检索结果-内蒙古大学图书馆

19th European Conference on computer Systems, EuroSys 2024

作者： Zhou, Ming Wang, Haining Li, Ke Zhu, Hongsong Sun, Limin School of Cyber Science and Engineering Nanjing University of Science and Technology China Department of Electrical and Computer Engineering Virginia Tech China Nari Group Corporation State Grid Electric Power Research Institute School of Cyber Security University of Chinese Academy of Sciences China Institute of Information Engineering Cas China Virginia Tech. United States

ISBN: (纸本)9798400704376

Industrial Control Systems (ICS), particularly programmable logic controllers (PLCs) responsible for managing underlying physical infrastructures, often operate for extended periods without interruption. Thus, it is challenging to patch security vulnerabilities of ICS in a timely manner after disclosure because it often necessitates waiting for a rare downtime window. While live patching has been introduced to avoid downtime and maintenance costs, conventional live patching methods are not viable for closed-source PLCs. Without the source code, it is difficult to understand the system behaviors and determine binary patch equivalence. To address these challenges, we present a Reliable Live Patching framework called RLPatch for applying live patches to third-party binary without source code. We design RLPatch to capture real-time conditions and dynamic behaviors of PLCs, which enables DevOps engineers to identify major non-recoverable fault (MNRF) vulnerabilities and generate hot patches. The core of RLPatch is an update agent that inserts breakpoints over the original MNRF code and then directs execution to the patches. To ensure system reliability, we use the unique constraints of PLCs to integrate the update processes with the scan cycle. We leverage RLPatch to patch 20 real vulnerabilities in three widely used Rockwell PLCs. We evaluate RLPatch in a real-world gas pipeline, demonstrating its reliability and effectiveness in practice. © 2024 Owner/Author.

关键词： Programmable logic controllers

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Data Aggregation with Error-Checking for Smart Grids

Fault-Tolerant Data Aggregation with Error-Checking for Smar...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and tech.ology Congress, DASC/PiCom/CBDCom/Cyberscitech.2023

作者： Wang, Congcong Wang, Chen Shen, Jian Vijayakumar, Pandi Bhuiyan, Zakirul Alam School of Software Nanjing University of Information Science & Technology Nanjing210044 China School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China University College of Engineering Tindivanam Department of Computer Science and Engineering Tamilnadu 604001 India Fordham University Department of Computer and Information Sciences NY10458 United States

ISBN: (纸本)9798350304602

With the rapid development of smart grid tech.ology, a new challenge has been brought about by the massive data generated from distributed devices. Data aggregation tech.ology plays a crucial role in smart grid schemes, in terms of energy data statistics and resource allocation. However, achieving fast error-checking and improving device fault-tolerance are still open issues in the smart grid data aggregation. To address these issues, this paper proposes an error-tolerant data aggregation scheme integrated with error-checking mechanisms. The scheme proposes a tree-based aggregation structure, facilitating swift error-checking of data. We combine masking values with user anonymity in the ElGamal cryptographic scheme to ensure the security of sensitive data and resist collusion attacks. Both theoretical and experimental analyses demonstrate that this scheme enables a lightweight, secure data aggregation, ensuring enhanced reliability and error-checking. © 2023 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Dual-Source CBCT for Larger Longitudinal Coverage: System Design and Image Reconstruction 46

Dual-Source CBCT for Larger Longitudinal Coverage: System De...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Zhang, Xusheng Lyu, Tianling Shi, Yijie Zhong, Xinyun Wu, Zhan Xi, Yan Wang, Shijie Chen, Yang Zhu, Wentao Southeast University School of Software Nanjing China Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Southeast University Laboratory of Image Science and Technology The School of Computer Science and Engineering Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

The application of CBCT systems in intraoperative environments has become increasingly common, but concurrent CBCT systems are unsuitable for situations that require a large longitudinal imaging FoV, such as orthopedics. To increase longitudinal coverage, we developed a dual-source CBCT (DS-CBCT) system in which two ray sources are symmetrically placed along the central plane. After further analyzing its geometric characteristics, we propose an analytical reconstruction algorithm termed DT-FDK specialized for DS-CBCT, which combines cone-beam rebinning and two rays with smaller cone angles among the four conjugate rays to further suppress cone beam artifacts. The system design and reconstruction algorithm are tested on both simulated and real-scanned data. Results show that the DS-CBCT can expand the effective imaging volume by 37.1% compared to single-source CBCT systems. The reconstructed images by DT-FDK also show improved image quality compared to traditional reconstruction algorithms. © 2024 IEEE.

关键词： Cones

来源：评论

学校读者我要写书评

暂无评论

Balancing Human-robot Collaborative Disassembly Line by Using Dingo Optimization Algorithm 4

Balancing Human-robot Collaborative Disassembly Line by Usin...

引用

4th IEEE International Conference on Human-Machine Systems, ICHMS 2024

作者： Guo, Xiwang Zhou, Liangbo Zhou, Mengchu Wang, Weitian Wang, Jiacun Qi, Liang Liaoning Petrochemical University Information And Control Engineering Fushun China Liaoning Petrochemical University Information And Control Fushun China New Jersey Institute Of Technology Electrical And Computer Engineering NewarkNJ United States Montclair State University School Of Computing Montclair United States Monmouth University Computer Science And Software Eng. West Long BranchNJ United States Shandong University Of Sci. And Tech. Computer Intelligent Sci. And Tech. Qingdao China

ISBN: (纸本)9798350315790

Disassembling and recycling scrapped products play important roles in effectively reducing environmental pollution and improving resource sustainability. A multi-product human-robot collaborative disassembly-line-balancing problem (MHDP) arises from doing so and represents an important yet to be solved in the remanufacturing field. This work explores how to use optimization algorithms to schedule tasks between humans and robots to maximize remanufacturing profit in human-robot collaboration contexts. Specifically, we investigate MHDP and develop a mixed integer programming model considering various system constraints. We propose a dingo optimization algorithm that simulates wild dogs' social hierarchy and chasing processes to solve MHDP. We compare the proposed algorithm with an exact solution finder, i.e., IBM CPLEX and a well-known intelligent optimization method, i.e., Genetic Algorithm to show its competitive performance in terms of solution accuracy and efficiency. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Rebalanced Multimodal Learning with Data-aware Unimodal Sampling

arXiv

引用

arXiv 2025年

作者： Jiang, Qingyuan Chi, Zhouyang Ma, Xiao Mao, Qirong Yang, Yang Tang, Jinhui School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Technology Zhejiang Sci-Tech University China School of Computer Science and Communication Engineering Jiangsu University China

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning (MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of model learning. However, almost all existing methods ignore the modality imbalance caused by unimodal data sampling, i.e., equal unimodal data sampling often results in discrepancies in informational content, leading to modality imbalance. Therefore, in this paper, we propose a novel MML approach called Data-aware Unimodal Sampling (DUS), which aims to dynamically alleviate the modality imbalance caused by sampling. Specifically, we first propose a novel cumulative modality discrepancy to monitor the multimodal learning process. Based on the learning status, we propose a heuristic and a reinforcement learning (RL)based data-aware unimodal sampling approaches to adaptively determine the quantity of sampled data at each iteration, thus alleviating the modality imbalance from the perspective of sampling. Meanwhile, our method can be seamlessly incorporated into almost all existing multimodal learning approaches as a plugin. Experiments demonstrate that DUS can achieve the best performance by comparing with diverse state-of-the-art (SOTA) baselines. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Parallel and Batch Multiple Replica Auditing Protocol for Edge Computing 21

Parallel and Batch Multiple Replica Auditing Protocol for Ed...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Li, Yi Zheng, Wenying Pandi, Vijayakumar Bhuiyan, Md Zakirul Alam Thamilarasi, C. Nanjing University of Information Science and Technology School of Computer Science Nanjing China Zhejiang Sci-Tech University School of Computer Science and Technology Hangzhou China University College of Engineering Tindivanam Anna University Chennai Department of Computer Science and Engineering Melpakkam India Fordham University Department of Computer and Information Sciences BronxNY United States P.S.V College of Enfgineering and Technoogy Department of Electronics and Communication Engineering Krishnagiri India

ISBN: (纸本)9798350329223

The edge computing architecture exposes data transmission and storage to unauthorized access, compromising data integrity. Users typically employ multiple data backups to ensure data reliability and availability, enhancing data redundancy and recovery capabilities. Nevertheless, verifying the integrity of multiple backup data under edge computing entails computational and communication overhead. In response, we present a parallel and batch multiple replica auditing protocol tailored for edge computing. Contributions include an efficient multiple replica construction method based on RSA, minimizing computational overhead, and a parallel data integrity verification approach that reduces communication overhead. A prototype implementation is evaluated in a real edge computing environment and compared to existing multiple replica auditing approaches. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Intra-Guided Dual-Energy Material Decomposition Method for Dual-Source CBCT Systems 46

Intra-Guided Dual-Energy Material Decomposition Method for D...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Zhong, Xinyun Lyu, Tianling Wu, Zhan Gao, Wei Xi, Yan Zhao, Wei Zhu, Wentao Chen, Yang Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Beihang University Beijing China Southeast University School of Computer Science and Engineering Laboratory of Image Science and Technology Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Dual-energy CBCT imaging plays a crucial role in advanced imaging applications due to its ability to quantify material components. Although there are multiple established systems for dual-energy imaging, they often come with high deployment costs. This study investigates the feasibility of dual-energy material decomposition on a less expensive dual-source CBCT system. Due to the specific geometry of dual-source CBCT, cone-beam (CB) artifacts seriously degrade the material decomposition quality when the direct inversion method is adopted. In this paper, a novel dual-source intra-guided material decomposition framework is proposed to suppress CB artifacts in the material maps. Firstly, a dual-source two-pass algorithm is developed for artifact pre-correction during image reconstruction. Then, the structure of small cone-angle regions from one X-ray source is utilized to guide cone beam artifact removal in large cone-angle regions from another source. Finally, direct matrix inverse material decomposition is applied to the filtered image. Extensive experiments have been conducted on the authentic human phantom and demonstrate that the proposed framework achieves excellent performance in cone beam artifact reduction compared to other methods, and significantly enhances the quality of the material maps. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Water Management: A Low-Cost Framework for Sustainable Irrigation in Agricultural Farms and Home Gardens

IoT-Enabled Water Management: A Low-Cost Framework for Susta...

引用

2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems, iCACCESS 2024

作者： Rana, Md Zweel Rahaman, A. S. Md. Mostafizur Ali, Md Osman Mahmud, M. A. Parvez Walton Hi-Tech Ind. Plc Dept. of Research and Innovation Gazipur1751 Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Savar Bangladesh Noakhali Sci. and Tech. University Dept. of Electrical and Electronic Engineering Noakhali3814 Bangladesh School of Mathematical and Physical Sciences University of Technology Sydney Australia

ISBN: (纸本)9798350350289

Agriculture is a major contributor to Bangladesh's economy, with many people depending on it for their livelihoods. Farming and gardening are considered a key initiative in mitigating global warming as well as providing economic support for many families in Bangladesh. However, the vulnerability of gardens to damage during long weekends and vacations necessitates smart solutions. Also, proper irrigation is crucial for agriculture-based farms to thrive, as it is highly dependent on environmental conditions. This paper explores the application of Internet of Things (IoT)-based smart tech.ologies as a promising solution to address this issue. A user-friendly, low-cost system facilitates the commercialization of such solutions on a large scale. In this work, we have implemented an IoT-based solution for the irrigation and watering system for agricultural firms and home gardens in Bangladesh, respectively. Considering the diverse weather conditions of Bangladesh, three key parameters, such as moisture, temperature, and humidity;have been monitored continuously and analyzed in real-time. The proposed system consists of two parts: the watering system, and the mobile app interface. The watering system incorporates an ESP32 Node MCU, sensors, two servo motors and a water pump. In automatic mode the water supply inside the garden or farm is connected to a water pump, that will be activated when the soil moisture sensor detects low moisture level, and the ambient sensor detects low humidity or high temperature. Alternatively, the garden or farm owners can remotely control the pump motor through the mobile app to water in the farm leveraging sensor data. Also, it can control the water flow angle according to their preferences. Additionally, this proposed system has the potential to save 25% to 40% of water and energy resources than traditional irrigation methods. The overall cost of the system is approximately 2476 taka, which is around the cost of 20 USD. The system is designe

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FedRFD: Heterogeneous Federated Learning via Refining Feature-level Distillation 24

FedRFD: Heterogeneous Federated Learning via Refining Featur...

引用

13th International Conference on Computing and Pattern Recognition, ICCPR 2024

作者： Yu, Peng Yuan, Yuwen Wang, Youquan Shi, Wei Shi, Zhihui Hua, Yue College of Information Engineering Nanjing University of Finance and Economics Jiangsu Nanjing China School of Computer Science and Engineering Taizhou Institute of Sci.&Tech. NJUST Jiangsu Taizhou China College of Liberal Arts and Sciences University of Illinois at Chicago ChicagoIL United States Department of Financial Technology Jiangsu Sushang Bank Co. Ltd. Jiangsu Nanjing China School of Marxism Jiangsu University Jinagsu Zhenjiang China

ISBN: (纸本)9798400717482

Federated learning faces a significant challenge in effectively aggregating knowledge from diverse local models with varying learning capabilities while preserving privacy through collaborative, local updates on private data. Previous methods for addressing such challenges involve combining distilled logits-based knowledge from various local models using weights derived from their respective learning capabilities as weighting coefficients. However, logits-based knowledge distillation suffers from information loss, expression diversity limitations, and model dependency, leading to a less affluent knowledge transfer. Therefore, we propose heterogeneous federated learning via refining feature-level distillation (FedRFD), which leverages richer knowledge of intermediate layer features for distillation. Specifically, (1) To facilitate communication between heterogeneous models, we align their feature-level with public data, eliminating the need for an additional global model. (2) To address feature alignment challenges in models with varying feature-level numbers, we propose the knowledge refining mechanism (KRM). (3) To increase the efficiency of collaborative learning, we propose a novel method to dynamically assign weights to each client. Extensive experiments confirm that our approach significantly outperforms state-of-the-art algorithms in heterogeneous model scenarios. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ReQ-tank: Fine-grained Distributed Machine Learning Flow Scheduling Approach

ReQ-tank: Fine-grained Distributed Machine Learning Flow Sch...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Quanyi Xu Kedong Yan Dan Yin Chanying Huang Shan Xiao Yuxin Yang School of Cyber Science and Engineering Nanjing University of Science and Technology Jiangyin China School of Computer Science and Engineering Nanjing Univ. of Science and Technology Nanjing China School of Computer Science and Engineering Beijing Univ. of Civil Engineering and Architecture Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Fiberhome Communication Tech. Co. Wuhan China

The swift advancement of distributed computing has enhanced the support for big data and massive-scale models. Yet, delivering superior services to manage large and intricate network flows in data center networks remains a formidable challenge. In this paper, we present ReQ-tank, an intricate flow scheduling approach based on a multi-level feedback queue (MLFQ) devised to achieve flow prioritization and efficient flow scheduling. ReQ-tank employs a two-tier scheduling strategy: On the flow scheduling layer, priority queues are segmented into two categories, and the flows within high-priority queues follow a strict priority scheduling, while those in low-priority queues adhere to differential weighted Round-robin scheduling; On the packet scheduling layer, ReQ-tank modifies the priority of initially high-priority re-transmitted packets to facilitate fine-grained data packet scheduling. We carry out simulation experiments on web search workloads and data mining workloads. Experimental results demonstrate that ReQ-tank can curtail packet wait time in the network, significantly truncate the flow completion time (FCT) of delay-sensitive flows and counteract the issue of flow starvation in traditional strict priority queues. Consequently, ReQ-tank is deemed more suitable for complex distributed network applications.

关键词：

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：