检索结果-内蒙古大学图书馆

Efficient State Estimation of Discrete-Timed Automata 1

25th International Conference on Formal engineering Methods, ICFEM 2024

作者： Klein, Julian Kogel, Paul Glesner, Sabine Software and Embedded Systems Engineering TU Berlin Berlin Germany

ISBN: (数字)9789819606177

ISBN: (纸本)9789819606160

State estimation is a fundamental method in control theory that has applications in privacy, fault diagnosis, and the verification of other state inference properties. State estimation methods for timed automata rely on discretizing time into atomic steps. These discrete time steps are enumerated in separate states, significantly limiting scalability for large, realistic systems. In this paper, we propose a more efficient state estimation method for discrete-timed automata. The key idea of our approach is to avoid the enumeration of single time steps when possible. We provide a formal definition of a new state estimator model and an efficient algorithmic approach to derive it from discrete-timed automata. We validate our method on 11 realistic case studies and show a significant decrease in computational costs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Learning Mealy Machines with Local Timers 24th

Learning Mealy Machines with Local Timers

引用

24th International Conference on Formal engineering Methods, ICFEM 2023

作者： Kogel, Paul Klös, Verena Glesner, Sabine Software and Embedded Systems Engineering TU Berlin Berlin Germany TU Dresden Dresden Germany

ISBN: (纸本)9789819975839

Active automata learning (AAL) algorithms infer accurate automata models of black box applications, letting developers verify the behavior of increasingly complex real-time systems (RTS). However, learning models of larger RTS often takes very long or is not feasible at all. We introduce Mealy machines with local timers, a new class of Mealy machines that permit multiple location-bound timers and that can be learned efficiently. We design an efficient learning algorithm for them and validate our method across diverse case studies ranging from automotive systems to smart home appliances, where we drastically reduce runtimes compared to the state-of-the-art approach, thus, making AAL available for a wide range of RTS. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

A Distributed Task Scheduling Framework for Edge Computing and Cyber-Physical systems 49

A Distributed Task Scheduling Framework for Edge Computing a...

引用

49th Euromicro Conference on software engineering and Advanced Applications, SEAA 2023

作者： Monecke, Milko Gowtham, Varun Magedanz, Thomas Technische Universität Berlin Software and Embedded Systems Engineering Berlin Germany Berlin Germany

ISBN: (纸本)9798350342352

The continuously increasing amount of sensors in cyber-physical systems requires efficient edge computing architectures which follow the paradigm to process data where it emerges. Encapsulated software functions enable the unrestricted allocation of software functions to the edge, but lack real-time execution semantics and a real-time scheduling algorithm. In general, the allocation and scheduling of multiple constraint tasks in a distributed execution environment is classified as NP-complete. Nevertheless, by using prior knowledge, we are able to set up an optimal scheduling algorithm which leads to a highly reduced time complexity. Thus, our efficient approach enables modularity even for safety-critical real-time systems. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

TTT/ik: Learning Accurate Mealy Automata Efficiently with an Imprecise Symbol Filter 1

引用

23rd International Conference on Formal engineering Methods, ICFEM 2022

作者： Kogel, Paul Klös, Verena Glesner, Sabine Software and Embedded Systems Engineering TU Berlin Berlin Germany

ISBN: (数字)9783031172441

ISBN: (纸本)9783031172434

Active automata learning algorithms like TTT infer accurate automata models of black-box applications and thereby help developers to understand the behavior of increasingly complex cyber-physical systems. However, learning systems with large input alphabets often takes very long or is not feasible at all. We present TTT/ik, an extension of TTT that exploits an imprecise symbol filter that uses imprecise prior knowledge of state local alphabets to learn accurate Mealy automata more efficiently. We show across seven realistic case studies that our method almost always dramatically reduces queries and symbols even with imprecise knowledge, while still being accurate, thus, greatly improving runtime in practice. © 2022, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Multi-layer composite autoencoders for semi-supervised change detection in heterogeneous remote sensing images

引用

Science China(Information Sciences) 2023年第4期66卷 124-125页

作者： Jiao SHI Tiancheng WU Hanwen YU A.K.QIN Gwanggil JEON Yu LEI School of Electronics and Information Northwestern Polytechnical University School of Resources and Environment University of Electronic Science and Technology of China Department of Computer Science and Software Engineering Swinburne University of Technology Department of Embedded Systems Engineering Incheon National University

With the increasing complexity of application scenarios, the fusion of different remote sensing data types has gradually become a trend, which can greatly improve the utilization of massive remote sensing *** the problem of change detection for heterogeneous remote images can be much more complicated than the traditional change detection for homologous remote sensing images,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning based water leakage detection for shield tunnel lining

引用

Frontiers of Structural and Civil engineering 2024年第6期18卷 887-898页

作者： Shichang LIU Xu XU Gwanggil JEON Junxin CHEN Ben-Guo HE College of Computer Science Sichuan UniversityChengdu 610065China School of Computer Science and Engineering Northeastern UniversityShenyang 110004China Department of Embedded Systems Engineering Incheon National UniversityIncheon 22012Korea School of Software Dalian University of TechnologyDalian 116621China Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines Northeastern UniversityShenyang 110819China

Shield tunnel lining is prone to water leakage,which may further bring about corrosion and structural damage to the walls,potentially leading to dangerous *** avoid tedious and inefficient manual inspection,many projects use artificial intelligence(Al)to detect cracks and water leakage.A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this *** proposal includes a ConvNeXt-S backbone,deconvolutional-feature pyramid network(D-FPN),spatial attention module(SPAM).and a detection *** can extract representative features of leaking areas to aid inspection *** further improve the model's robustness,we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training *** experiments are performed,achieving the average precision(AP)score of 56.8%,which outperforms previous work by a margin of 5.7%.Visualization illustrations also support our method's practical effectiveness.

关键词： water leakage detection deep learning deconvolutional-feature pyramid spatial attention

来源：评论

学校读者我要写书评

暂无评论

Enhancing configurable limitless paths in virtual reality environments 2022

Enhancing configurable limitless paths in virtual reality en...

引用

15th Innovations in software engineering Conference, ISEC 2022

作者： Mittal, Raghav Karre, Sai Anirudh Gururaj, Y. Pawan Kumar Reddy, Y. Raghu Software Engineering Research Center IIIT Hyderabad India Center for VLSI Embedded Systems Technologies IIIT Hyderabad India

ISBN: (纸本)9781450396189

Locomotion in a virtual environment within a limited physical space is a complex activity. There exist established techniques to support limitless natural walking in virtual environments. These include Redirected walking, Dynamic path generation, and Walk-In-place technique, etc. PragPal is one such limitless path generation technique that supports natural walking in virtual environments. It is a novel software-based non-haptic locomotion technique. In this paper, we detail the enhancements to the existing PragPal path generation technique that addresses underlying issues in the technique like (1) path collision at angular turns, (2) effective usage of the physical play area, and (3) the ability to set path-width during path turns. © 2022 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZATION-BASED MOTION PRIMITIVE AUTOMATA FOR AUTONOMOUS DRIVING

arXiv

引用

arXiv 2024年

作者： Pedrosa, Matheus V.A. Scheffe, Patrick Alrifaee, Bassam Flabkamp, Kathrin Systems Modeling and Simulation Systems Engineering Saarland University Germany Embedded Software RWTH Aachen University Germany

Trajectory planning for autonomous cars can be addressed by primitive-based methods, which encode nonlinear dynamical system behavior into automata. In this paper, we focus on optimal trajectory planning. Since, typically, multiple criteria have to be taken into account, multiobjective optimization problems have to be solved. For the resulting Pareto-optimal motion primitives, we introduce a universal automaton, which can be reduced or reconfigured according to prioritized criteria during planning. We evaluate a corresponding multi-vehicle planning scenario with both simulations and laboratory experiments. © 2024, CC BY-NC-ND.

关键词： Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Self-Guided Autoencoders for Unsupervised Change Detection in Heterogeneous Remote Sensing Images

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2458-2471页

作者： Shi, Jiao Wu, Tiancheng Kai Qin, Alex Lei, Yu Jeon, Gwanggil Northwestern Polytechnical University School of Electronics and Information Xi'an710129 China Northwestern Polytechnical University in Shenzhen Research and Development Institute Shenzhen518057 China Chongqing Innovation Center of Northwestern Polytechnical University Chongqing401135 China Swinburne University of Technology Department of Computer Science and Software Engineering HawthornVIC3122 Australia Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

To address the problem of enormous differences in two heterogeneous images, the traditional unsupervised frameworks are most normally realized by converting two images into a common domain with various auxiliary strategies, such as transformation and alignment, which requires extensive calculation and has difficulty balancing the training tasks. To achieve a concise framework, this article proposes self-guided autoencoders (SGAE) for unsupervised change detection (CD) in heterogeneous remote sensing images (RSIs). Unlike traditional methods that aim to narrow the differences of heterogeneous images to highlight the changed information, SGAE forces the flow of identification in formation generated in unlabeled data through self-guided iterations. First, initial unsupervised networks output an elementary change map that will be screened to obtain reliable pseudolabels. The selected pseudolabeled samples will be used as the input of a supervised network to obtain another change map. Then, multiple change maps will be fused to refine the confidence of pseudolabels again, obtaining new fused pseudolabeled samples for the self-guided network, which will be trained with pseudolabeled samples and unlabeled samples. Finally, the above operations will be repeated to continuously optimize the net, which helps itself to extract the discriminative features for classification in self-guided iterations. Experiments compared with several algorithms on four datasets demonstrate the effectiveness and robustness of our method, which can help unsupervised models improve discriminative feature extraction and classification performance with a more flexible learning method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Online Learning and Continuous Model Upgrading with Data Streams Through the Kafka-Ml Framework

SSRN

引用

SSRN 2024年

作者： Carnero, Alejandro Martín, Cristian Jeon, Gwanggil Díaz, Manuel ITIS Software University of Malaga Malaga Spain Department of Embedded Systems Engineering Incheon National University Incheon Korea Republic of

A pipeline of unbroken data streams is being built by the Internet of Things (IoT) to monitor information about the physical environment. In parallel, Artificial Intelligence (AI) is constantly developing and enhancing both economic and academic endeavors as well as quality of life thanks to these IoT data. In streaming contexts, Kafka-ML is an open-source framework that enables the management of Machine Learning (ML) and AI pipelines over data streams. Accordingly, it simplifies the deployment of Deep Neural Networks (DNNs) in practical applications. Nonetheless, this framework did not support the possibility of carrying out an Online Learning (OL) process, which is needed when new data are continuously arriving, and the models need to adapt to them on the fly. In this work, we have extended the Kafka-ML framework to enhance the management of ML/AI pipelines with OL features to enable both ML/AI distributed and centralized models to learn indefinitely over time. These models are continuously upgraded thanks to a process where automatic and flexible inference is carried out when improvements in the model performance are achieved. We have validated these new features by adapting and deploying state-of-the-art DNN models in different online scenarios, for both single and distributed configurations. The results show the capability of Kafka-ML to execute effective online training processes for ML models, improving their performance over time as new data becomes available. © 2024, The Authors. All rights reserved.

关键词： Pipelines

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：