检索结果-内蒙古大学图书馆

11th Vienna International Conference on Mathematical Modelling, MATHMOD 2025

作者： Viehauser, Maximilian Bicher, Martin Rößler, Matthias Popper, Niki TU Wien Institute of Information Systems Engineering Favoritenstraße 9-11 Vienna1040 Austria DWH Simulation Services Neustiftgasse 57-59 Vienna1070 Austria

This study presents a novel approach for disaggregating aggregated train delays into primary and secondary components using Gated Graph Convolutional Networks (GatedGCNs). We develop a graph-based representation of railway traffic that captures complex spatiotemporal relationships and long-range dependencies. Our method is applied to synthetic delay data generated from an agent-based simulation model of the Austrian railway network. We evaluate the model on classification and regression tasks, demonstrating high accuracy in distinguishing between primary and secondary delays. The classification task achieves 96% accuracy and 0.99 AUC, while the regression task attains an R-squared value of 0.86. These results significantly outperform a naive baseline model. The findings suggest that GatedGCN is a promising method for delay disaggregation and has potential for broader applications in capturing delay propagation processes. However, while the results on synthetic data demonstrate strong performance, further validation on real-world data is essential to confirm its practical applicability. Copyright © 2025 The Authors.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling of Agent Decisions Using Conditional Generative Adversarial Networks 24

Modeling of Agent Decisions Using Conditional Generative Adv...

引用

Proceedings of the Winter simulation Conference

作者： Martin Bicher Dominik Brunmeir Niki Popper Institute for Information Systems Engineering TU Wien Vienna AUSTRIA Institute for Information Systems Engineering TU Wien Vienna AUSTRIA and dwh simulation services dwh GmbH Vienna AUSTRIA

ISBN: (纸本)9798331534202

In this paper, we investigate the use of Generative Adversarial Networks (GAN) to model agent behavior in agent-based models. We hereby focus on use cases in which an agent's decision-making process may only be modeled from data, but it is infeasible to be modeled causally. In these situations, meta-models are often the only way to quantitatively parameterize the agent-based model. However, methods that capture not only deterministic relationships but also stochastic uncertainty are rare. Since GANs are well known for their property to generate pseudo-random-numbers for complex distributions, we explore pros and cons of this strategy for modeling a delay-process in a large-scale agent-based SARS-CoV-2 simulation model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimation of the Parameters of the Havriliak-Negami Model for Breast Phantoms

Estimation of the Parameters of the Havriliak-Negami Model f...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Viktor Baranov Andrey Kuzmin Yury Smirnov Valeria Martynova Kseniya Demushkina Information- Measurement Systems and Metrology Penza State University Penza Russia Information and Computing Systems Penza State University Penza Russia Mathematics and Supercomputer Simulation Penza State University Penza Russia

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

This article is devoted to determining the parameters of the Havriliak- Negami dielectric model for breast phantoms using dielectric impedance spectroscopy. Experimental studies of homogeneous and inhomogeneous breast phantoms were conducted using a two-electrode capacitive sensor. The impedance components of the sensor with phantoms were measured using a precision RLC meter in the frequency range of up to 2 MHz. The original technique for processing the results of breast phantom bioimpedance measurements is based on the analytical solution of the inverse problem for the Havriliak-Negami model obtained by the authors and the use of the least squares method to optimize the parameters. The applicability of the model and the method for numerically finding its parameters was experimentally confirmed. The obtained model data coincide quite accurately with the experimental data. A number of statistical parameters, including the Hausdorff metric, were used for the assessment. The difference in the frequency response curves of the target inhomogeneous phantom by the MAEP parameter was about 0.2% for the $\mathcal{E}^{\prime}$ component and about 3.5% for the $\mathcal{E}^{\prime\prime}$ component, by the Hausdorff distance about 0.2 and about 0.007 for the $\mathcal{E}^{\prime}$ and $\mathcal{E}^{\prime\prime}$ components respectively.

关键词： Spectroscopy Biological system modeling Phantoms Breast Nonhomogeneous media Software Numerical models Dielectrics Impedance Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

Disaggregating Train Delays into Primary and Secondary Components using Gated Graph Convolutional Networks ⁎

引用

IFAC-PapersOnLine 2025年第1期59卷 439-444页

作者： Maximilian Viehauser Martin Bicher Matthias Rößler Niki Popper TU Wien Institute of Information Systems Engineering Favoritenstraße 9-11 1040 Vienna Austria DWH Simulation Services Neustiftgasse 57-59 1070 Vienna Austria

关键词： Graph Neural Networks Train Delay Disaggregation Gated Graph Convolutional Networks Railway systems Delay Propagation Synthetic Data Agent-Based simulation Machine Learning Transportation Networks Delay Management

来源：评论

学校读者我要写书评

暂无评论

Validation and Quantification of Possible Model Extensions for a Railway Operations Model Using Delay Data Disaggregation 24

Validation and Quantification of Possible Model Extensions f...

引用

Proceedings of the Winter simulation Conference

作者： Nadine Schwab Matthias Rößler Hannah Kastinger Günter Schneckenreither Matthias Wastian Niki Popper Institute for Information Systems Engineering TU Wien Vienna AUSTRIA and dwh Simulation Services dwh GmbH Vienna AUSTRIA dwh Simulation Services dwh GmbH Vienna AUSTRIA dwh Simulation Services dwh GmbH Vienna AUSTRIA and Institute of Statistics and Mathematical Methods in Economics TU Wien Vienna AUSTRIA Institute for Information Systems Engineering TU Wien Vienna AUSTRIA and dwh Simulation Services dwh GmbH Vienna AUSTRIA and Institute of Statistics and Mathematical Methods in Economics TU Wien Vienna AUSTRIA

ISBN: (纸本)9798331534202

In simulation of railway traffic, it is crucial to incorporate realistic delays. Delay data can be obtained from historical records containing scheduled and actual times of trains. Labelled or unlabelled with delay causes, these data do not consistently indicate whether a delay is secondary (e.g., caused by another delayed train) or primary (i.e., caused by external or unknown events) for a specific simulation application due to missing, inconsistent, and biased data. In a realistic simulation, only primary delays should be injected, whereas secondary delays emerge from the simulated dynamics. The authors developed an approach to differentiate between primary and secondary delays that is flexible in regard to simulated resources, performing a network analysis and using different thresholds for blocking trains. Finally, the disaggregated primary delays were inserted into a simulation model, showing that it can reproduce the actual total delays with reasonable errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biomedical Antenna Design Optimization Using Multi-Objective Inverse Neural Networks

引用

Progress in Electromagnetics Research C 2025年 154卷 47-59页

作者： Ben Melouka, Rania Ibtissam Tighilt, Yamina Zebiri, Chemseddine Karaçuha, Kamil Ferhat Hamida, Abdelhak Mashat, Arwa Alaoui, Nail Department of Electronics University of Ferhat Abbas Setif-1 Setif19000 Algeria Department of Electronics Faculty of Engineering University of Ferhat Abbas Setif-1 Setif19000 Algeria Electrical Engineering Department Istanbul Technical University Istanbul Turkey Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University P. O. Box 344 Rabigh21911 Saudi Arabia Laboratoire de Modélisation Simulation et Optimisation des Systèmes Complexes Réels University of Djelfa Djelfa17000 Algeria

A new approach based on an Inverse Artificial Neural Network (IANN) for Multi-Objective Antenna design is presented in this paper. The network sets geometrical variables as the output and uses three antenna performances as inputs. The proposed ANN model is structured into two distinct parts: In the first part, three autonomous branches establish the correlation among the S parameters, gain, specific absorption rate (SAR), and geometric variables of the antenna. The outputs of these branches are used as input in the second part to derive a distinctive solution for these geometric variables. The proposed antenna dimensions are 20 × 24 × 1.58 mm3, and an ultra-wideband of 4.1 GHz to 8.7 GHz is achieved in free space and on human tissue, which coincides with the 5.8 GHz ISM band. Body temperature and specific absorption rate are simulated using the suggested rectangular patch antenna. The resulting optimized antenna holds promising potential for biomedical applications. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

The co-evolution of East Asian subtropical westerly jet and East Asian summer monsoon during different time periods in the Holocene and its influence on precipitation patterns in China

引用

Science China Earth Sciences 2025年第4期68卷 1100-1115页

作者： Yawen LIU Mi YAN Jian LIU Sumin WANG Zhengyu LIU Liang NING Ziyi WANG Key Laboratory for Virtual Geographic Environment Ministry of Education/State Key Laboratory Cultivation Base of Geographical Environment Evolution and Regional Response/Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and ApplicationSchool of GeographyNanjing Normal UniversityNanjing210023China Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical SciencesNanjing Normal UniversityNanjing210023China Nanjing Institute of Geography and Limnology Chinese Academy of SciencesNanjing210008China Department of Geography The Ohio State UniversityColumbusOH43210USA

Generally,the interaction between the East Asian subtropical westerly jet(EASWJ)and the East Asian summer monsoon(EASM)is regarded as a critical dynamic factor in the evolution of precipitation patterns in *** simulation results from the transient climate evolution since the last glacial maximum,this study applies the multivariate empirical orthogonal function(MVEOF)analysis method to investigate the co-evolution relationships of the EASWJ and the EASM during the early,middle,and late Holocene,as well as their influence on precipitation patterns in *** results indicate that all the first MVEOF modes in different time periods of the Holocene display an out-of-phase relationship in the intensity anomaly between the EASWJ and the ***,the jet stream is wider and more tilted in the late *** the influence of secondary circulations formed during their co-evolution,a north-south dipolar precipitation pattern in eastern China(“flood in the south and drought in the north”or“drought in the south and flood in the north”)and an east-west dipolar pattern in northern China(“wet in the west and dry in the east”or“wet in the east and dry in the west”)are found in the early and middle Holocene,while in the late Holocene a regionally-consistent precipitation pattern is witnessed across the whole *** this mode,the precipitation in the middle and late Holocene is primarily dominated by trend *** second MVEOF mode reveals that the EASM weakens when the EASWJ shifts eastward and the jet steam axis shortens during the early Holocene,resulting in a north-south dipolar precipitation pattern in eastern China and a regionally-consistent pattern in northern *** the middle Holocene,dipolar precipitation patterns are also observed in both eastern China and northern China when the EASWJ moves northward and the EASM strengthens,while the moisture condition in North China is less pronounced,and vice *** the late Holocene,the intensity anomali

关键词： Holocene East Asian subtropical westerly jet East Asian summer monsoon Co-evolution Precipitation pattern

来源：评论

学校读者我要写书评

暂无评论

Editorial: Soil modeling and simulation for terramechanics applications of manned and unmanned autonomous vehicles

引用

Journal of Terramechanics 2025年 117卷

作者： Tekeste, Mehari Way, Thomas R. Alsaleh, Mustafa Physical Systems Modeling and Simulation of Agricultural and Off-Road Machinery Systems Department of Agricultural and Biosystems Engineering Iowa State University AmesIA United States USDA-ARS National Soil Dynamics Lab AuburnAL United States Information Technology Manager Data Warehouse and Business Intelligence GIS Caterpillar Inc. PeoriaIL United States

来源：评论

学校读者我要写书评

暂无评论

From active objects to autonomous agents

引用

IEEE CONCURRENCY 1999年第3期7卷 68-76页

作者： Guessoum, Z Briot, JP Objects and Agents for Simulation and Information Systems (OASIS) LIP6 Objects and Agents for Simulation and Information Systems (OASIS) Paris France

The authors describe how they extended a framework of active objects, named Actalk, into a generic multiagent platform, named DIMA. They discuss how they implemented this extension and report on one DIMA application t... 详细信息

关键词： Autonomous agents Object oriented modeling Appropriate technology Object oriented programming information systems Programming environments Computer languages Production facilities Design methodology Protocols

来源：评论

学校读者我要写书评

暂无评论

Development of a Hybrid Measurement System for Surgical Instrument Motion of Laparoscopic Surgery

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical Robotics and Bionics 2025年第2期7卷 550-561页

作者： Ebina, Koki Abe, Takashige Yan, Lingbo Hotta, Kiyohiko Kamijo, Chihiro Higuchi, Madoka Kon, Masafumi Kikuchi, Hiroshi Miyata, Haruka Matsumoto, Ryuji Osawa, Takahiro Murai, Sachiyo Kurashima, Yo Shichinohe, Toshiaki Watanabe, Masahiko Komizunai, Shunsuke Tsujita, Teppei Sase, Kazuya Chen, Xiaoshuai Senoo, Taku Shinohara, Nobuo Konno, Atsushi Hokkaido University Graduate School of Information Science and Technology Sapporo Japan Hokkaido University Faculty of Medicine Department of Renal and Genitourinary surgery Sapporo Japan Hokkaido University Clinical simulation center Faculty of Medicine Sapporo Japan Hokkaido University Faculty of Medicine Department of Gastroenterological Surgery II Sapporo Japan Hokkaido University Faculty of Medicine Department of Anatomy Sapporo Japan Kagawa University Faculty of Eenginerring and Design Takamatsu Japan National Defense Academy of Japan Department of Mechanical Engineering Yokosuka Japan Tohoku Gakuin University Department of Mechanical Engineering and Intelligent Systems Sendai Japan Hirosaki University Graduate School of Science and Technology Hirosaki Japan

Laparoscopic surgery has become a common surgical technique owing to its minimal invasiveness. However, surgeons require advanced techniques, and several studies have evaluated surgical skills through motion measurements to improve skill proficiency. However, existing measurement systems have a low tolerance for occlusion and are difficult to use in operating rooms with many obstacles. Therefore, a hybrid measurement system was developed for laparoscopic surgery. This system consists of an inertial measurement unit (IMU), a distance sensor, and an optical motion capture (MoCap). When MoCap data are unavailable, surgical instrument motion is calculated using the IMU and distance sensor data, and when it is available, the IMU drift is corrected using MoCap data. The MoCap markers were arranged individually, thus facilitating the measurement of multiple instruments simultaneously. The validation experiment in the wet-lab training confirmed that the error was smaller than that measured using MoCap alone, and the subjects expressed that the subjective disturbance caused by the sensors was very small during the procedure. The measurement experiment was conducted in cadaver surgical training, and 15 cases of nephrectomy were successfully recorded. This system facilitated highly accurate measurements during practical surgical training and surgical skills analysis. © 2018 IEEE.

关键词： Laparoscopy

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：