检索结果-内蒙古大学图书馆

23rd IFIP WG 6.1 international Conference on distributed Applications and Interoperable systems (DAIS) Held as Part of the 18th international Federated Conference on distributed Computing Techniques (DisCoTec)

作者： Sirocchi, Christel Bogliolo, Alessandro Univ Urbino DiSPeA Piazza Repubbl 13 I-61029 Urbino PU Italy Digit Srl Corso Giuseppe Garibaldi 66 I-61029 Urbino PU Italy

ISBN: (纸本)9783031352591;9783031352607

Most real-world networks tend to organise according to an underlying modular structure, where nodes are relatively more connected with nodes belonging to the same community than others. Modularity can impact the performance of distributed data aggregation and computation in networked systems due to limited communication between communities. This paper examines the effects of modularity in the context of distributed averaging, a fundamental cooperative control problem and a central task in various applications ranging from clock synchronisation to formation control. Numerical experiments on synthetic networks demonstrate that modularity negatively affects the convergence rate of randomised gossip algorithms for distributed averaging. Further analysis suggests that nodes bridging communities (here termed boundary nodes) hold a crucial role in controlling the information flow across the network and that a modularity metric dependent on boundary nodes is a good linear predictor of performance while computable in a distributed manner. The averaging gossip protocol is then integrated with a distributed community detection algorithm, giving rise to a novel gossip scheme that leverages local community structure to improve performance by balancing the information flow at boundary nodes. The proposed community-based gossip algorithm is evaluated on synthetic modular structures, and its improved performance is confirmed by simulations run on real-world peer-to-peer networks. These findings emphasise the importance of community structure in distributed computation and might inspire further investigation in this direction.

关键词： distributed community detection distributed averaging Gossip algorithms Community structure Peer-to-peer networks

来源：评论

学校读者我要写书评

暂无评论

Finding of DDoS Attack in IoT-Based networks Using Ensemble Technique

Finding of DDoS Attack in IoT-Based Networks Using Ensemble ...

引用

2024 international Conference on Intelligent systems for Cybersecurity, ISCS 2024

作者： Srivastava, Animesh Tiwari, Shweta Kumar, Deepak Garg, Navin Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Chandigarh University Department of Computer Science and Engineering University Institute of Engineering Punjab Mohali India Sgt University Department of Computer Science and Engineering Gurugram India Uttarakhand Dehradun India

ISBN: (纸本)9798350375237

Ensemble techniques could find DDoS attacks more quickly in IoT. A more dependable and precise detection system can be achieved by integrating the most advantageous attributes of XGBoost and Random Forest. This ensures that Internet of Things systems remain operational. Internet of Things (IoT) systems are significantly compromised regarding security and dependability by distributed Denial of Service (DDoS) assaults. Ensemble approaches, which utilize multiple machine learning models to generate predictions, appear to be a viable method for facilitating the detection of DDoS attacks in such contexts. Conventional defenses against these everevolving attacks prove inadequate when applied to a singular method. It emphasizes Random Forest and XGBoost. The accuracy of the proposed ensemble in detecting distributed denial of service attacks initiated by Internet of Things devices is 99%. The findings demonstrate how ensemble methodologies can enhance the precision and resilience of DDoS attack detection in Internet of Things systems against adversarial assaults. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

27th international Conference on distributed computer and Communication networks, DCCN 2024

27th International Conference on Distributed Computer and Co...

引用

27th international Conference on distributed computer and Communication networks, DCCN 2024

ISBN: (纸本)9783031808524

The proceedings contain 36 papers. The special focus in this conference is on distributed computer and Communication networks. The topics include: Radio Resources Management Model of 5G Network with Two NSIs and Priority Service;energy-Efficient Framework for Task Caching and Computation Offloading in Multi-tier Vehicular Edge-Cloud systems;autoregressive and Arima Pro-integrated Moving Average Models for Network Traffic Forecasting;stability Conditions of Two-Class Preemptive Priority Retrial System with Constant Retrial Rate;on Physical Proximity Serverless Presentations;measurement-Based Received Signal Time-Series Generation for 6G Terahertz Cellular systems;optimizing Energy Efficiency via Small Cell-Controlled Power Management for Seamless Data Connectivity;analysing Performance Metrics of an All-Optical Network in Fault Conditions and Traffic Surges;analysis of Polling Queueing System with Two Buffers and Varying Service Rate;simulation of M/G/1//N System with Collisions, Unreliable Primary and a Backup Server;state-Dependent Admission Control in Heterogeneous Queueing-Inventory System with Constant Retrial Rate;stochastic Analysis of a Multi-server Production Inventory System with N-Policy;simulation-Based Optimization for Resource Allocation Problem in Finite-Source Queue with Heterogeneous Repair Facility;tandem Retrial Queueing System with Markovian Arrival Process and Common Orbit;Polling Model for Analysis of Round-Trip Time in the IAB Network;reliability Analysis of a k-out-of-n Single Server System Extending Service to External Customers Under N-Policy and Server Vacations;reliability Analysis of a Double Hot Standby System Using Marked Markov Processes;modeling Distributions of Node Characteristics in Directed Graphs Evolving by Preferential Attachment;convolution Algorithm for Evaluation of Probabilistic Characteristics of Resource Loss systems with Signals;Controlled Markov Queueing systems Under Uncertainty with Deep RL Algorithm;probability Chara

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chirp-Based Majority Vote Computation for Federated Edge Learning and distributed Localization

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2023年 4卷 1060-1074页

作者： Hoque, Safi Shams Muhtasimul Sahin, Alphan Univ South Carolina Dept Elect Engn Columbia SC 29208 USA

In this study, we propose an over-the-air computation (OAC) scheme based on chirps to detect the majority votes (MVs) in a wireless network for federated edge learning (FEEL) and distributed localization. With the proposed approach, a group of votes is mapped to an index of a linear chirp at each edge device (ED). From superposed chirp signals, the corresponding MVs at the edge server (ES) are then detected non-coherently with a set of energy comparators by exploiting the bit representation of the indices. The proposed scheme is power-efficient and has low out-of-band emission while it does not use the channel state information (CSI) at the EDs and ES. Hence, it paves the way for long-distance FEEL and distributed localization based on MVs in a wireless sensor network with low-complexity devices. For FEEL, we comprehensively demonstrate the efficacy of the proposed approach under heterogeneous data distribution. For localization, we propose iterative refinements and multiple repetitions to improve the localization performance. We show that the proposed strategies minimize the distance between the root-mean-square error (RMSE) error and quantization bound.

关键词： Location awareness Chirp Symbols Wireless sensor networks Distance learning computer aided instruction Spectral efficiency distributed learning distributed localization over-the-air computation PMEPR

来源：评论

学校读者我要写书评

暂无评论

Exploring Artificial Intelligence’s Potential in Developing Advanced distributed Denial of Service Defense Strategies

Exploring Artificial Intelligence’s Potential in Developing...

引用

international Conference on Computing and Machine Learning, CML 2024

作者： Alhindi, Ahmad Computer Science and Artificial Intelligence Department College of Computer and Information Systems Makkah Saudi Arabia

ISBN: (纸本)9789819778386

Facing the growing menace of distributed denial of service (DDoS) attacks, there’s a critical demand for enhanced detection mechanisms. This necessitates a shift from traditional methodologies to more advanced, dynamic detection techniques. The significance of advanced computational methods in pinpointing DDoS threats is increasingly recognized. This paper delves into the crucial role these techniques play in detecting DDoS activities, with a focus on the adaptability of network-based algorithms and the proficiency of advanced models like Convolutional Neural networks (CNNs), Recurrent Neural networks (RNNs), and autoencoders in identifying complex attack patterns that traditional methods may overlook. Our findings reveal that while advanced computational strategies offer considerable benefits over conventional methods in terms of detection accuracy and adaptability to evolving threats, they also present unique challenges, including higher computational demands and the need for continuous model training to keep pace with new attack vectors. The comparative analysis underscores the operational advantages and potential limitations of these approaches, providing a nuanced understanding of their application in real-world scenarios. This investigation aims to present a current view of advancements in digital security techniques and to serve as a basis for future research and the development of innovative, practical solutions. It suggests that enhancing the resilience of digital infrastructures against DDoS attacks will require not only technological innovation but also a comprehensive strategy that includes ongoing research, collaboration among stakeholders, and the adoption of adaptive, scalable detection systems capable of responding to the dynamic nature of cyber threats. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Negative Learning Emotion Recognition in English Classroom using Cross Space based Convolutional Neural Network

Research on Negative Learning Emotion Recognition in English...

引用

2024 international Conference on distributed systems, computer networks and Cybersecurity, ICDSCNC 2024

作者： Tan, Xuanxuan Hou, Xiaoli Dai, Xiaojia Tan, Lilanjun Hunan Sany Polytechnic College Department of International Business and Economics Changsha China

ISBN: (纸本)9798350375442

In English classroom the teaching behavior, changes according to the student's facial emotions which are observed by facial expressions and behavioral phases in the class. Nonetheless, in the English classroom, behavior of the students during learning is changeable and complex to understand by teacher's and it also difficult for understanding the negative emotions such as bored, stressed and not interested in the English classroom. To overcome these limitations, a Cross-Space based Convolutional Neural Network (CS-CNN) model is proposed to recognize the which is observed from students. The proposed method learns multiscale information such as subtle differences between various emotions and complex negative emotion pattern efficiently by cross-space feature fusion. This helps to enhance the recognition performance to assist the teachers to change their teaching strategies to make the students more focused and improve learning environment of students. For extracting significant features from the facial images are preprocessed by histogram equalization and extracted using DeepNet architecture. The experimental results of the proposed CS-CNN method achieved accuracy of 94.33% which is higher when compared to existing recognition approaches such as Support Vector Machine (SVM) and Yolo-V3. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Live Demonstration: 5-bit signed SRAM-based DNN CIM for Image Recognition

Live Demonstration: 5-bit signed SRAM-based DNN CIM for Imag...

引用

IEEE international symposium on Circuits and systems (ISCAS)

作者： Pereira-Rial, O. Garcia-Lesta, D. Vaquero, L. Lopez, P. Brea, V. M. Cabello, D. Univ Santiago Compostela Ctr Singular Invest Tecnol Intelixentes CiTIUS Santiago De Compostela Spain

ISBN: (纸本)9798350330991;9798350331004

This live demonstration shows a mixed-signal computer In Memory (CIM) macro deep neural network (DNN) integrated circuit in 180 nm CMOS technology for image recognition. Images are coded as pulse width modulation (PWM) signals. DNN weights are stored as voltages in 6T-SRAM memories which drive current sources inside every multiplier. Multipliers are arranged within processing elements laid down in a 2D mesh suitable for image processing. The power consumption per multiplier of the CIM macro is of 0.22 mu W, below state-of-the-art competitors following the same multiply and accumulate (MAC) principle.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Polynomial Stability of Coupled Waves with Weak Indirect Damping 26

Polynomial Stability of Coupled Waves with Weak Indirect Dam...

引用

26th international symposium on Mathematical Theory of networks and systems (MTNS)

作者： Kosonen, Jasper Paunonen, Lassi Vanspranghe, Nicolas Tampere Univ Fac Informat Technol & Commun Sci Math FI-33720 Tampere Finland

We study the stability properties of coupled one-dimensional wave equations with indirect damping. We employ methods based on observability estimates for the undamped system to prove polynomial stability and rational energy decay for the classical solutions of the coupled systems. We present our results for two different kinds of indirect damping - viscous damping and weak damping. Copyright (c) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： distributed parameter systems coupled wave equations polynomial stability observability estimates output feedback

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Techniques for Solving Complex computer Vision Challenges and Enhancing Pattern Recognition Accuracy

Innovative Deep Learning Techniques for Solving Complex Comp...

引用

2024 international Conference on distributed systems, computer networks and Cybersecurity, ICDSCNC 2024

作者： Jayachitra, T. Sathya, S. Ramesh, P.S. Jothikumar, R. Gouri, M.S. Hussain, Mohammed Waheeduddin Sharda University Department of Electrical Electronics and Communication Engineering Greater Noida India Grt Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Tiruttani India Vellore Institute of Technology Department of Smart Computing Vellore India Shadan College of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Baselios Mathews - Ii College of Engineering Department of Computer Science and Engineering Sasthamcotta Kollam India Shadan College of Engineering and Technology Department of Information Technology Peerancheru Hyderabad India

ISBN: (纸本)9798350375442

The proposed work provides an in-depth analysis of DL techniques to enhance pattern recognition accuracy in difficult computer vision applications. This background explains the present status of the problems in the area and motivates the development of a complex framework that blends innovative neural network topologies, state-of-the-art optimization approaches, and inventive data augmentation strategies. Among the methods are CNNs enhanced with residual blocks and attention mechanisms, which are implemented using the TensorFlow deep learning framework. The results demonstrate significant improvements over baseline models on a number of measures. Using the CIFAR-10 dataset, the proposed system achieves an impressive 92.5% accuracy and 92.1% F1-score for classification tasks. With an IoU of 78.2% and a mAP of 81.4% in object identification tasks, the system shows its robustness in accurately localizing and recognizing things within photos. These findings have practical ramifications for industries needing accurate visual identification, such autonomous driving and medical imaging, in addition to advancing theoretical knowledge. The efficacy of the architecture highlights its potential to serve as a benchmark for next deep learning studies and applications. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Approximate Convolutional Neural networks Based on Dynamic Binding Windows 5

Approximate Convolutional Neural Networks Based on Dynamic B...

引用

5th CPSSI international symposium on Cyber-Physical systems (Applications and Theory), CPSAT 2024

作者： Adelkhani, Morteza Sedighi, Mehdi Amirkabir University of Technology Computer Engineering Tehran Iran

ISBN: (纸本)9798331529284

The rapid growth of applications focused on handling amounts of data has increased the demand, for computational power especially in areas such as machine learning and graph analysis within big data frameworks. While these applications have traditionally been run on data centers, they now encounter issues concerning security and quick access to data leading to a shift towards embedded systems with processing capacity. To tackle this challenge, we suggest a strategy to improve the efficiency of Convolutional Neural networks (CNNs) on embedded systems through hardware-driven computing. Our innovative method, "Dynamic Binding Window"adjusts calculation precision dynamically within convolution layers based on feature map windows and layer positions reducing burden and energy usage without compromising accuracy. Our research demonstrates that this approach effectively overcomes the constraints of embedded systems allowing for real-time processing on devices. Comparative evaluations indicate enhancements in processing speed and energy efficiency showcasing the impact of our approach in fields, like autonomous vehicles that rely on swift and precise image analysis. © 2024 IEEE.

关键词： Convolutional neural networks

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：