检索结果-内蒙古大学图书馆

A Pavement Crack Detection Method Based on Multiscale Attention and HFS

Computational Intelligence and Neuroscience 2022年 2022卷 1822585页

作者： Li, Chun Wen, Yu Shi, Qingxuan Yang, Fang Ma, Hongyan Tian, Xuedong School of Cyber Security and Computer Hebei University Baoding071002 China Hebei Machine Vision Engineering Research Center Hebei University Baoding071002 China Institute of Intelligent Image and Document Information Processing Hebei University Baoding071002 China School of Mathematics and Information Science Hebei University Baoding071002 China

To solve the problem of low detection accuracy due to the loss of detailed information when extracting pavement crack features in traditional U-shaped networks, a pavement crack detection method based on multiscale attention and hesitant fuzzy set (HFS) is proposed. First, the encoding-decoding structure is used to construct a pavement crack segmentation network, ResNeXt50 is used to extract features in the encoding stage, and a multiscale feature fusion module (MFF) is designed to obtain multiscale context information. Second, in the decoding stage, a high-efficiency dual attention module (EDA) is used to enhance the ability of capturing details of the cracks while suppressing background noise. Finally, the membership degree of the crack is calculated based on the advantages of the HFS in multiattribute decision-making to obtain the similarity of the crack, and the binary image after segmentation is judged by the hesitation fuzzy measure. The experiment was conducted on the public road crack dataset Crack500. In terms of segmentation performance, the evaluation indexes Intersection over Union (IoU), Precision, and Dice coefficients of the proposed network reached 55.56%, 74.26%, and 67.43%, respectively;in terms of classification performance, for transversal and longitudinal cracks, the classification accuracy was 84% ± 0.5%, while the block and the alligator were both 78% ± 0.5%. The experimental results prove that the crack details detected by the proposed method are more abundant, and the image detection effect of complex topological structures and small cracks are better. © 2022 Chun Li et al.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Interval and -interval rational parking functions

arXiv

引用

arXiv 2023年

作者： Aguilar-Fraga, Tomás Elder, Jennifer Garcia, Rebecca E. Hadaway, Kimberly P. Harris, Pamela E. Harry, Kimberly J. Hogan, Imhotep B. Johnson, Jakeyl Kretschmann, Jan Lawson-Chavanu, Kobe Carlos Martínez Mori, J. Monroe, Casandra D. Quiñonez, Daniel Tolson, Dirk Williams, Dwight Anderson Department of Mathematics Harvey Mudd College ClaremontCA United States Department of Computer Science Mathematics and Physics Missouri Western State University MO United States Department of Mathematics and Computer Science Colorado College Colorado SpringsCO United States Department of Mathematics Iowa State University AmesIA United States Department of Mathematical Sciences University of Wisconsin-Milwaukee MilwaukeeWI United States Department of Mathematics Florida A&M University TallahasseeFL United States Department of Mathematics San Francisco State University San FranciscoCA United States Department of Mathematics Emory College AtlantaGA United States H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA United States Department of Mathematics University of Texas at Austin AustinTX United States Department of Mathematics UC Irvine IrvineCA United States Department of Mathematics and statistics Sonoma State University Rohnert ParkCA United States Department of Mathematics Morgan State University BaltimoreMD United States

Interval parking functions are a generalization of parking functions in which cars have an interval preference for their parking. We generalize this definition to parking functions with n cars and m ≥ n parking spots, which we call interval rational parking functions and provide a formula for their enumeration. By specifying an integer parameter ≥ 0, we then consider the subset of interval rational parking functions in which each car parks at most spots away from their initial preference. We call these -interval rational parking functions and provide recursive formulas to enumerate this set for all positive integers m ≥ n and . We also establish formulas for the number of nondecreasing -interval rational parking functions via the outcome map on rational parking functions. We also consider the intersection between -interval parking functions and Fubini rankings and show the enumeration of these sets is given by generalized Fibonacci numbers. We conclude by specializing = 1, and establish that the set of 1-interval rational parking functions with n cars and m spots are in bijection with the set of barred preferential arrangements of [n] with m−n bars. This readily implies enumerative formulas. Further, in the case where = 1, we recover the results of Hadaway and Harris that unit interval parking functions are in bijection with the set of Fubini rankings, which are enumerated by the Fubini *** Codes 05A05, 05A15, 05A18, 05A19 Copyright © 2023, The Authors. All rights reserved.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

Analysis of temperature-sensitive on short-term electricity load forecasting 4

Analysis of temperature-sensitive on short-term electricity ...

引用

2020 IEEE-HYDCON International Conference on engineering in the 4th Industrial Revolution, HYDCON 2020

作者： Tung, Nguyen Xuan Dat, Nguyen Quang Thang, Tran Ngoc Solanki, Vijender Kumar Anh, Nguyen Thi Ngoc Cmc Corporation Hanoi Viet Nam Hanoi University of Science Technology School of Applied Mathematics and Informatics Hanoi Viet Nam Cmr Institute of Technology Dept of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9781728149943

Short-termelectricityloadforecastingisessentialfor the operating energy of a nation. Accuracy of forecasting is important for power operation however it is dependent on weather. This paper focuses on model sensitive analysis temperature on short-term electricity load forecasting. The new models have proposed to analyze the effect of temperature on the electricity load forecasting. In detail, three methods (linear regression, local method and Monte Carlo) are analysis for temperature-sensitive on short-term electricity load forecasting. Then, the proposed models are applied to Vietnam electricity load forecasting. Index Terms-Sensitive Analysis, Electricity load forecasting, Short-term forecasting, Temperature effect, Regression © 2020 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

GLAD: LEARNING SPARSE GRAPH RECOVERY 8

GLAD: LEARNING SPARSE GRAPH RECOVERY

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Shrivastava, Harsh Chen, Xinshi Chen, Binghong Lan, Guanghui Aluru, Srinivas Liu, Han Song, Le School of Computational Science & Engineering Georgia Institute of Technology United States School of Mathematics Georgia Institute of Technology United States School of Industrial and Systems Engineering Georgia Institute of Technology United States Computer Science Department Northwestern University United States Ant Financial Services Group

Recovering sparse conditional independence graphs from data is a fundamental problem in machine learning with wide applications. A popular formulation of the problem is an `1 regularized maximum likelihood estimation. Many convex optimization algorithms have been designed to solve this formulation to recover the graph structure. Recently, there is a surge of interest to learn algorithms directly based on data, and in this case, learn to map empirical covariance to the sparse precision matrix. However, it is a challenging task in this case, since the symmetric positive definiteness (SPD) and sparsity of the matrix are not easy to enforce in learned algorithms, and a direct mapping from data to precision matrix may contain many parameters. We propose a deep learning architecture, GLAD, which uses an Alternating Minimization (AM) algorithm as our model inductive bias, and learns the model parameters via supervised learning. We show that GLAD learns a very compact and effective model for recovering sparse graphs from data. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Identifiable Latent Causal Content for Domain Adaptation under Latent Covariate Shift

arXiv

引用

arXiv 2022年

作者： Liu, Yuhang Zhang, Zhen Gong, Dong Gong, Mingming Huang, Biwei van den Hengel, Anton Zhang, Kun Shi, Javen Qinfeng Australian Institute for Machine Learning The University of Adelaide Australia School of Computer Science and Engineering The University of New South Wales Australia School of Mathematics and Statistics The University of Melbourne Australia Halicioğlu Data Science Institute University of California San Diego United States Department of Philosophy Carnegie Mellon University United States

Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain by leveraging both the labeled data from multiple source domains and the unlabeled data from the target domain. Conventional MSDA approaches often rely on covariate shift or conditional shift paradigms, which assume a consistent label distribution across domains. However, this assumption proves limiting in practical scenarios where label distributions do vary across domains, diminishing its applicability in real-world settings. For example, animals from different regions exhibit diverse characteristics due to varying diets and genetics. Motivated by this, we propose a novel paradigm called latent covariate shift (LCS), which introduces significantly greater variability and adaptability across domains. Notably, it provides a theoretical assurance for recovering the latent cause of the label variable, which we refer to as the latent content variable. Within this new paradigm, we present an intricate causal generative model by introducing latent noises across domains, along with a latent content variable and a latent style variable to achieve more nuanced rendering of observational data. We demonstrate that the latent content variable can be identified up to block identifiability due to its versatile yet distinct causal structure. We anchor our theoretical insights into a novel MSDA method, which learns the label distribution conditioned on the identifiable latent content variable, thereby accommodating more substantial distribution shifts. The proposed approach showcases exceptional performance and efficacy on both simulated and real-world datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Gentlest ascent dynamics on manifolds defined by adaptively sampled point-clouds

arXiv

引用

arXiv 2023年

作者： Bello-Rivas, Juan M. Georgiou, Anastasia Vandecasteele, Hannes Kevrekidis, Ioannis G. Department of Chemical and Biomolecular Engineering Whiting School of Engineering Johns Hopkins University 3400 North Charles Street BaltimoreMD21218 United States Department of Computer Science KU Leuven Celestijnenlaan 200A Leuven3001 Belgium Departments of Applied Mathematics and Statistics Johns Hopkins University 3400 North Charles Street BaltimoreMD21218 United States

Finding saddle points of dynamical systems is an important problem in practical applications such as the study of rare events of molecular systems. Gentlest ascent dynamics (GAD)1 is one of a number of algorithms in existence that attempt to find saddle points in dynamical systems. It works by deriving a new dynamical system in which saddle points of the original system become stable equilibria. GAD has been recently generalized to the study of dynamical systems on manifolds (differential algebraic equations) described by equality constraints2 and given in an extrinsic formulation. In this paper, we present an extension of GAD to manifolds defined by point-clouds, formulated using the intrinsic viewpoint. These point-clouds are adaptively sampled during an iterative process that drives the system from the initial conformation (typically in the neighborhood of a stable equilibrium) to a saddle point. Our method requires the reactant (initial conformation), does not require the explicit constraint equations to be specified, and is purely data-driven. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing nanofiltration for PFOS removal: A gradient boosting convolutional model approach

引用

Journal of Environmental Chemical engineering 2025年第4期13卷

作者： Junhua Xiao Heng Li Jianbin Hu Yunkun Wang Yunqian Wang Department of Computer Science and Technology School of Mathematics and Computer Sciences Nanchang University Nanchang 330031 China CAS Key Laboratory of Urban Pollutant Conversion Department of Environmental Science and Engineering University of Science & Technology of China Hefei 230026 China

The extensive utilization of perfluorooctane sulfonate (PFOS) has exerted significant repercussions on the global aquatic ecosystem. Nanofiltration (NF) emerges as a potent tool for PFOS removal; however, its efficacy is contingent upon various influencing factors. In order to enhance the performance of NF, this study employed a one-dimensional gradient-based convolutional neural network model (1D-GBCNN) to investigate the intricate correlation between membrane properties, operational conditions, and PFOS rejection rate. The objective was to elucidate the dynamic mechanism of PFOS inhibition under various operational scenarios. Our findings highlight the exceptional performance of the 1D-GBCNN model compared to traditional machine learning methods, achieving the highest coefficient of determination ( R 2 ) of 0.902 and the lowest root mean square error (RMSE) of 2.379 among all models evaluated. Employing the SHAP (SHapley Additive exPlanations) method unveils the pivotal role and hierarchical significance of individual parameters, and the results showed that membrane pore size, temperature, water flux, ion concentration and molecular weight cutoff were the key factors affecting PFOS removal. This investigation underscores the utility of the 1D-GBCNN model in furnishing actionable insights for optimizing NF process performance, thereby alleviating the experimental burden on researchers and is expected to contribute to the continued advancement of membrane filtration technology.

关键词： PFOS NF 1D-GBCNN

来源：评论

学校读者我要写书评

暂无评论

Mantaray Foraging Optimization based Makespan Enhancement in Cloud based Scheduling Environment

Mantaray Foraging Optimization based Makespan Enhancement in...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： J Aswini K. Johny Elma P. John Augustine N. Kopperundevi S. M. Chithra T. Parasuraman Saveetha Engineering College (Autonomous) Affiliated to Anna University Information Technology Easwari Engineering College Department of Information Technology Sri Eshwar College of Engineering Vadasithur-Via Kinathukadavu Coimbatore School of Computer Science and Engineering Vellore Institute of Technology Vellore Tamil Nadu Department Of Mathematics R. M. K. College of Engineering and Technology School of Physical Education & Sports Sciences Hindustan Institute of Technology & Science Chennai Tamil Nadu

ISBN: (纸本)9781665460859

Cloud computing (CC) delivers on-demand and powerful business environments. It can be constructed on top of virtualized data hubs. Virtualization renders a flexible infrastructure for cloud. However, scheduling the tasks and managing the resources in virtualized data hubs will be difficult. Maximizing the virtual machine utilization and minimizing the total makespan is imperative in the cloud environment. The task scheduling issue can be indicated as multi-objective optimization problem, which is solved by utilizing optimization methods. This study develops a Mantaray Foraging Optimization based Makespan Enhancement in Cloud based Scheduling Environment (MROME-CSE) technique. The presented MROME-CSE technique aims to allocate the resources proficiently in the cloud environment. In the presented MROME-CSE technique, the behavior of manta rays is mainly involved. Furthermore, the MROME-CSE method derived an objective function to allocate n individual tasks to m heterogeneous accessible resources, thereby task conclusion period was minimalized and resource was fully exploited. The experimental evaluation of the MROME-CSE technique is examined briefly. The experimental outcomes stated the superior performance of the MROME-CSE technique over other recent models.

关键词： Cloud computing Renewable energy sources Processor scheduling Computational modeling Optimization methods Linear programming Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Situation Awareness and Routing Challenges in Unmanned HAPS/UAV based Communications Networks

Situation Awareness and Routing Challenges in Unmanned HAPS/...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Ogbonnaya Anicho Philip B Charlesworth Gurvinder S Baicher Atulya Nagar School of Mathematics Computer Science and Engineering Liverpool Hope University

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

This paper examines Situation Awareness (SA) as a factor in addressing routing challenges in HAPS/UAV based networks especially in multi-HAPS/UAV implementations. Routing in UAV-based networks is a critical element for successful transmission of data from source to destination node. However, in UAV based networks the concept of routing assumes a more challenging dimension mainly due to the mobility of the vehicles or platforms. This paper highlights how situation awareness can impact routing decisions and consequently improve network throughput. It is suggested that SA should be considered a factor in mitigating routing challenges in UAV based networks.

关键词： Routing Routing protocols Unmanned aerial vehicles Decision making Ad hoc networks Network topology Topology

来源：评论

学校读者我要写书评

暂无评论

Semi-Markov Telecommunication Networks Model

Semi-Markov Telecommunication Networks Model

引用

International Conference on Actual Problems of Electron Devices engineering, (APEDE)

作者： Mikhail S. Svetlov Alexey A. L’vov Arman M. Martirosyan David M. Martirosyan Igor S. Bagaev Semen T. Khasanov Laboratory of Control and Automation Problems in Mechanical Engineering Institute of Precision Mechanics and Control of RAS Saratov Russian Federation Institute of Institute of Electronic Engineering and Instrumentation Yuri Gagarin State Technical University of Saratov Saratov Russian Federation Institute of Applied Information Technologies and Communications Yuri Gagarin State Technical University of Saratov Saratov Russian Federation Phystech-School of Applied Mathematics and Computer Science Moscow Institute of Physics and Technology Moscow Russian Federation

ISBN: (数字)9798350393316

ISBN: (纸本)9798350393323

This paper proposes a semi-Markov model of telecommunication network (TCN). The variant of dynamic traffic adaptive control of queuing system as a special case of TCN is considered. The main purpose of control is to minimize the average cost per unit of time to service the incoming flow of information (packets). This takes into account the different bandwidth of the channels, the processing speed of information in the channel and the information capacity of the buffers. The approach to the organization of dynamic control taking into account noise immunity (information reliability) and information security is discussed.

关键词： Adaptation models Costs Noise Information security Bandwidth Organizations Communications technology Telecommunication network reliability Adaptive control Electron devices

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：