检索结果-内蒙古大学图书馆

FedScore: A privacy-preserving framework for federated scoring system development

JOURNAL OF BIOMEDICAL INFORMATICS 2023年第1期146卷 104485页

作者： Li, Siqi Ning, Yilin Ong, Marcus Eng Hock Chakraborty, Bibhas Hong, Chuan Xie, Feng Yuan, Han Liu, Mingxuan Buckland, Daniel M. Chen, Yong Liu, Nan Duke NUS Med Sch Ctr Quantitat Med 8 Coll Rd Singapore 169857 Singapore Duke NUS Med Sch Programme Hlth Serv & Syst Res Singapore Singapore Singapore Hlth Serv Hlth Serv Res Ctr Singapore Singapore Singapore Gen Hosp Dept Emergency Med Singapore Singapore Natl Univ Singapore Dept Stat & Data Sci Singapore Singapore Duke Univ Dept Biostat & Bioinformat Durham NC 27710 USA Duke Univ Sch Med Dept Emergency Med Durham NC USA Univ Penn Dept Biostat Epidemiol & Informat Philadelphia PA USA Natl Univ Singapore Inst Data Sci Singapore Singapore

Objective: We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations. Materials and methods: The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison. Results: We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models. Conclusion: This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

关键词： Clinical decision making distributed algorithm Electronic health record Electronic medical record Federated learning Scoring system

来源：评论

学校读者我要写书评

暂无评论

Hierarchical coordinated energy management strategy for electricity-hydrogen integrated charging stations based on IGDT and hybrid game

引用

ELECTRIC POWER SYSTEMS RESEARCH 2023年第1期223卷

作者： Cai, Pengcheng Mi, Yang Xing, Haijun Li, Dongdong Li, Hongzhong Wang, Peng Shanghai Univ Elect Power Shanghai 200090 Peoples R China Nanyang Technol Univ Singapore 639798 Singapore

The popularity of environment-friendly vehicles promotes the rapid development of electric and hydrogen integrated charging stations (EHI-CSs), which makes the power system face unprecedented challenges. Optimized and effective management strategies are needed to coordinate the operation among EHI-CSs and the distribution system operator (DSO). To this end, a bi-level energy management framework is proposed for DSO and EHI-CSs. The framework takes DSO as the leader of the upper game and provides dynamic differential pricing for EHI-CSs, while EHI-CSs work as the followers, react to the leader's decision in the manner of Nash-Harsanyi bargaining game. Moreover, aiming at the uncertainty of photovoltaic, a risk aversion robustness model for EHI-CSs is designed with information gap decision theory. A two-stage solution is proposed to solve the nonlinear bi-level programming problem with hierarchical energy interaction. Firstly, the lower-level energy cooperation is equivalent to two sub-problems of coalition's profit maximization and payment bargaining, the bisection approach is employed to distributed solve the energy pricing problem in the first stage with tie-line power and prices being the only exchange information. Then the second stage determines the payment according to the scheduling results. Numerical simulations verify the effectiveness of the proposed model and algorithm.

关键词： Electricity -hydrogen integrated charging stations Hierarchical hybrid game Peer -to -peer energy sharing Information gap decision theory distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

A localized algorithm for clustering in cognitive radio networks

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2021年第5期33卷 600-607页

作者： Kumar, Santosh Singh, Awadhesh Kumar Natl Inst Technol Dept Comp Engn Kurukshetra 136119 Haryana India

With the steep increase in wireless devices, the requirement of the spectrum has increased for communication. However, despite huge demand, the available spectrum is underutilized. The cognitive radio network (CRN) is more challenging environment as compared to conventional mobile ad hoc network because of node mobility and dynamic channel availability. Therefore, we propose a localized clustering scheme, which aims to provide better stability, scalability, efficient spectrum management, and reduce communication overhead. Each node computes its weight and shares with its one hop neighbours, and a node with maximal weight becomes the cluster head. Subsequently, the neighbour nodes sharing the channel(s) with a cluster head join it to form a cluster. To provide fault tolerance, vice-cluster head is also selected along with cluster head. We compare the performance of our protocol with competing protocols in the CRN. Finally, we present analytic as well as simulation study of our protocol and provide a method to handle the cluster dynamics. (c) 2018 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Cognitive radio networks Cognitive radio Clustering distributed algorithm Localized algorithm

来源：评论

学校读者我要写书评

暂无评论

Hierarchical game for integrated energy system and electricity-hydrogen hybrid charging station under distributionally robust optimization

引用

ENERGY 2023年第1期283卷

作者： Cai, Pengcheng Mi, Yang Ma, Siyuan Li, Hongzhong Li, Dongdong Wang, Peng Shanghai Univ Elect Power Shanghai 200090 Peoples R China Nanyang Technol Univ Singapore 639798 Singapore

To facilitate energy coupling and distributed coordinate the economic improvement needs of multi-stakeholders, a bi-level strategic operation framework is proposed for integrated energy system (IES) with electricity-hydrogen hybrid charging station (HCS) via utilizing the distributionally robust optimization (DRO) approach together with hierarchical game. Firstly, a Stackelberg game dynamic pricing strategy with the IES plays the leader at the upper level while the HCS is regarded as the follower at the lower level is established, in which electricity price and power are the only interactive information. Secondly, a comprehensive norm consisting of 1-norm and & INFIN;-norm is elaborately constructed as the uncertainty probability information ambiguity set to capture the uncertainty of intractable electric vehicles' type characteristics in the HCS. Besides, a solving technique of the bisection-based distributed algorithm combined with the column-and-constraint generation algorithm is presented to overcome the convergence difficulty in the two-stage mathematical programming model with lowerlevel nonconvex problems. Finally, numerical simulation results are conducted confirming the priority of the employed model and method in balancing conflicts of interest, compromising economy and robustness, as well as the computational efficiency of the algorithm.

关键词： Integrated energy system Electricity -hydrogen hybrid charging station Hierarchical game Distributionally robust optimization distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

Novel distributed Dynamic Backbone-based Flooding in Unstructured Networks

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2020年第3期13卷 872-889页

作者： Saeedvand, Saeed Aghdasi, Hadi S. Khanli, Leili Mohammad Univ Tabriz Fac Elect & Comp Engn Tabriz Iran

Resource discovery on different unstructured and dynamic networks such as grid, peer-to-peer, and cloud networks is an inevitable challenging issue. The primary method for resource discovery on the unstructured networks is flooding a query on the network. All existing flooding algorithms for unstructured networks generate almost high additional duplicated queries. This high duplication of the unstructured networks causes a lot of network traffic. This paper, therefore, proposes a novel flexible distributed Dynamic backbone-based Flooding (DDBF) algorithm for distributed unstructured networks. This paper explores Grid middleware, Peer-to-Peer (P2P) paradigm, and cloud networks resource discovery requirements and it proposes flooding algorithm based on the P2P networks using simulation. To evaluate and prove DDBF algorithm we, first, evaluated it on four fixed network topologies along with two different query flooder distributions, then we evaluated it with one dynamic network topology. The performance of the proposed DDBF algorithm was assessed with five different metrics. The result showed a dramatic decrease in the number of engaged flooder nodes, the number of duplicated queries and consequently, network delay compared with the state-of-the-art algorithms.

关键词： Resource Discovery Flooding Unstructured Dynamic Networks Peer-to-Peer Networks distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

distributed assignment with limited communication for multi-robot multi-target tracking

引用

AUTONOMOUS ROBOTS 2020年第1期44卷 57-73页

作者： Sung, Yoonchang Budhiraja, Ashish Kumar Williams, Ryan K. Tokekar, Pratap Virginia Tech Dept Elect & Comp Engn 1185 Perry St Blacksburg VA 24061 USA

We study the problem of tracking multiple moving targets using a team of mobile robots. Each robot has a set of motion primitives to choose from in order to collectively maximize the number of targets tracked or the total quality of tracking. Our focus is on scenarios where communication is limited and the robots have limited time to share information with their neighbors. As a result, we seek distributed algorithms that can find solutions in a bounded amount of time. We present two algorithms: (1) a greedy algorithm that is guaranteed to find a 2-approximation to the optimal (centralized) solution but requiring |R| communication rounds in the worst case, where |R| denotes the number of robots, and (2) a local algorithm that finds a are parameters that allow the user to trade-off the solution quality with communication time. In addition to theoretical results, we present empirical evaluation including comparisons with centralized optimal solutions.

关键词： Multi-robot system Task assignment distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

distributed Computation for Solving the Sylvester Equation Based on Optimization

引用

IEEE CONTROL SYSTEMS LETTERS 2020年第2期4卷 414-419页

作者： Deng, Wen Zeng, Xianlin Hong, Yiguang Univ Chinese Acad Sci Sch Math Sci Beijing 100190 Peoples R China Chinese Acad Sci Acad Math & Syst Sci Key Lab Syst & Control Beijing 100190 Peoples R China Beijing Inst Technol Sch Automat Key Lab Intelligent Control & Decis Complex Syst Beijing 100081 Peoples R China

This letter solves the Sylvester equation in the form of AX + XB = C in a distributed way, and proposes a distributed continuous-time algorithm when there is at least one exact solution to the equation. Based on local information and appropriate communication among neighbor agents, we solve the distributed computation problem of the Sylvester equation from the optimization viewpoint, and we design a distributed algorithm based on the saddle-point dynamics and derivative feedback. Finally, we prove the exponential convergence of the proposed algorithm to an optimal solution with help of the convex optimization and semi-stability theory.

关键词： distributed algorithm Sylvester equation convex optimization derivative feedback semi-stability

来源：评论

学校读者我要写书评

暂无评论

distributed Heavy-Ball Nash Equilibrium Seeking algorithm in Aggregative Games

Distributed Heavy-Ball Nash Equilibrium Seeking Algorithm in...

引用

第三十九届中国控制会议

作者： Chenhui Song Chenpeng Wu Zhongtao Lv Fangshuo Zhang Jingyu Li Shaofu Yang Chien-Shiung Wu College Southeast University School of Economics and Management Southeast University School of Computer Science and Engineering Southeast University

In this paper, we address the distributed Nash equilibrium seeking problem in an aggregative game, in which each agent is required to optimize a self-interested objective function that depends on both its own decision and the aggregate of all agents' decisions. By integrating the heavy-ball method with consensus-based gradient method, a novel distributed algorithm is proposed for seeking the Nash equilibrium with an improved convergence rate. Rigorous theoretical analysis is provided to prove the convergence of the algorithm. Finally, detailed numerical simulation results are provided to show the effectiveness and the acceleration performance of our algorithm.

关键词： Aggregative Game Nash Equilibrium Seeking distributed algorithm Heavy-Ball Method

来源：评论

学校读者我要写书评

暂无评论

A Fully distributed algorithm for Dynamic Channel Adaptation in Canonical Communication Networks

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2013年第5期2卷 491-494页

作者： Zheng, Jianchao Cai, Yueming Yang, Wendong Wei, Yi Yang, Weiwei PLA Univ Sci & Technol Coll Commun Engn Nanjing 210007 Jiangsu Peoples R China

In this letter, a low-complexity, fully distributed algorithm is designed for dynamic channel adaptation in a canonical communication network, where each player can independently update its action without any information exchange. Both the static and dynamic channel environments are studied. The proposed algorithm converges to a set of correlated equilibria with probability one. Moreover, the optimality property of the problem is analyzed. Simulation results demonstrate that the proposed algorithm achieves a near-optimal performance for interference mitigation.

关键词： distributed algorithm dynamic channel allocation correlated equilibrium interference mitigation

来源：评论

学校读者我要写书评

暂无评论

Regularized dual gradient distributed method for constrained convex optimization over unbalanced directed graphs

引用

NUMERICAL algorithmS 2020年第1期84卷 91-115页

作者： Gu, Chuanye Wu, Zhiyou Li, Jueyou Cutin Univ Dept Math & Stat Perth WA 6845 Australia Chongqing Normal Univ Sch Math Sci Chongqing 400047 Peoples R China

This paper investigates a distributed optimization problem over a cooperative multi-agent time-varying network, where each agent has its own decision variables that should be set so as to minimize its individual objective subjected to global coupled constraints. Based on push-sum protocol and dual decomposition, we design a regularized dual gradient distributed algorithm to solve this problem, in which the algorithm is implemented in unbalanced time-varying directed graphs only requiring the column stochasticity of communication matrices. By augmenting the corresponding Lagrangian function with a quadratic regularization term, we first obtain the bound of the Lagrangian multipliers which does not require constructing a compact set containing the dual optimal set when compared with most of primal-dual based methods. Then, we obtain that the convergence rate of the proposed method can achieve the order of O(lnT/T) for strongly convex objective functions, where T is the number of iterations. Moreover, the explicit bound of constraint violations is also given. Finally, numerical results on the network utility maximum problem are used to demonstrate the efficiency of the proposed algorithm.

关键词： Convex optimization distributed algorithm Dual decomposition Regularization Multi-agent network

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：