检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Tian, Wan Qin, Zhongfeng School of Economics and Management Beihang University Beijing100191 China Key Laboratory of Complex System Analysis Management and Decision Beihang University Ministry of Education Beijing100191 China

Modeling and forecasting interval-valued time series (ITS) have attracted considerable attention due to their growing presence in various contexts. To the best of our knowledge, there have been no efforts to model large-scale ITS. In this paper, we propose a feature extraction procedure for large-scale ITS, which involves key steps such as auto-segmentation and clustering, and feature transfer learning. This procedure can be seamlessly integrated with any suitable prediction models for forecasting purposes. Specifically, we transform the automatic segmentation and clustering of ITS into the estimation of Toeplitz sparse precision matrices and assignment set. The majorization-minimization algorithm is employed to convert this highly non-convex optimization problem into two subproblems. We derive efficient dynamic programming and alternating direction method to solve these two subproblems alternately and establish their convergence properties. By employing the Joint Recurrence Plot (JRP) to image subsequence and assigning a class label to each cluster, an image dataset is constructed. Then, an appropriate neural network is chosen to train on this image dataset and used to extract features for the next step of forecasting. Real data applications demonstrate that the proposed method can effectively obtain invariant representations of the raw data and enhance forecasting performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Interval-Valued Time Series Classification Using DK-Distance

arXiv

引用

arXiv 2025年

In recent years, modeling and analysis of interval-valued time series have garnered increasing attention in econometrics, finance, and statistics. However, these studies have predominantly focused on statistical inference in the forecasting of univariate and multivariate interval-valued time series, overlooking another important aspect: classification. In this paper, we introduce a classification approach that treats intervals as unified entities, applicable to both univariate and multivariate interval-valued time series. Specifically, we first extend the point-valued time series imaging methods to interval-valued scenarios using the DK-distance, enabling the imaging of interval-valued time series. Then, we employ suitable deep learning model for classification on the obtained imaging dataset, aiming to achieve classification for interval-valued time series. In theory, we derived a sharper excess risk bound for deep multiclassifiers based on offset Rademacher complexity. Finally, we validate the superiority of the proposed method through comparisons with various existing point-valued time series classification methods in both simulation studies and real data applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Adaptive Classification of Interval-Valued Time Series

arXiv

引用

arXiv 2025年

In recent years, the modeling and analysis of interval-valued time series have garnered significant attention in the fields of econometrics and statistics. However, the existing literature primarily focuses on regression tasks while neglecting classification aspects. In this paper, we propose an adaptive approach for interval-valued time series classification. Specifically, we represent interval-valued time series using convex combinations of upper and lower bounds of intervals and transform these representations into images based on point-valued time series imaging methods. We utilize a fine-grained image classification neural network to classify these images, to achieve the goal of classifying the original interval-valued time series. This proposed method is applicable to both univariate and multivariate interval-valued time series. On the optimization front, we treat the convex combination coefficients as learnable parameters similar to the parameters of the neural network and provide an efficient estimation method based on the alternating direction method of multipliers (ADMM). On the theoretical front, under specific conditions, we establish a margin-based multiclass generalization bound for generic CNNs composed of basic blocks involving convolution, pooling, and fully connected layers. Through simulation studies and real data applications, we validate the effectiveness of the proposed method and compare its performance against a wide range of point-valued time series classification methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A model-free feature extraction procedure for interval-valued time series prediction

引用

Soft Computing 2025年第6期29卷 2727-2741页

作者： Tian, Wan Qin, Zhongfeng Hu, Tao School of Economics and Management Beihang University Beijing China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education Shanghai China Key Laboratory of Complex System Analysis Management and Decision (Beihang University) Beijing China School of Mathematical Sciences Capital Normal University Beijing China

We present a novel feature extraction procedure to predict interval-valued time series by combing transfer learning and imaging approaches. Initially, we represent interval-valued time series as a bivariate point-valued time series, and then transform each time series into images by employing imaging approaches such as recurrence plot, gramian angular summation/difference field, and Markov transition field, thereby obtaining an image dataset containing four classes. Based on this dataset, we train multiple candidate feature extraction networks, specifically ResNet with varying layers. Then we choose the penultimate layer of the feature extraction networks to extract the most relevant features from the images. To formulate prediction, we integrate the extracted features into a traditional prediction model. The proposed method are evaluated on three data-generating processes as well as the S&P 500 index, and the experimental results demonstrate a notable improvement in prediction performance compared to existing methods.

关键词： Feature extraction Imaging Interval-valued time series Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A model-free feature extraction procedure for interval-valued time series prediction

arXiv

引用

arXiv 2025年

作者： Tian, Wan Qin, Zhongfeng Hu, Tao School of Economics and Management Beihang University Beijing100191 China Key Laboratory of Complex System Analysis Management and Decision Beihang University Ministry of Education Beijing100191 China School of Mathematical Sciences Capital Normal University Beijing100048 China

In this paper, we present a novel feature extraction procedure to predict interval-valued time series by combing transfer learning and imaging approaches. Initially, we represent interval-valued time series using a bivariate point-valued time series, which serves as a representative form. We first transform each time series into images by employing various imaging approaches such as recurrence plot, gramian angular summation/difference field, and Markov transition field, and construct an image dataset by treating each imaging method’s output as a separate class. Based on this dataset, we train several candidates for a feature extraction network (FEN), specifically ResNet with varying layers. Then we choose the penultimate layer of the FEN to extract the most relevant features from the transformed images. We integrate the extracted features into conventional predictive models to formulate the corresponding prediction models. To formulate prediction, we integrate the extracted features into a regular prediction model. The proposed methods are evaluated based on the S&P 500 index and three data-generating processes (DGPs), and the experimental results demonstrate a notable improvement in prediction performance compared to existing methods. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertain queueing model with group arrivals

引用

Soft Computing 2024年第13-14期28卷 7999-8012页

作者： Liu, Yang Qin, Zhongfeng School of Economics and Management Beihang University Beijing100191 China Key Laboratory of Complex System Analysis Management and Decision Beihang University Beijing100191 China

The main goal of mathematical modeling and analysis of queueing systems is to understand the dynamic behavior of the underlying processes, enabling informed and intelligent management decisions. While the queueing systems with random factors have received extensive scrutiny, this paper introduces an uncertain queueing model that considers the belief degree of customer behavior. In this model, customers arrive in groups and the interarrival times and service times are treated as uncertain variables. To evaluate the performance of this proposed uncertain queueing model, the busy index and busy period are also discussed, and the analytical formulas and uncertainty distribution are derived respectively. Additionally, two numerical examples are also given to illustrate the obtained results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Content-sharing platforms’ copyright protection strategies with non-fungible tokens

引用

Electronic Commerce Research and Applications 2025年 71卷

作者： Ankai Li Li Wang Haijun Yang Harris Wu School of Economics and Management Beihang University Beijing 100191 China Key Laboratory of Complex System Analysis Management and Decision Ministry of Education Beihang University Beijing 100191 China Strome College of Business Old Dominion University Norfolk VA 23529 USA

The growth of content-sharing platforms facilitates the transfer of users to e-commerce sites. However, content-sharing platforms face copyright infringement issues related to content theft and platform invasion, dampening the flow of traffic to e-commerce. Traditional copyright protection methods lack effectiveness and efficiency, which can be solved by Non-Fungible Tokens (NFTs) stored on a blockchain. This study examines how a content-sharing platform adopts three NFT-based copyright protection strategies: the NFT-based copyright certification strategy to combat content theft, the NFT-based content moderation, and copyrighted material provision strategies to combat platform invasion. Our paper models a two-sided platform with content consumers and suppliers. Platform invasion occurs when suppliers bring copyright-infringing content to the platform, while content theft refers to content suppliers being pirated outside the platform. We identify the optimal combination of platform copyright protection strategies. The platform may adopt the copyright certification strategy to combat content theft. However, we show that the platform cannot benefit from adopting both content moderation and material provision strategies to counter platform invasion if the quantity of infringing materials used by infringers is small and the material provisioning costs of the platform are low. Moreover, there are mutually enhancing effects between content moderation and material provision strategies. Our study emphasizes the importance of NFT-based copyright protection strategies to content-sharing platforms and provides a comprehensive framework for understanding the implications of copyright certification, content moderation, and copyrighted material provision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-driven energy technology innovation: Dynamic impact and mechanism exploration

引用

Energy Economics 2025年 147卷

作者： Renbo Shi Wei Shan Richard Evans Qingjin Wang School of Economics and Management Beihang University Beijing China Key Laboratory of Complex System Analysis and Management Decision Ministry of Education Beijing China College of Digital Transformation Faculty of Computer Science Dalhousie University Halifax Canada Business School Qingdao University Qingdao China

Energy Technology Innovation (ETI) has received considerable attention in recent decades as firms strive to comply with pollution regulations and advance green transformation. This study investigates the dynamic impact of Artificial Intelligence (AI) on firm-level ETI and the mechanisms driving this relationship. The results show that AI positively contributes to ETI, although its effects exhibit a time lag, with the long-term impact being more significant. Specifically, AI exerts a more pronounced positive impact on renewable ETI compared to traditional ETI, guiding firms' innovation towards cleaner energy sources. The promotion of ETI by AI is found to be stronger in heavily polluted industries and geographical regions with greater openness. In addition, mechanism analysis demonstrates that AI primarily promotes ETI through enhanced Research and Development (R&D) activities, factor allocation effects, and increased financial opportunities. Furthermore, these AI-driven advancements in ETI contribute to improved energy efficiency. This study provides valuable guidance for firms seeking to effectively integrate AI into their ETI strategies and holds significant theoretical and practical implications for accelerating energy transformation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Passenger emergency evacuation from bus carriage:Results from realistic data and modeling simulations

引用

Journal of Management Science and Engineering 2022年第4期7卷 530-549页

作者： Hai-Hong Xu Ren-Yong Guo School of Economics and Management Beihang UniversityBeijing10191China Key Laboratory of Complex System Analysis and Management Decision Ministry of EducationBejing100191China

One of critical challenges in the development of pedestrian models is the lack of relevant data under emergency *** this paper,we reveal several behavior characteristics of passenger emergency evacuation from a burning bus carriage,by observing and analyzing a video recording,attempting to close the gap between practical observation and theoretical *** analysis results show that there are considerable differences between real emergency evacuation and experimental normal evacuation with respect to the cumulative flows,flows,and time gap ***,the behavior of falling-down,which contributes to the formation of movable obstacles,interrupts the continuity of the evacuation ***,we incorporate these behavioral characteristics into a microscopic pedestrian model with a fine lattice space *** simulation results indicate that the escape is slowed down by the falling behavior,as well as by the luggage-carrying behavior.

关键词： Emergency evacuation Bus passenger Egress behavior Movable obstacle Microscopic pedestrian model

来源：评论

学校读者我要写书评

暂无评论

SINGULAR DOUBLE PHASE EQUATIONS

引用

Acta Mathematica Scientia 2023年第3期43卷 1031-1044页

作者：刘振海 Nikolaos S.PAPAGEORGIOU Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal UniversityYulin537000China Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis Guangxi Minzu UniversityNanning530006China Department of Mathematics National Technical UniversityZografou Campus15780AthensGreece

We study a double phase Dirichlet problem with a reaction that has a parametric singular term. Using the Nehari manifold method, we show that for all small values of the parameter, the problem has at least two positiv... 详细信息

关键词： double phase singular term unbalanced growth Musielak-Orlice spaces Nehari manifold positive solutions

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：