检索结果-内蒙古大学图书馆

Max-Min-Degree Neural Network for Centralized-decentralized Collaborative computing

IEICE TRANSACTIONS ON COMMUNICATIONS 2016年第4期E99B卷 841-848页

作者： Sheng, Yiqiang Wang, Jinlin Li, Chaopeng Qi, Weining Chinese Acad Sci Natl Network New Media Engn Res Ctr Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

In this paper, we propose an undirected model of learning systems, named max-min-degree neural network, to realize centralized-decentralized collaborative computing. The basic idea of the proposal is a max-min-degree constraint which extends a k-degree constraint to improve the communication cost, where k is a user-defined degree of neurons. The max-min-degree constraint is defined such that the degree of each neuron lies between k(min) and k(max). Accordingly, the Boltzmann machine is a special case of the proposal with k(min) = k(max) = n, where n is the full-connected degree of neurons. Evaluations show that the proposal is much better than a state-of-the-art model of deep learning systems with respect to the communication cost. The cost of the above improvement is slower convergent speed with respect to data size, but it does not matter in the case of big data processing.

关键词： big data cloud computing decentralized computing collaborative computing learning systems

来源：评论

学校读者我要写书评

暂无评论

Emergency communications leveraging decentralized swarm computing

Emergency communications leveraging decentralized swarm comp...

引用

Cyber-Physical Systems and Internet-of-Things Week (CPS-IoT Week)

作者： Kourtis, Michail Alexandros Xylouris, Georgios Kourtis, Anastasios Batistatos, Michael Markakis, Albertos Natl Ctr Sci Res Demokritos Athens Greece Univ Peloponnese Dept Informat & Telecommunicat Tripolis Greece Adrestia Private Co Iraklion Greece

ISBN: (纸本)9798400700491

Reliable and ubiquitous communications, offering high data rates, low latency and supporting large numbers of connected devices, are critical requirements for modern emergency rescue missions. Multiple teams of First Responders, operating at remote areas, on rough terrain or under harsh conditions (e.g. wildfires, earthquakes, flooding etc.) need seamless connectivity to send/receive mission data and organize their operations. decentralized swarm computing architectures offer a wide range of capabilities to enhance and accelerate edge processing for critical use case scenarios. This paper presents a converged approach on swarm computing and intelligence using decentralized Autonomous Organizations for emergency communications, and how a swarm of drones can leverage different edge accelerators for different applications.

关键词： Emergency communications drones swarm intelligence decentralized computing blockchain DAO

来源：评论

学校读者我要写书评

暂无评论

The Internet of AI Agents (IAIA): A New Frontier in Networked and Distributed Intelligence

引用

INTERNATIONAL JOURNAL OF NETWORKED AND DISTRIBUTED computing 2025年第1期13卷 1-11页

作者： Dazzi, Patrizio Univ Pisa Dept Comp Sci Largo Bruno Pontecorvo 3 I-56127 Pisa Italy

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) has led to the emergence of the Artificial Intelligence of Things (AIoT), a paradigm that enhances distributed intelligence across interconnected systems. This paper explores the evolutionary shift from AIoT towards the Internet of Artificial Intelligence Agents (IAIA), a transformative framework in which autonomous, networked AI agents engage in collaborative decision-making, real-time learning, and adaptive problem solving. By integrating edge computing, federated learning, and decentralized architectures, IAIA transcends the limitations of conventional IoT and AIoT models, enabling a scalable, resilient, and intelligent ecosystem. We analyze key enablers, including 5G/6G connectivity, blockchain for trust and security, and swarm intelligence for emerging behaviors. Furthermore, we discuss cross-domain applications that span smart cities, healthcare, industrial automation, and next-generation cyber-physical systems. Finally, we outline the critical challenges, such as governance, security, and ethical AI, and propose a roadmap for the widespread adoption of IAIA. This work provides a foundational perspective on the future of intelligent distributed systems, setting the stage for a new era of AI-driven, self-organizing networks.

关键词： Networked computing Internet of AI agents AIoT Distributed intelligence Edge AI Federated learning Autonomous systems Networked AI decentralized computing

来源：评论

学校读者我要写书评

暂无评论

Federated Fuzzy Clustering for decentralized Incomplete Longitudinal Behavioral Data

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第8期11卷 14657-14670页

作者： Ngo, Hieu Fang, Hua Rumbut, Joshua Wang, Honggang Univ Massachusetts Dartmouth Coll Engn N Dartmouth MA 02747 USA Univ Massachusetts Dartmouth Dept Comp & Informat Sci N Dartmouth MA 02747 USA Univ Massachusetts Chan Med Sch Dept Populat & Quantitat Hlth Sci Worcester MA 01655 USA Yeshiva Univ Katz Sch Sci & Hlth Dept Grad Comp Sci & Engn New York NY 10033 USA

The use of medical data for machine learning, including unsupervised methods, such as clustering, is often restricted by privacy regulations, such as the health insurance portability and accountability act (HIPAA). Medical data is sensitive and highly regulated and anonymization is often insufficient to protect a patient's identity. Traditional clustering algorithms are also unsuitable for longitudinal behavioral health trials, which often have missing data and observe individual behaviors over varying time periods. In this work, we develop a new decentralized federated multiple imputation-based fuzzy clustering algorithm for complex longitudinal behavioral trial data collected from multisite randomized controlled trials over different time periods. Federated learning (FL) preserves privacy by aggregating model parameters instead of data. Unlike previous FL methods, this proposed algorithm requires only two rounds of communication and handles clients with varying numbers of time points for incomplete longitudinal data. The model is evaluated on both empirical longitudinal dietary health data and simulated clusters with different numbers of clients, effect sizes, correlations, and sample sizes. The proposed algorithm converges rapidly and achieves desirable performance on multiple clustering metrics. This new method allows for targeted treatments for various patient groups while preserving their data privacy and enables the potential for broader applications in the Internet of Medical Things.

关键词： Behavior decentralized computing diet federated learning (FL) fuzzy clustering Internet of Medical Things (IoMT) longitudinal trial missing data

来源：评论

学校读者我要写书评

暂无评论

p2pGNN: A decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks

引用

IEEE ACCESS 2022年 10卷 34755-34765页

作者： Krasanakis, Emmanouil Papadopoulos, Symeon Kompatsiaris, Ioannis Ctr Res & Technol Hellas Inst Informat Technol Thessaloniki 57001 Greece

In this work, we aim to classify nodes of unstructured peer-to-peer networks with communication uncertainty, such as users of decentralized social networks. Graph Neural Networks (GNNs) are known to improve the accuracy of simple classifiers in centralized settings by leveraging naturally occurring network links, but graph convolutional layers are challenging to implement in decentralized settings when node neighbors are not constantly available. We address this problem by employing decoupled GNNs, where base classifier predictions and errors are diffused through graphs after training. For these, we deploy pre-trained and gossip-trained base classifiers and implement peer-to-peer graph diffusion under communication uncertainty. In particular, we develop an asynchronous decentralized formulation of diffusion that converges to centralized predictions in distribution and linearly with respect to communication rates. We experiment on three real-world graphs with node features and labels and simulate peer-to-peer networks with uniformly random communication frequencies;given a portion of known labels, our decentralized graph diffusion achieves comparable accuracy to centralized GNNs with minimal communication overhead (less than 3% of what gossip training already adds).

关键词： Peer-to-peer computing Training Social networking (online) Data models Computer architecture Protocols Predictive models decentralized computing machine learning network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Solving Large-Scale Robust Stability Problems by Exploiting the Parallel Structure of Polya's Theorem

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2013年第8期58卷 1931-1947页

作者： Kamyar, Reza Peet, Matthew M. Peet, Yulia Arizona State Univ Cybernet Syst & Controls Lab Dept Mech Engn Tempe AZ 85281 USA Arizona State Univ Sch Engn Matter Transport & Energy Engn Res Ctr Tempe AZ 85281 USA

In this paper, we propose a distributed computing approach to solving large-scale robust stability problems on the simplex. Our approach is to formulate the robust stability problem as an optimization problem with polynomial variables and polynomial inequality constraints. We use Polya's theorem to convert the polynomial optimization problem to a set of highly structured linear matrix inequalities (LMIs). We then use a slight modification of a common interior-point primal-dual algorithm to solve the structured LMI constraints. This yields a set of extremely large yet structured computations. We then map the structure of the computations to a decentralized computing environment consisting of independent processing nodes with a structured adjacency matrix. The result is an algorithm which can solve the robust stability problem with the same per-core complexity as the deterministic stability problem with a conservatism which is only a function of the number of processors available. Numerical tests on cluster computers and supercomputers demonstrate the ability of the algorithm to efficiently utilize hundreds and potentially thousands of processors and analyze systems with dimensional state-space. The proposed algorithms can be extended to perform stability analysis of nonlinear systems and robust controller synthesis.

关键词： decentralized computing large-scale systems polynomial optimization robust stability

来源：评论

学校读者我要写书评

暂无评论

A decentralized Communication-Efficient Federated Analytics Framework for Connected Vehicles

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第7期73卷 10856-10861页

作者： Zhao, Liang Valero, Maria Pouriyeh, Seyedamin Li, Fangyu Guo, Lulu Han, Zhu Kennesaw State Univ Dept Informat Technol Marietta GA 30060 USA Beijing Univ Technol Engn Res Ctr Digital Community Beijing Key Lab Computat Intelligence & Intelligen Minist EducFac Informat Technol Beijing 100124 Peoples R China Tongji Univ Dept Control Sci & Engn Shanghai 201804 Peoples R China Univ Houston Elect & Comp Engn Dept Houston TX 77004 USA

This letter presents a novel communication-efficient and decentralized approach for data analytics in connected vehicles. We extend the paradigm of federated learning (FL) to enable decentralized on-vehicle model training without a central server. To improve communication efficiency, we design a federated regularized nonlinear acceleration-based local training scheme to reduce the communication rounds and a random broadcast gossip-based mechanism to decrease the complexity per iteration. Experimental results demonstrate that our approach significantly reduces the communication cost compared to general gradient descent and momentum-based FL solutions and is promising for efficient data analytics in autonomous vehicle environments.

关键词： decentralized computing federated analytics smart connected vehicles decentralized computing federated analytics smart connected vehicles

来源：评论

学校读者我要写书评

暂无评论

Incentivizing Socio-Ethical Integrity in decentralized Machine Learning Ecosystems for Collaborative Knowledge Sharing

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第6期11卷 7857-7870页

作者： Chi, Yuanfang Zhang, Qiyue Sun, Jiaxiang Cai, Wei Wang, Z. Jane Leung, Victor C. M. Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China

To broaden domain knowledge and enable advanced analytics, machine learning (ML) algorithms increasingly utilize comprehensive datasets across diverse sectors. However, these disparate datasets held by various stakeholders raise concerns over data heterogeneity, privacy, and security. decentralized ML research aims to protect data privacy and integrate knowledge bases, especially knowledge graphs, to address data heterogeneity challenges. Yet, the question of how to foster trustworthy collaborations in decentralized ML ecosystems remains underexplored. This study pioneers two innovative socio-economic mechanisms designed to ensure dependable collaborations with socio-ethical integrity within a decentralized knowledge inference framework, enabling participants to share knowledge while maintaining data privacy and ethical standards. We employ an evolutionary game theory model to analyze the dynamic interactions between requestors and workers, focusing on achieving a stable equilibrium through theoretical and numerical evaluations. Furthermore, we explore how various critical factors, such as incentive schemes and the accuracy of identifying malicious workers, influence the system's equilibrium, providing insights into optimizing collaborative efforts in decentralized ML ecosystems.

关键词： Stakeholders Collaboration Knowledge graphs Cognition Machine learning algorithms Socioeconomics Security decentralized computing evolutionary game theory reputation system

来源：评论

学校读者我要写书评

暂无评论

Big Data Resource Management & Networks: Taxonomy, Survey, and Future Directions

引用

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS 2021年第4期23卷 2098-2130页

作者： Awaysheh, Feras M. Alazab, Mamoun Garg, Sahil Niyato, Dusit Verikoukis, Christos Univ Tartu Data Syst Grp EE-50090 Tartu Estonia Univ Santiago de Compostela Ctr Singular Invest Tecnol Intelixentes Santiago De Compostela 15782 Spain Charles Darwin Univ Coll Engn IT & Environm Casuarina NT 0810 Australia Univ Quebec Elect Engn Dept Ecole Technol Super Montreal PQ H3C 1K3 Canada Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Telecommun Technol Ctr Catalonia CTTC CERCA SMARTECH Dept Barcelona 08860 Spain

Big Data (BD) platforms have a long tradition of leveraging trends and technologies from the broader computer network and communication community. For several years, dedicated servers of homogeneous clusters were employed as the dominant paradigm in BD networks. In recent years, the BD landscape has changed, porting different deployment architectures with various network models. This trend has resulted in various associated opportunities and challenges that induce BD practitioners to achieve the next-generation BD vision. In particular, addressing the BD velocity with batch and micro-batch processing. Nevertheless, the literature misses an extensive study of the associated impacts of adopting these new deployment architectures, giving it holds a significant research interest. This study addresses the previous concern, offering a comprehensive review of the architectural elements of BD batch query deployment models and environments. A novel taxonomy is proposed to classify these models based on their underlying communication systems. We first discuss the batch query processing requirements as comparison criteria of BD communication models and compare their salient features. The benefits/challenges of these environments away from BD traditional on-premise dedicated clusters are presented. Thereafter, we provide an extensive survey of the modern BD deployment architectures, categorizing them based on their underlying infrastructure. Finally, several directions are outlined for future research on improving the state-of-the-art of BD landscape and provide recommendations for the BD practitioners on emerging environments supporting BD applications and the general large-scale data analytics.

关键词： Computer architecture Task analysis Resource management Taxonomy Tutorials Market research Data models Big data batch query systems resource management and communication computer network comparison cloud computing grid computing HPC decentralized computing hybrid computing

来源：评论

学校读者我要写书评

暂无评论

Autonomous decentralized structural health monitoring using smart sensors

引用

STRUCTURAL CONTROL & HEALTH MONITORING 2009年第7-8期16卷 842-859页

作者： Nagayama, T. Spencer, B. F., Jr. Rice, Jennifer A. Univ Illinois Dept Civil & Environm Engn Urbana IL 61801 USA Univ Tokyo Dept Civil Engn Bunkyo Ku Tokyo 1138656 Japan Texas Tech Univ Dept Civil & Environm Engn Lubbock TX 79409 USA

Though smart sensor technology has seen substantial advances during recent years, implementation of smart sensors on full-scale structures has been limited. Direct replacement of wired sensing systems with wireless sensor networks is not straightforward as off-the-shelf wireless systems are unlikely to provide the data users expect. The difficulty arises, in part, because centralized systems common for wired measurements are not scalable to large numbers of smart sensors. decentralized computing is required to harvest the rich information that a dense array of smart sensors can make available for structural health monitoring (SHM). decentralized system can be effectively managed by each sensor node and cluster autonomously performing tasks such as sensing and damage detection. Taking advantage of recent developments in middleware services which provide basic functionality for structural vibration measurements (e.g. synchronized sensing and reliable communication) this paper proposes an autonomous decentralized SHM approach using smart sensors. A set of algorithms that mesh well with the decentralized approach are first proposed and implemented on smart sensors. Finally, experimental validation of the implemented system is given and its damage detection capability is discussed. Copyright (C) 2009 John Wiley & Sons, Ltd.

关键词： structural health monitoring decentralized computing smart sensor

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：