIs). This study prioritizes the consideration of both HRs and HOIs, emphasizing their interdependence. Notably, employing Granger Causality Tests reveals the presence of bidirectional causality between HRs and HOIs. Leveraging this insight, we propose a Bidirectional-Causal GAR network. This network establishes a causality commu-nication channel while modeling relations and interactions, enabling reciprocal enhancement between human-object interactions and human relations, ensuring their mutual consistency. Additionally, an Interaction Module is devised to effectively capture the dynamic nature of human-object interactions. Comprehensive experiments conducted on two publicly available datasets showcase the superiority of our proposed method over state-of-the-art approaches. Our project page: https://***/***/

关键词： computer vision Computational modeling Cause effect analysis Communication channels Activity recognition

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：