检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Bora Yongacoglu Gürdal Arslan Lacra Pavel Serdar Yüksel Department of Electrical and Computer Engineering University of Toronto Department of Electrical Engineering University of Hawaii at Manoa Department of Mathematics and Statistics Queen’s University

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Weakly acyclic games generalize potential games and are fundamental to the study of game theoretic control. In this paper, we present a generalization of weakly acyclic games, and we observe its importance in multi-agent learning when agents employ experimental strategy updates in periods where they fail to best respond. While weak acyclicity is defined in terms of path connectivity properties of a game’s better response graph, our generalization is defined using a generalized better response graph. We provide sufficient conditions for this notion of generalized weak acyclicity in both two-player games and n-player games. To demonstrate that our generalization is not trivial, we provide examples of games admitting a pure Nash equilibrium that are not generalized weakly acyclic. The generalization presented in this work is closely related to the recent theory of satisficing paths, and the counterexamples presented here constitute the first negative results in that theory.

关键词： Sufficient conditions Games Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

GLOBAL LINEARIZATION WITHOUT HYPERBOLICITY

arXiv

引用

arXiv 2025年

作者： Kvalheim, Matthew D. Sontag, Eduardo D. Department of Mathematics and Statistics University of Maryland Baltimore CountyMD United States Departments of Electrical and Computer Engineering and Bioengineering Departments of Mathematics and Chemical Engineering Northeastern University BostonMA United States

We give a proof of an extension of the Hartman-Grobman theorem to nonhyperbolic but asymptotically stable equilibria of vector fields. Moreover, the linearizing topological conjugacy is (i) defined on the entire basin of attraction if the vector field is complete, and (ii) a Ck≥1 diffeomorphism on the complement of the equilibrium if the vector field is Ck and the underlying space is not 5-dimensional. We also show that the Ck statement in the 5-dimensional case is equivalent to the 4-dimensional smooth Poincaré conjecture. Copyright © 2025, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A data augmentation procedure to improve detection of spike ripples in brain voltage recordings

引用

Neuroscience Research 2025年 215卷 15-26页

作者： Schlafly, Emily D. Carbonero, Daniel Chu, Catherine J. Kramer, Mark A. Department of Mathematics and Statistics Boston University Boston MA United States Department of Biomedical Engineering Boston University Boston MA United States Department of Neurology Massachusetts General Hospital Boston MA United States Harvard Medical School Boston MA United States Center for Systems Neuroscience Boston University Boston MA United States

Epilepsy is a major neurological disorder characterized by recurrent, spontaneous seizures. For patients with drug-resistant epilepsy, treatments include neurostimulation or surgical removal of the epileptogenic zone (EZ), the brain region responsible for seizure generation. Precise targeting of the EZ requires reliable biomarkers. Spike ripples - high-frequency oscillations that co-occur with large amplitude epileptic discharges - have gained prominence as a candidate biomarker. However, spike ripple detection remains a challenge. The gold-standard approach requires an expert manually visualize and interpret brain voltage recordings, which limits reproducibility and high-throughput analysis. Addressing these limitations requires more objective, efficient, and automated methods for spike ripple detection, including approaches that utilize deep neural networks. Despite advancements, dataset heterogeneity and scarcity severely limit machine learning performance. Our study explores long-short term memory (LSTM) neural network architectures for spike ripple detection, leveraging data augmentation to improve classifier performance. We highlight the potential of combining training on augmented and in vivo data for enhanced spike ripple detection and ultimately improving diagnostic accuracy in epilepsy treatment. © 2024 The Authors

关键词： Deep Learning Detection Long Short-Term Memory Models Neural Networks Seizures Sharp Wave Ripples

来源：评论

学校读者我要写书评

暂无评论

ISUAM: Intelligent and Safe UAM with Deep Reinforcement Learning 29

ISUAM: Intelligent and Safe UAM with Deep Reinforcement Lear...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Garcia, Cristiano P. Weigang, Li Hirata, Nina S. T. Neumann, Clovis University of Brasilia Computer Science Department Brasília Brazil University of São Paulo Institute of Mathematics and Statistics São Paulo Brazil University of Brasilia Production Engineering Department Brasília Brazil

ISBN: (纸本)9798350330717

Urban air mobility (UAM) is on the verge of a fast-growing expansion as the major aircraft manufacturers are in the late-stage development of various Electric Vertical Take-Off and Landing (eVTOL) aircraft models. In recent decades, conflict detection and resolution (CD&R) in air traffic management has been widely studied. However, factors such as the wide availability of unmanned aerial vehicles (UAV), the expected use of eVTOL, and the latest development of groundbreaking deep reinforcement learning (DRL) have generated new interest in this research field. Some characteristics of this new aircraft type, such as weight, speed, and maneuverability, require a revisit of the CD&R for adaptation to the new paradigm. We propose an Intelligent and Safe UAM with Deep Reinforcement Learning (ISUAM) system that can perform tactical deviation maneuvers in the UAM environment using some latest DRL models. After extensive testing, including various DRL agents, Dueling Deep Q Networks (Dueling DQN) has provided the best performance and proved its ability to provide satisfactory conflict resolution. © 2023 IEEE.

关键词： Air Traffic Management eVTOL Leamig Reinforcement UAM

来源：评论

学校读者我要写书评

暂无评论

KEP-1.0: An Automatic Pipeline to Assist a Rapid Learning of COVID-19 Publications

KEP-1.0: An Automatic Pipeline to Assist a Rapid Learning of...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Shi, Jingyi Ghanbari, Ghodsieh Xia, Chao Mississippi State University Department of Mathematics and Statistics Mississippi StateMS United States Xiamen University Department of Software Engineering Xiamen Fujian China

ISBN: (纸本)9781665468190

Toward efficient learning of massive publications during the COVID-19 pandemic, we propose a pipeline, Knowledge Extraction for COVID-19 Publications (KEP), that aims at automatic extraction and representation of key knowledge from user-interested publications. The first version, KEP-1.0, has been developed and published on the Python Package Index (PyPI) (URL: https://***/project/KEP/). In this first release, knowledge about key topics, disease discussions, and location mentions for each publication is provided. KEP-1.0 not only extracts relevant knowledge but, more importantly, emphasizes the top discussed entities and presents visualizable plots, including bar graphs and word clouds. This allows a rapid preliminary understanding of the main discussions in the publication from these three aspects. Moreover, an enhanced TF-IDF algorithm, the weighted TF-IDF, targeting the publication topic identification purpose, has been proposed and evaluated. The pipeline is fully open-sourced and customizable. KEP-1.0 is ready for use in its current form or to be embedded into existing literature platforms. This pipeline is designed for COVID-related publications, but it has the potential to benefit similar knowledge extraction tasks for other topics of interest with a rapidly increasing number of publications. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Investigation of new solutions for an extended(2+1)-dimensional Calogero-Bogoyavlenskii-Schif equation

引用

Frontiers of mathematics in China 2021年第4期16卷 925-936页

作者： Mohamed R.ALI R.SADAT Wen-Xiu MA Department of Mathematics Faculty of EngineeringBenha UniversityEgypt Department of Mathematics Zagazig Faculty of EngineeringZagazig UniversityZagazigEgypt Department of Mathematics Zhejiang Normal UniversityJinhua 321004China Department of Mathematics King Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Mathematics and Statistics University of South FloridaTampaFL33620-5700USA School of Mathematics South China University of TechnologyGuangzhou 510640China School of Mathematical and Statistical Sciences North-West UniversityMafikeng CamusPrivate Bag X2046Mmabatho 2735South Africa

We investigate and concentrate on new infinitesimal generators of Lie symmetries for an extended(2+1)-dimensional Calogero-Bogoyavlenskii-Schif(eCBS)equation using the commutator table which results in a system of nonlinear ordinary differential equations(ODEs)which can be manually *** two stages of Lie symmetry reductions,the eCBS equation is reduced to non-solvable nonlinear ODEs using different combinations of optimal Lie *** the integration method and the Riccati and Bernoulli equation methods,we investigate new analytical solutions to those *** substituting to the original variables generates new solutions to the eCBS *** results are simulated through three-and two-dimensional plots.

关键词： Extended Calogero-Bogoyavlenskii-Schif(eCBS)equation Riccati-Bernoulli equation symmetry analysis integrating factor nonlinear integrable equations

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Game Theory for AI-Enabled Human-Robot Collaboration System Design in Industry 4.0 14

Deep Learning and Game Theory for AI-Enabled Human-Robot Col...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Xing, Yuan Hou, Dongfang Liu, Jason Yuan, Holly Verma, Abhishek Shi, Wei University of Wisconsin-Stout Engineering and Technology Department MenomonieWI54751 United States University of Wisconsin-Stout Operations & Management Department MenomonieWI54751 United States University of Wisconsin-Stout Mathematics Statistics Computer Science Department MenomonieWI54751 United States

ISBN: (纸本)9798350360134

In this paper, an optimization problem in a human-robot collaboration system is addressed. In Industry 4.0, mobile robots and stationary human workers work simultaneously in the same working environment. The robots have to determine the optimal path to move while avoiding colliding with the human workers and other robots. The challenge is for the robots to determine their optimal paths while avoiding collisions with both human workers and other robots. Traditional Deep Reinforcement Learning exhibits poor performance in this complex scenario, primarily due to slow convergence. To mitigate this issue, we propose a hybrid approach that combines Deep Reinforcement Learning with game theory. In the algorithm, first, a heuristic approach is used to evaluate the potential for collisions between robots. If no collision risk is detected, the Deep Reinforcement Learning algorithm is used to determine the optimal path for each robot in serial with the working environment updated iteratively. If the collision risk exists, a cooperative game is formulated within the Deep Reinforcement Learning algorithm framework to resolve the collision concern. The numerical results prove the superiority of the proposed algorithm in solving the distributed path planning problem for each robot compared with the state-of-the-art. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of multiclass classification techniques using dry bean dataset

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 6-20页

作者： Salauddin Khan, Md Nath, Tushar Deb Murad Hossain, Md Mukherjee, Arnab Bin Hasnath, Hafiz Manhaz Meem, Tahera Khan, Umama Statistics Discipline Science Engineering and Technology School Khulna University Khulna-9208 Bangladesh Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Modeling and Data Science University of Turin Italy Mathematics Discipline Science Engineering and Technology School Khulna University Khulna-9208 Bangladesh Biotechnology and Geneetic Engineering Discipline Life Science School Khulna University Khulna-9208 Bangladesh

Background: The application of classsification methods through multivariate and machine learning techniques has enormous significance in agricultural sector. It is vital to classify various types of seeds as well as identify the quality of seeds which has a great impact on the production of crops. There is a wide range of genetic variations in dry beans all over the world. Many studies have been conducted previously on various dataset to indentify the sorts of dry beans, however most of them focused on machine learning techniques with binary classification. Objective: The aim of this study is to investigate a reliable classifier which has the lowest noise implications and establish an algorithm for dry bean classification effectively. This paper focuses on outlier removals, oversampling with Adaptive Synthetic (ADASYN) algorithm and finding the best classifier to guarantee the highest possible accuracy. Methods: The raw dataset for this study was accessed from UCI Machine Learning Repository. The dataset contained grains having 16 features, 12 dimensions, and 4 distinct shapes. For the purpose of eliminating missing values from the dataset, interquartile range (IQR) with python programming was utilized. Eight most popular classifiers were used in this study which are Logistic Regression (LR), Naïve Bayes (NB), k-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Machine (SVM), and Multilayer Perception (MLP) with balanced and imbalanced classes. The authors utilized frequency tables, bar diagrams, boxplots, analysis of variance for descriptive analysis as well as data preprocessing. Results: The XGB classifier preferably outperformed than other classifiers with balanced and imbalanced distribution of dry beans within each class. It has acquired accuracy (ACC) 93.0% and 95.4% in imbalanced and balanced classes respectively. In case of balanced dataset, after application of ADASYN algorithm both KNN and RF t

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Globally Q-linear Gauss-Newton method for overparameterized non-convex matrix sensing 24

Globally Q-linear Gauss-Newton method for overparameterized ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xixi Jia Fangchen Feng Deyu Meng Defeng Sun School of Mathematics and Statistics Xidian University L2TI Laboratory University Sorbonne Paris Nord School of Mathematics and Statistics Xi'an Jiaotong University and Macao Institute of Systems Engineering Macau University of Science and Technology Department of Applied Mathematics The Hong Kong Polytechnic University

ISBN: (纸本)9798331314385

This paper focuses on the optimization of overparameterized, non-convex low-rank matrix sensing (LRMS)—an essential component in contemporary statistics and machine learning. Recent years have witnessed significant breakthroughs in firstorder methods, such as gradient descent, for tackling this non-convex optimization problem. However, the presence of numerous saddle points often prolongs the time required for gradient descent to overcome these obstacles. Moreover, over-parameterization can markedly decelerate gradient descent methods, transitioning its convergence rate from linear to sub-linear. In this paper, we introduce an approximated Gauss-Newton (AGN) method for tackling the non-convex LRMS problem. Notably, AGN incurs a computational cost comparable to gradient descent per iteration but converges much faster without being slowed down by saddle points. We prove that, despite the non-convexity of the objective function, AGN achieves Q-linear convergence from random initialization to the global optimal solution. The global Q-linear convergence of AGN represents a substantial enhancement over the convergence of the existing methods for the overparameterized non-convex LRMS. The code for this paper is available at https://***/hsijiaxidian/AGN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Flow Artist for High-Dimensional Cellular Data

A Flow Artist for High-Dimensional Cellular Data

引用

IEEE Workshop on Machine Learning for Signal Processing

作者： Kincaid MacDonald Dhananjay Bhaskar Guy Thampakkul Nhi Nguyen Joia Zhang Michael Perlmutter Ian Adelstein Smita Krishnaswamy Department of Mathematics Yale University Department of Genetics Yale School of Medicine Department of Computer Science Yale University Department of Mathematics Pomona College Applied Mathematics Program Yale University Department of Statistics University of Washington Department of Mathematics Boise State University Computational Biology and Bioinformatics Program Yale University

We consider the problem of embedding point cloud data sampled from an underlying manifold with an associated flow or velocity. Such data arises in many contexts where static snapshots of dynamic entities are measured, including in high-throughput biology such as single-cell transcriptomics. Existing embedding techniques either do not utilize velocity information or embed the coordinates and velocities independently, i.e., they either impose velocities on top of an existing point embedding or embed points within a prescribed vector field. Here we present FlowArtist, a neural network that embeds points while jointly learning a vector field around the points. The combination allows FlowArtist to better separate and visualize velocity-informed structures. Our results, on toy datasets and single-cell RNA velocity data, illustrate the value of utilizing coordinate and velocity information in tandem for embedding and visualizing high-dimensional data.

关键词：

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：