检索结果-内蒙古大学图书馆

Human-Computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Behiye Sahin Ipek Neslihan Alpugan Aerospace Engineering Departmet Tarsus University Mersin Turkey Department of Computer Engineering Ankara University Ankara Turkey

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

Rapid urbanization and population growth have intensified transportation challenges and traffic safety concerns, driving advancements in autonomous driving systems and intelligent transportation systems (ITS). Within this context, accurate and efficient traffic sign detection plays a crucial role in enhancing road safety and optimizing traffic flow. This study presents an improved algorithm based on the YOLOv9 model, tailored for traffic sign detection in ITS applications. The proposed algorithm is evaluated against the baseline YOLOv9 model using a carefully prepared dataset, focusing on key performance metrics. Results demonstrate that the improved YOLOv9 model achieves approximately 3% enhancement in precision, recall, mean average precision (mAP), and F1 score compared to the original model. Furthermore, with a detection time of 8.22 ms, the algorithm is highly suitable for real-time applications. These findings underscore the potential of the enhanced YOLOv9 model in addressing critical ITS challenges and advancing the state-of-the-art in traffic sign detection.

关键词： YOLO Human computer interaction Urban areas Transportation approximation algorithms Real-time systems Road safety Safety Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning

引用

IEEE Transactions on Automatic Control 2025年

作者： Dai, Pengcheng Mo, Yuanqiu Yu, Wenwu Ren, Wei Southeast University School of Mathematics Nanjing210096 China Southeast University School of Mathematics Frontiers Science Center for Mobile Information Communication and Security Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China University of California Department of Electrical and Computer Engineering RiversideCA92521 United States

This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer from poor expression due to linear function approximation, we propose a distributed neural policy gradient algorithm that features two innovatively designed neural networks, specifically for the approximate $Q$-functions and policy functions of agents. This distributed neural policy gradient algorithm consists of two key components: the distributed critic step and the decentralized actor step. In the distributed critic step, agents receive the approximate $Q$-function parameters from their neighboring agents via a time-varying communication networks to collaboratively evaluate the joint policy. In contrast, in the decentralized actor step, each agent updates its local policy parameter solely based on its own approximate $Q$-function. In the convergence analysis, we first establish the global convergence of agents for the joint policy evaluation in the distributed critic step. Subsequently, we rigorously demonstrate the global convergence of the overall distributed neural policy gradient algorithm with respect to the objective function. Finally, the effectiveness of the proposed algorithm is demonstrated by comparing it with a centralized algorithm through simulation in the robot path planning environment. © 1963-2012 IEEE.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Primitive Agentic First-Order Optimization

Primitive Agentic First-Order Optimization

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： R. Sala Department of Mechanical and Process Engineering RPTU Kaiserslautern Germany

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Efficient numerical optimization methods can improve performance and reduce the environmental impact of computing in many applications. This work presents a proof-of-concept study combining primitive state representations and agent-environment interactions as first-order optimizers in the setting of budget-limited optimization. Through reinforcement learning (RL) over a set of training instances of an optimization problem class, optimal policies for sequential update selection of algorithmic iteration steps are approximated in generally formulated low-dimensional partial state representations that consider aspects of progress and resource use. For the investigated case studies, deployment of the trained agents to unseen instances of the quadratic optimization problem classes outperformed conventional optimal algorithms with optimized hyperparameters. The results show that elementary RL methods combined with succinct partial state representations can be used as heuristics to manage complexity in RL-based optimization, paving the way for agentic optimization approaches.

关键词： Training Optimization methods Reinforcement learning approximation algorithms Complexity theory Information technology Optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Curing and Network Design in SIS Epidemic Processes

Dynamic Curing and Network Design in SIS Epidemic Processes

引用

IEEE Conference on Decision and Control

作者： Yuhao Yi Liren Shan Philip E. Paré Karl H. Johansson Institute of Clinical Pathology West China Hospital and College of Computer Science Sichuan University Chengdu China Toyota Technological Institute at Chicago School of Electrical and Computer Engineering Purdue University West Lafayette IN USA Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and they are also affiliated with Digital Futures Stockholm Sweden

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper studies efficient algorithms for dynamic curing policies and the corresponding network design problems to guarantee fast extinction of epidemic spread in a Markov process-based susceptible-infected-susceptible (SIS) model. We provide a computationally efficient curing algorithm based on the curing policy proposed by Drakopoulos, Ozdaglar, and Tsitsiklis (2014). Since the corresponding optimization problem is NP-hard, finding optimal policies is intractable for large graphs. We provide approximation guarantees on the curing budget of the proposed dynamic curing algorithm. To avoid the waiting period included in the original curing policy, we study network design problems to reduce the total infection rate by deleting edges or reducing the weight of edges. To this end, we provide algorithms with provable guarantees. In summary, the proposed curing and network design algorithms together provide an effective and computationally efficient approach that mitigates SIS epidemic spread in networks.

关键词： Epidemics Heuristic algorithms Computational modeling Curing Markov processes approximation algorithms Linear programming Computational efficiency Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

MPC of Uncertain Nonlinear Systems with Meta-Learning for Fast Adaptation of Neural Predictive Models

MPC of Uncertain Nonlinear Systems with Meta-Learning for Fa...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Jiaqi Yan Ankush Chakrabarty Alisa Rupenyan John Lygeros Automatic Control Laboratory ETH Zurich Switzerland Mitsubishi Electric Research Laboratories Cambridge MA USA ZHAW Centre for Artificial Intelligence Zurich University of Applied Sciences Switzerland

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In this paper, we consider the problem of reference tracking in uncertain nonlinear systems. A neural State-Space Model (NSSM) is used to approximate the nonlinear system, where a deep encoder network learns the nonlinearity from data, and a state-space component captures the temporal relationship. This transforms the nonlinear system into a linear system in a latent space, enabling the application of model predictive control (MPC) to determine effective control actions. Our objective is to design the optimal controller using limited data from the target system (the system of interest). To this end, we employ an implicit model-agnostic meta-learning (iMAML) framework that leverages information from source systems (systems that share similarities with the target system) to expedite training in the target system and enhance its control performance. The framework consists of two phases: the (offine) meta-training phase learns an aggregated NSSM using data from source systems, and the (online) meta-inference phase quickly adapts this aggregated model to the target system using only a few data points and few online training iterations, based on local loss function gradients. The iMAML algorithm exploits the implicit function theorem to exactly compute the gradient during training, without relying on the entire optimization path. By focusing solely on the optimal solution, rather than the path, we can meta-train with less storage complexity and fewer approximations than other contemporary meta-learning algorithms. We demonstrate through numerical examples that our proposed method can yield accurate predictive models by adaptation, resulting in a downstream MPC that outperforms several baselines.

关键词： Training Metalearning Adaptation models Target tracking Transforms Predictive models Prediction algorithms approximation algorithms Data models Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Gradient matching of higher order combinatorial optimization in quadratic Ising machines

Gradient matching of higher order combinatorial optimization...

引用

IEEE International Conference on Rebooting Computing (ICRC)

作者： Dmitrii Dobrynin Mauricio Tedeschi Arne Heittmann John Paul Strachan PGI-14 Forschungszentrum Jülich GmbH Germany RWTH Aachen University Aachen Germany

ISBN: (数字)9798331541279

ISBN: (纸本)9798331541286

The key limitation of physics-inspired hardware accelerators such as Ising machines (IM) or Hopfield neural networks (HNN) is their lack of support of higher order couplings of spins/neurons. As a result, many classes of combinatorial optimization problems featuring polynomial interactions (PUBO) require quadratic hardware embeddings, QUBO mappings. Such embeddings were shown to risk severe performance reduction due to mismatched configuration space features (energy landscape) compared to the native space formulation. Here, we propose a gradient matching (GM) algorithm which leverages existing IM or in-memory HNN architectures and approximately recovers the native energy landscape. We show an exponential scaling advantage of the GM algorithm time-to-solution. Finally, we propose a hardware design to physically realize our GM in an HNN-based solver.

关键词： Couplings Adaptive systems Neuromorphic engineering Hopfield neural networks Computer architecture approximation algorithms Polynomials Optimization Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Adaptive Active Balancing in Battery Management Systems with Comprehensive System Modeling

Adaptive Active Balancing in Battery Management Systems with...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Wu Cong Lim Boon Chiat Terence Teo Xian Yang Lim Liter Siek Eng Leong Tan School of Electrical and Electronic Engineering Nanyang Technological University (NTU) Singapore

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

This paper presents a comprehensive design consideration crucial for effective cell balancing system design and an adaptive active cell balancing technique for lithium-ion batteries. The proposed method aims to mitigate state of charge (SOC) imbalances among battery cells, thereby improving overall battery performance and lifespan. The adaptive nature of the balancing algorithm ensures efficient and optimal balancing operations under varying battery conditions. Simulation results demonstrate the proposed adaptive active cell balancing technique reduced the charge transfer loss by approximately 16.47% as compared to the conventional active balancing.

关键词： Lithium-ion batteries Electric potential Adaptive systems Simulation Battery management systems Systems modeling approximation algorithms State of charge Charge transfer

来源：评论

学校读者我要写书评

暂无评论

Learned Finite-Time Consensus for Distributed Optimization

Learned Finite-Time Consensus for Distributed Optimization

引用

European Signal Processing Conference (EUSIPCO)

作者： Aaron Fainman Stefan Vlaski Department of Electrical and Electronic Engineering Imperial College London

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate of contraction determined by the mixing rate of the underlying network topology. For very sparse graphs this can yield a bottleneck, slowing down the convergence of the learning algorithm. We show that a sequence of matrices achieving finite-time consensus can be learned for unknown graph topologies in a decentralized manner by solving a constrained matrix factorization problem. We demonstrate numerically the benefit of the resulting scheme in both structured and unstructured graphs.

关键词： Network topology Signal processing algorithms Europe Signal processing approximation algorithms Topology Sparse matrices Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Simulation of Marketing Risk Prediction Model Based on K-Means Clustering Algorithm

Simulation of Marketing Risk Prediction Model Based on K-Mea...

引用

Software Engineering, Social Network Analysis and Intelligent Computing (SSAIC), Asia-Pacific Conference on

作者： Yun Zhang Yunnan Technology and Business University Kunming Yunnan China

ISBN: (数字)9798350393682

ISBN: (纸本)9798350393699

With the development of Internet technology, marketing is developing towards intelligence. On the one hand, social network based on Internet technology has become an important platform for marketing, which has attracted wide attention from industry and academia. On the other hand, the Internet makes information and data more transparent, and it can provide support for marketing decisions based on the mining and analysis of a large number of data. During the marketing period, enterprises will be affected by many different factors, which will also restrict the development of enterprise marketing work. In order to improve the advantages of enterprises in market competition, reasonable measures should be taken to complete the corresponding prediction and control. In this paper, factor indicators are extracted through factor analysis, and then K-means clustering algorithm is used to cluster the operation data of online loan platform based on the change of factor indicators. Finally, the risk of online loan platform is divided through the clustering results. In the process of estimating and calculating the parameters of the prediction model, a set of relatively optimal prediction parameters is determined by selecting an error criterion. Finally, the obtained model is verified and analyzed. The experimental results show that the linear prediction method can be used to establish the marketing prediction model, and the established prediction model has certain practical application value.

关键词： Analytical models Social networking (online) Software algorithms Clustering algorithms Predictive models Prediction algorithms approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Latency-aware Design for Computation Offloading and Content Caching in F-RANs

Latency-aware Design for Computation Offloading and Content ...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Xuewei Zhang Hongkun Yan Yuan Ren Fan Jiang Junxuan Wang School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

This paper investigates the joint computation offloading and content caching scheme in fog radio access networks (F-RANs), where users and fog nodes (FNs) are all endowed with caching and computing capabilities. The Kuhn-Munkres (KM) algorithm is first used to make the user-and-FN matching decisions. We then comprehensively reveal the service modes when a user receives the requested data to perform a computation task. The optimization problem of minimizing the task response latency is formulated under the constraints of limited cache sizes for users and FNs, aiming to yield the optimal decisions for computation offloading and content caching. The formulated problem is NPhard, and transformed into the convex form by introducing the methods of difference of convex (DC) function, successive convex approximation (SCA), and arithmetic geometric mean (AGM) inequality. Simulation results demonstrate the fast convergence speed of the proposed algorithm, and show superior latency performance of our designed scheme to the benchmarks.

关键词： Simulation Benchmark testing approximation algorithms Minimization Optimization Convergence Radio access networks Land mobile radio Arithmetic

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：