检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Yi, Xinlei Zavlanos, Michael M. Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Lab for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Mechanical Engineering and Material Science Duke University DurhamNC27708 United States

Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative impact of change to avoid potentially risky situations. In this paper, we investigate risk-averse online optimization where the distribution of the random cost changes over time. We minimize risk-averse objective function using the Conditional Value at Risk (CVaR) as risk measure. Due to the difficulty in obtaining the exact CVaR gradient, we employ a zeroth-order optimization approach that queries the cost function values multiple times at each iteration and estimates the CVaR gradient using the sampled values. To facilitate the regret analysis, we use a variation metric based on Wasserstein distance to capture time-varying distributions. Given that the distribution variation is sub-linear in the total number of episodes, we show that our designed learning algorithm achieves sub-linear dynamic regret with high probability for both convex and strongly convex functions. Moreover, theoretical results suggest that increasing the number of samples leads to a reduction in the dynamic regret bounds until the sampling number reaches a specific limit. Finally, we provide numerical experiments of dynamic pricing in a parking lot to illustrate the efficacy of the designed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Two-person Positive Shortest Path Games Have Nash Equilibria in Pure Stationary Strategies

arXiv

引用

arXiv 2024年

作者： Boros, Endre Elbassioni, Khaled Gurvich, Vladimir Vyalyi, Mikhail MSIS & RUTCOR Business School Rutgers University 100 Rockafellar Road PiscatawayNJ08854 United States Computer Science Department Khalifa University of Science and Technology Abu Dhabi127788 United Arab Emirates of National Research University Moscow Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Russia Department of Control and Applied Mathematics Moscow Institute of Physics and Technology Moscow Russia

We prove that every finite two-person shortest path game, where the local cost of every move is positive for each player, has a Nash equilibrium (NE) in pure stationary strategies, which can be computed in polynomial time. We also extend the existence result to infinite graphs with finite out-degrees. Moreover, our proof gives that a terminal NE (in which the play is a path from the initial position to a terminal) exists provided at least one of the two players can guarantee reaching a terminal. If none of the players can do it, in other words, if each of the two players has a strategy that separates all terminals from the initial position s, then, obviously, a cyclic NE exists, although its cost is infinite for both players, since we restrict ourselves to positive games. We conjecture that a terminal NE exists too, provided there exists a directed path from s to a terminal. However, this is open. We extend our result to short paths interdiction games, where at each vertex, we allow one player to block some of the arcs and the other player to choose one of the non-blocked arcs. Assuming that blocking sets are chosen from an independence system given by an oracle, we give an algorithm for computing a NE in time O(|E|(log |V | + τ)), where V is the set of vertices, E is the set of arcs, and τ is the maximum time taken by the oracle on any *** Codes 91A05 © 2024, CC BY.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Synergistically Learning Class-specific Tokens for Multi-class Whole Slide Image Classification

Synergistically Learning Class-specific Tokens for Multi-cla...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Pengzhong Sun Wei Wang Xiangyu Li Suyu Dong Shuo Li Kuanquan Wang Gongning Luo Faculty of Computing Harbin Institute of Technology Harbin China Faculty of Computing Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China Case School of Engineering Case Western Reserve University Cleveland USA

The application of transformer architecture in analyzing whole slide images (WSIs) has become increasingly popular due to its remarkable ability to learn complex associations. Nevertheless, a significant drawback emerges in the multiclass analysis of WSIs. The majority of the transformer-based methods available currently rely primarily on a single, class-agnostic token. This approach might not ideally capture the subtleties of class-discriminative information. To address this challenge, we present an innovative approach tailored for multi-class WSI analysis that harnesses the power of class-specific tokens. Central to our method is a novel attention mechanism designed to foster a synergistic learning relationship between patch and class tokens, enhancing the granularity of information captured and ensuring a more comprehensive representation of the WSI. Complementing this, we introduce a dynamic class-centric training strategy designed to optimize token representation learning, ensuring each token is informatively aligned with its corresponding class. Through extensive experimentation on three challenging multi-class WSI analysis datasets, our method consistently demonstrates superior performance, underscoring its potential as a robust solution for multi-class WSI analysis tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BDCP: An Improved Nested Named Entity Recognition Model Based on LSTM 6

BDCP: An Improved Nested Named Entity Recognition Model Base...

引用

6th IEEE International Conference on Data Science in Cyberspace, DSC 2021

作者： Zhou, Ling Luan, Tianjiao Yao, Na Li, Jianming Ding, Jie School Of Computer Science Guangzhou University Guangzhou China China Academy Of Launch Vehicle Technology Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9781665418157

In construction of knowledge graphs (KGs), named entity recognition (NER) is a sub-task to identify the boundaries of entities with special meaning and predict their categories in texts. The instance that an entity contains one or more entities is called nested entity. The current work on NER usually ignores the nested NER. We propose an improved model named Boundary Detection and Category Prediction (BDCP) for Nested NER. Our model uses LSTM to extract the contextual features of the sequence, and uses boundary detection unit to mark the boundaries of entities in the text. By introducing boundary detection unit, our model extracts the boundaries of entities and restrict the number of candidate entities. We also design a layer-by-layer decoding module by boundary detection unit for Nested NER. Experiments on Nested NER datasets named GENIA [1] demonstrate the effectiveness of our model on nested NER. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Data-driven SOC Estimation with Moving Window Adaptive Residual Generator for Li-ion Battery

Data-driven SOC Estimation with Moving Window Adaptive Resid...

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Xu, Xiaoyi Luo, Hao Wang, Hao Chow, Mo-Yuen Huang, Cong-Sheng Harbin Institute of Technology Department of Control Science and Engineering Harbin China North Carolina State University Department of Electrical and Computer Engineering RaleighNC United States

ISBN: (纸本)9781665401159

Lithium battery has been widely used in electric vehicle (EV) and microgrid applications as an outstanding energy storage device. To optimally control the batteries, the nonlinear battery dynamics and the battery State-of-Charge (SOC) need to be real-time and accurately estimated by the battery management systems (BMSs). Compared with traditional estimation algorithms, the observer-based adaptive residual generator has the advantages of small calculation amount, stability, and adaptability. It can accurately estimate the SOC of a battery with a high excited load current. However, in the case of a low excited load current, the SOC estimation effect is poor. Besides, as a data-driven algorithm, the adaptive residual generator's estimation effect will deteriorate when affected by measurement noise. This paper proposes a moving window scheme for the adaptive residual generator and analyzes the parameter setting range to ensure the stability and convergence of the algorithm, which provides guidance for parameter selection when applying the algorithm. On the one hand, the proposed moving window scheme effectively reduces the high excitation requirement of the adaptive residual generator for the load current. Even under low excitation, the moving window adaptive residual generator can still accurately estimate the SOC. On the other hand, the addition of a moving window effectively improves the anti-disturbance ability of the adaptive residual generator. The performance of the proposed method is verified by lithium battery simulation experiments. © 2021 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Drift With a Soft Actor-critic Reinforcement Learning Agent 20

Autonomous Vehicle Drift With a Soft Actor-critic Reinforcem...

引用

20th IEEE Jubilee World Symposium on Applied Machine Intelligence and Informatics, SAMI 2022

作者： Hunor Toth, Szilard Janos Viharos, Zsolt Bardos, Adam Institute of Computer Science and Control Research Laboratory on Engineering Management Intelligence Intelligent Processes Research Group Budapest Hungary John von Neumann University Faculty of Economics Kecskemét Hungary Budapest University of Technology and Economics Department of Automotive Technologies Budapest Hungary

ISBN: (纸本)9781665497046

Self-driving vehicles have become a more and more important field in recent years. Supported by the techniques of Artificial Intelligence (AI), the current tendency of positive results in applications is making it a promising area to focus further research. Additionally, Reinforcement Learning (RL) is already proved to be an efficient approach for complex problems, e.g. robots, industrial systems and also games (like chess, Go), *** is a driving technique at handling limits where the driver intentionally oversteers, with loss of traction, while driving the vehicle through the entirety of a corner. It is a very challenging control task and often results in an accident when it occurs on public roads, consequently, the efficient control of this motion is especially important in the safety of autonomous *** paper reports novel research results whose main goal is to develop a self-driving agent for drift motion control based on vehicle simulation by Matlab/Simulink. Longitudinal and lateral velocity together with the yaw rate formed the state representation of the vehicle. The agent action space consists of two continuous actuator values: pedal ratio and roadwheel angle. The goal of the agent is twofold: first, it has to jump into a drifting state, second, it has to keep the vehicle in *** simulation results show that the proposed Soft Actor-Critic (SAC) RL agent is capable of learning to approach a pre-determined drift equilibrium from cornering and staying in this drift situation as well. For the training, the solution excluded using any kind of prior data, it only works with information gained from the simulation model, which is a remarkable difference from the actual state-of-the-art RL-based solutions. © 2022 IEEE.

关键词： Training Roads Simulation Reinforcement learning Mathematical models Data models Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Sensor Fault Detection and Isolation in Autonomous Nonlinear Systems Using Neural Network-Based Observers

arXiv

引用

arXiv 2023年

作者： Cao, John Niazi, M. Umar B. Barreau, Matthieu Johansson, Karl Henrik Division of Decision and Control Systems Digital Futures KTH Royal Institute of Technology StockholmSE-100 44 Sweden Laboratory for Information & Decision Systems Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States

This paper presents a novel observer-based approach to detect and isolate faulty sensors in nonlinear systems. The proposed sensor fault detection and isolation (s-FDI) method applies to a general class of nonlinear systems. Our focus is on s-FDI for two types of faults: complete failure and sensor degradation. The key aspect of this approach lies in the utilization of a neural network-based Kazantzis- Kravaris/Luenberger (KKL) observer. The neural network is trained to learn the dynamics of the observer, enabling accurate output predictions of the system. Sensor faults are detected by comparing the actual output measurements with the predicted values. If the difference surpasses a theoretical threshold, a sensor fault is detected. To identify and isolate which sensor is faulty, we compare the numerical difference of each sensor meassurement with an empirically derived threshold. We derive both theoretical and empirical thresholds for detection and isolation, respectively. Notably, the proposed approach is robust to measurement noise and system uncertainties. Its effectiveness is demonstrated through numerical simulations of sensor faults in a network of Kuramoto oscillators. © 2023, CC BY.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Theory of phase reduction for systems with higher-order interactions: a route to Kuramoto models on hypergraphs

arXiv

引用

arXiv 2025年

作者： León, Iván Muolo, Riccardo Hata, Shigefumi Nakao, Hiroya Department of Applied Mathematics and Computer Science Universidad de Cantabria Santander39005 Spain Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Graduate School of Science and Engineering Kagoshima University Kagoshima890-0065 Japan Research Center for Autonomous Systems Materialogy Institute of Innovative Research Tokyo Institute of Technology Yokohama226-8501 Japan

Phase reduction is a powerful technique in the study of nonlinear oscillatory systems. Under certain assumptions, it allows us to describe each multidimensional oscillator by a single phase variable, giving rise to simple phase models such as the Kuramoto model. Classically, the method has been applied in the case where the interactions are only pairwise (two-body). However, increasing evidence shows that interactions in real-world systems are not pairwise but higher-order, i.e., many-body. Although synchronization in higher-order systems has received much attention, analytical results are scarce because of the highly nonlinear nature of the framework. In this paper, we fill the gap by presenting a general theory of phase reduction for the case of higher-order interactions. We show that the higher-order topology is preserved in the phase reduced model at the first order and that only odd couplings have an effect on the dynamics when certain symmetries are present. Additionally, we show the power and ductility of the phase reduction approach by applying it to a population of Stuart-Landau oscillators with an all-to-all configuration and with a ring-like hypergraph topology;in both cases, only the analysis of the phase model can provide insights and analytical results. © 2025, CC BY-NC-ND.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Modeling Method of Aircraft Simulation Based on Formal Description of Petri Net 18th

Modeling Method of Aircraft Simulation Based on Formal Des...

引用

18th Chinese Intelligent Systems Conference, CISC 2022

作者： Zhan, Tianming Huang, Yu Geng, Huapin Tong, Jiahui TAIJI Computer Co. Ltd Beijing100102 China Peking University Beijing100871 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100190 China Beijing Electro-Mechanical Engineering Institute Beijing102299 China

ISBN: (纸本)9789811962028

The simulation of aircraft guidance and control system has characteristics such as multiple model classification, large parameter influence,complex information interaction and so on. The traditional code-level model development method has many limitations, such as time consuming, low reusability, low modeling efficiency, and model quality can not be guaranteed. Based on the concurrency, graphic representation, mathematics and simulation characteristics of Petri net, this paper studies the aircraft simulation modeling method of formal description based on Petri net, constructs a general modeling development and integration software tool that can carry out component, parametric and graphical modeling, solves the problems of multi granularity model modeling and automatic generation of real-time simulation model code, and realizes the visual graphic modeling and comprehensive integration of different granularity models such as components, modules and meta models. The research method has been successfully applied in the simulation modeling of an aircraft. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Complex Permeability Determination for EE Core Based on Flexible PCB Fixture and Magnetic Flux Path Length Analysis

Complex Permeability Determination for EE Core Based on Flex...

引用

China Power Supply Society Electromagnetic Compatibility Conference (CPEMC)

作者： Huamin Jie Zhenyu Zhao Yongqi Chang Changdong Wang Shiqi Jiang Richard Xian-Ke Gao Kye Yak See School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Department of Electrical and Computer Engineering National Univeristy of Singapore Singapore Singapore Department of Control Science and Engineering Harbin Institute of Technology Harbin China School of Electronics and Information Engineering Harbin Institute of Technology Harbin China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China A*STAR Institute of High Performance Computing Singapore Singapore

ISBN: (数字)9798331509552

ISBN: (纸本)9798331509569

The complex permeability of magnetic cores acts as a vital factor in electromagnetic interference (EMI) filtering choke design and optimization. Many efforts have been reported for toroid cores, but fewer target those with other shapes, such as EE, EI, UU, and UI cores. Owing to their commonly used in planar EMI filters, determining the complex permeability of them is of significance. Targeting EE cores, this paper presents a flexible printed circuit board (PCB)-based fixture adapter tailored designed for performing the measurement, while the corresponding core permeability can be calculated through magnetic flux path length analysis. The experiments validate the effectiveness and accuracy of the proposed methods, spanning a wide frequency range up to 120 MHz.

关键词： Magnetic flux Accuracy Flexible printed circuits Magnetic cores Fixtures Electromagnetic interference Permeability measurement Length measurement Permeability Inductors

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：