检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hu, Yingbai Abu-Dakka, Fares J. Chen, Fei Luo, Xiao Li, Zheng Knoll, Alois Ding, Weiping Multi-Scale Medical Robotics Centre Ltd. The Chinese University of Hong Kong Hong Kong School of Computation Information and Technology Technical University of Munich Munich85748 Germany Electronic and Computer Science Department Faculty of Engineering Mondragon Unibertsitatea Arrasate20500 Spain Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Department of Surgery The Chinese University of Hong Kong Hong Kong School of Information Science and Technology Nantong University Nantong226019 China

Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds significant promise for capturing expert motor skills through efficient imitation, facilitating adept navigation of complex scenarios. A persistent challenge in IL lies in extending generalization from historical demonstrations, enabling the acquisition of new skills without re-teaching. Dynamical system-based IL (DSIL) emerges as a significant subset of IL methodologies, offering the ability to learn trajectories via movement primitives and policy learning based on experiential abstraction. This paper emphasizes the fusion of theoretical paradigms, integrating control theory principles inherent in dynamical systems into IL. This integration notably enhances robustness, adaptability, and convergence in the face of novel scenarios. This survey aims to present a comprehensive overview of DSIL methods, spanning from classical approaches to recent advanced approaches. We categorize DSIL into autonomous dynamical systems and non-autonomous dynamical systems, surveying traditional IL methods with low-dimensional input and advanced deep IL methods with high-dimensional input. Additionally, we present and analyze three main stability methods for IL: Lyapunov stability, contraction theory, and diffeomorphism mapping. Our exploration also extends to popular policy improvement methods for DSIL, encompassing reinforcement learning, deep reinforcement learning, and evolutionary strategies. The primary objective is to expedite readers' comprehension of dynamical systems' foundational aspects and capabilities, helping identify practical scenarios and charting potential future directions. By offering insights into the strengths and limitations of dynamical system methods, we aim to foster a deeper understanding among readers. Furthermore, we outline potential extensions and enhancements within the realm of dynamical systems, outlining avenues for further exploration. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generalized Implicit Neural Representation for Efficient MRI Parallel Imaging Reconstruction

arXiv

引用

arXiv 2023年

作者： Li, Hao Zhou, Yusheng Liu, Jianan Liu, Xiling Huang, Tao Lyu, Zhihan Cai, Weidong Chen, Wei Department of Neuroradiology University Hospital Heidelberg Heidelberg Germany School of Electrical Engineering and Automation Wuhan University Wuhan China Momoni AI Gothenburg Sweden Department of Stomatology Shenzhen People's Hospital Shenzhen China College of Science and Engineering James Cook University SmithfieldQLD4878 Australia Department of Game Design Faculty of Arts Uppsala University Sweden School of Computer Science University of Sydney Sydney Australia School of Biomedical Engineering The University of Sydney Camperdown Australia

High-resolution magnetic resonance imaging (MRI) is essential in clinical diagnosis. However, its long acquisition time remains a critical issue. Parallel imaging (PI) is a common approach to reduce acquisition time by periodically skipping specific k-space lines and reconstructing images from undersampled data. This study presents a generalized implicit neural representation (INR)- based framework for MRI PI reconstruction, addressing limitations commonly encountered in conventional methods, such as subject-specific or undersampling scale-specific requirements and long reconstruction time. The proposed method overcomes these limitations by leveraging prior knowledge of voxel-specific features and integrating a novel scale-embedded encoder module. This encoder generates scale-independent voxel-specific features from undersampled images, enabling robust reconstruction across various undersampling scales without requiring retraining for each specific scale or subject. The framework's INR model treats fully sampled MR images as a continuous function of spatial coordinates and prior voxel-specific features, efficiently reconstructing high-quality MR images from undersampled data. Extensive experiments on publicly available MRI datasets demonstrate the superior performance of the proposed method in reconstructing images at multiple acceleration factors (4×, 5×, and 6×), achieving higher evaluation metrics and visual fidelity compared to stateof- the-art methods. In terms of efficiency, this INR-based approach exhibits notable advantages, including reduced floating point operations and GPU usage, allowing for accelerated processing times while maintaining high reconstruction quality. The generalized design of the model significantly reduces computational resources and time consumption, making it more suitable for real-time clinical applications. The proposed framework represents a promising solution for faster and more flexible MRI acquisition, capable of enhancing the cl

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Protocol for the fabrication of self-standing (nano)cellulose-based 3D scaffolds for tissue engineering

引用

STAR Protocols 2025年第1期6卷 103583页

作者： Mohan, Tamilselvan Bračič, Matej Bračič, Doris Lackner, Florian Nagaraj, Chandran Štiglic, Andreja Dobaj Kargl, Rupert Kleinschek, Karin Stana Graz University of Technology Institute for Chemistry and Technology of Biobased System (IBioSys) Stremayrgasse 9 Graz 8010 Austria University of Maribor Faculty of Mechanical Engineering Laboratory for Characterization and Processing of Polymers Smetanova Ulica 17 Maribor 2000 Slovenia Department of Internal Medicine Division of Pulmonology Medical University of Graz Graz Austria Institute of Automation Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia Members of the European Polysaccharide Network of Excellence (EPNOE) Austria

Three-dimensional (3D) and porous scaffolds made from nanocellulosic materials hold significant potential in tissue engineering (TE). Here, we present a protocol for fabricating self-standing (nano)cellulose-based 3D scaffolds designed for in vitro testing of cells from skin and cartilage tissues. We describe steps for preparation of nanocellulose ink, scaffold formation using 3D printing, and freeze-drying. We then detail post-processing procedures to enhance mechanical properties, stability, and biocompatibility. This protocol offers researchers a framework for developing versatile and sustainable biomaterials for regenerative medicine. For complete details on the use and execution of this protocol, please refer to Mohan et al.¹ and Štiglic et al.² © 2025 The Authors

关键词： Biotechnology and bioengineering Chemistry Material sciences Tissue engineering

来源：评论

学校读者我要写书评

暂无评论

Offloading safety- And mission-critical tasks via unreliable connections 32

Offloading safety- And mission-critical tasks via unreliable...

引用

32nd Euromicro Conference on Real-Time Systems, ECRTS 2020

作者： Schönberger, Lea Chen, Kuan-Hsun Youssef, Hazem Wietfeld, Christian Chen, Jian-Jia von der Brüggen, Georg Sliwa, Benjamin Venkatapathy, Aswin Karthik Ramachandran ten Hompel, Michael Design Automation for Embedded Systems Group Faculty of Computer Science TU Dortmund University Germany Material Handling and Warehousing Faculty of Mechanical Engineering TU Dortmund University Germany Communication Networks Institute Faculty of Electrical Engineering TU Dortmund University Germany

ISBN: (纸本)9783959771528

For many cyber-physical systems, e.g., IoT systems and autonomous vehicles, offloading workload to auxiliary processing units has become crucial. However, since this approach highly depends on network connectivity and responsiveness, typically only non-critical tasks are offloaded, which have less strict timing requirements than critical tasks. In this work, we provide two protocols allowing to offload critical and non-critical tasks likewise, while providing different service levels for non-critical tasks in the event of an unsuccessful offloading operation, depending on the respective system requirements. We analyze the worst-case timing behavior of the local cyber-physical system and, based on these analyses, we provide a sufficient schedulability test for each of the proposed protocols. In the course of comprehensive experiments, we show that our protocols have reasonable acceptance ratios under the provided schedulability tests. Moreover, we demonstrate that the system behavior under our proposed protocols is strongly dependent on probability of unsuccessful offloading operations, the percentage of critical tasks in the system, and the amount of offloaded workload. © Lea Schönberger, Georg von der Brüggen, Kuan-Hsun Chen, Benjamin Sliwa, Hazem Youssef, Aswin Ramachandran, Christian Wietfeld, Michael ten Hompel, and Jian-Jia Chen.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

An Algebraic Method to Stabilize Large-Scale Boolean Networks via Pinning Control

引用

IEEE Transactions on Network science and engineering 2025年

作者： Liu, Jiayang Liu, Yang Jiang, Haijun Abdel-Aty, Mahmoud Zhejiang Normal University School of Mathematical Sciences Jinhua321004 China Zhejiang Normal University Hangzhou School of Automation Hangzhou311231 China Yili Normal University School of Mathematics and Statistics Yining835000 China Ahlia University Graduate Studies and Research Manama10878 Bahrain Abu Dhabi University Electrical and Computer Engineering Department Zayed City MZ39 United Arab Emirates Sohag University Mathematics Department Faculty of Science Sohag82524 Egypt

As a discrete-time system, the dynamics of each gene node of Boolean networks (BNs) is determined by logical functions. This article aims to stabilize BNs globally through distributed pinning control. According to the existing literature, the state transition matrix-based pinning control strategy always suffers from high time complexity. The proposed approach, while likewise matrix-based, replaces the state transition matrix in favor of structure matrices based on the logical functions of each node and develops four computationally effective phases to solve the minimum set of controlled nodes and the corresponding pinning controllers, reducing the time complexity to O(2ξ), where ξ is a value determined by the specific network and the target state. The primary contribution is to provide a new method that eliminates time complexity as a barrier to matrix-based pinning control strategy by determining the index set of key nodes, particularly for sparse biological networks while preserving the benefits of matrix-based strategies. Finally, to demonstrate the effectiveness of the control method, gene networks with different sizes are discussed as simulations. © 2013 IEEE.

关键词： Discrete time control systems

来源：评论

学校读者我要写书评

暂无评论

Improving Referring Expression Comprehension by Suppressing Expression-unrelated Proposals

Improving Referring Expression Comprehension by Suppressing ...

引用

Electronic Information engineering and computer Technology (EIECT), International Conference on

作者： Qun Wang Feng Zhu Xiang Li Ruida Ye Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Faculty of Computer Science and Engineering Northeastern University Shenyang China Department of Aerospace Engineering and Technology Space Engineering University Beijing China

The prevailing referring expression comprehension (REC) method is based on two stages: 1) detecting multiple candidate proposals using an object detector and 2) aligning proposals with text descriptions. Existing two-stage models have achieved significant improvements with excellent alignment modules. However, their alignment modules treat each proposal equally without filtering expression-unrelated proposals. These expression-unrelated proposals may interfere with the alignment modules’ ability to accurately reason about the target proposal. These proposals also increase the difficulty of training alignment modules. To solve this problem, we propose a new framework, that can suppress expression-unrelated proposals for alignment modules. Specifically, we first design a suppression module, which calculates the relevance scores between the proposals and the expression by using the semantics in the expression. Then, these scores are integrated into three basic alignment modules, including subject, location, and relationship modules, to guide each module to focus on the expression-related proposals. We conduct extensive experiments on three benchmark datasets, and the results show the effectiveness of our suppression module and performance improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Infrared Spectroscopy for Discrimination Between Electrical and Thermal Faults in Transformer Oil

Application of Infrared Spectroscopy for Discrimination Betw...

引用

2022 9th International Conference on Condition Monitoring and Diagnosis (CMD)

作者： Mohamed M. F. Darwish Mohamed H. A. Hassan Nagat M. K. Abdel-Gawad Diaa-Eldin A. Mansour Department of Electrical Engineering Faculty of Engineering at Shoubra Benha University Cairo Egypt Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical Power Engineering School of Electronics Communications and Computer Engineering Egypt-Japan University of Science and Technology (E-JUST) New Borg El-Arab City Alexandria Egypt Department of Electrical Power and Machines Engineering Faculty of Engineering Tanta University Tanta Egypt

ISBN: (数字)9784886864314

ISBN: (纸本)9781665470155

Power transformer diagnostics and condition assessment are essential measures to increase the transformer's lifetime. In this regard, the dissolved gas analysis (DGA), the most common method worldwide in predicting the incipient faults in the transformer, is applied. Recently, the optical spectroscopy methods have attracted most of the attention towards effective monitoring of the state of power transformer insulation. Therefore, in this paper, Fourier Transform Infrared (FTIR) spectroscopy was employed to discriminate between the electrical and thermal faults that frequently happen in oil insulation. Regarding the electrical fault, it was simulated by applying repeated high voltage impulses to a fresh oil sample while the thermal fault was imitated through a localized overheating in another fresh oil sample with the help of a heating coil. Firstly, the two samples were examined via FTIR spectroscopy to obtain their FTIR spectra. Then, the effect of ageing on the spectrum was studied comprehensively for determining the degree of deterioration as well as any change that happen in the concentration or structure of the oil molecules. After that, both of them were analyzed by DGA to measure the concentration of the dissolved gases in the oil in order to confirm the FTIR spectroscopy results. In the final analysis, it was obvious that the implementation of the optical method is considered a promising tool to monitor the faulted oil and distinguish between the electrical fault and the thermal one making the FTIR spectroscopy a superior alternative for DGA.

关键词： Temperature sensors Temperature measurement Spectroscopy Oils Oil insulation Dissolved gas analysis Aging

来源：评论

学校读者我要写书评

暂无评论

Synergy Analysis of Industrial, Research and University Training Centers Collaboration: A Case Study in Thailand's Eastern Economic Corridor

Synergy Analysis of Industrial, Research and University Trai...

引用

Portland International Conference on Management of engineering and Technology (PICMET)

作者： Udom Lewlomphaisarl Ukrit Pungjitwisut Wassana Pullpol Kumpee Suksomboon Arnuphap Dowrueng Industrial IoT and Automation Research Group (IIARG) Sustainable Manufacturing Center (SMC) Eastern Economic Corridor of Innovation (EECi) Rayong Thailand EEC Automation Park Faculty of Engineering Burapha University Chonburi Thailand Intelligent SCADA Technology Research Team (IST) Advanced Control and Electronics Research Group (ACERG) National Electronics and Computer Technology Center (NECTEC) Pathum Thani Thailand National Electronics and Computer Technology Center (NECTEC) National Science and Technology Development Agency (NSTDA) Pathum Thani Thailand

The Royal Thai Government has outlined a 20-year strategy to achieve high-income status by 2036. “Thailand 4.0” is guided by the concept of “Industry 4.0”, which aims to transform the country into an innovative, value-driven industry, with a focus on 12 areas such as automation & Robotics, Aviation & Logistics, Biofuel & Biochemicals, and Digital. The development of Eastern Economic Corridor (EEC) lies at the heart of Thailand 4.0 scheme. The EEC is an area-based development initiative aimed at revitalizing the prestigious East Coast, where numerous business developers have experienced a rewarding investment journey and exceptional success over the past 30 *** paper introduces a synergy analysis of the 3-phase collaboration approach between the EEC automation Park located on the campus of Burapha University as the main university in the EEC and the Sustainable Manufacturing Center (SMC) at automation Robotics and Intelligent System (ARIPOLIS) in Eastern Economic Corridor of Innovation (EECi) with strong partners from industry e.g. Mitsubishi Electric Factory automation (Thailand) Limited. This 3-phase approach:}{1. Build an island demonstrator, 2. Link production demonstration lines and 3. Transfer to 100 factories in the EEC helps managers realize possible difficulties and systematically prepare solutions in advance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Neural Network Image Classification with Fractional Order Gradient Methods

SSRN

引用

SSRN 2023年

作者： Zhao, Haiming Chen, Jiejie Jiang, Ping Zeng, Zhigang Fan, Rui Yang, Honggang School of Computer and Information Engineering Hubei Normal University Huangshi435000 China School of Automation Wuhan University of Technology Wuhan430000 China School of Computer Hubei PolyTechnic University Huangshi435000 China Faculty of Artificial Intelligence Education Central China Normal University Wuhan430000 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430000 China

As deep learning technology increasingly permeates various fields, the significance of optimization algorithms in neural network training has become more prominent. Typically, the training of deep learning networks relies on gradient descent optimizers based on calculus computations. Traditional integer-order calculus optimizers often fall short when dealing with complex and subtle data. To overcome these limitations, we innovatively utilized the Grünwald-Letnikov and Caputo definitions of fractional calculus to develop two new optimization algorithms: Fractional Order Adagrad (FAdagrad) and Fractional Order Adam (FAdam). These algorithms have been proven to converge to extremal points.A key advantage of our methods is their capability in handling complex, high-dimensional tasks, such as artistic painting image classification, where they exhibit exceptional performance in recognizing and processing subtle differences. The robustness and adaptability of these algorithms were further validated through experiments on the CIFAR-100 dataset. The results demonstrate the efficacy of fractional order optimizers in enhancing training efficiency and accuracy. © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A reputation-based approach using consortium blockchain for cyber threat intelligence sharing

arXiv

引用

arXiv 2021年

作者： Zhang, Xiaohui Miao, Xianghua Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Computer Technology Application Key Laboratory of Yunnan Province Kunming China

The CTI (Cyber Threat Intelligence) sharing and exchange is an effective method to improve the responsiveness of the protection party. Blockchain technology enables sharing collaboration consortium to conduct a trusted CTI sharing and exchange without a trusted centralized institution. However, the distributed connectivity of the blockchain-based CTI sharing model proposed before exposes the systems into byzantine attacks, the compromised members of partner organizations will further decrease the accuracy and trust level of CTI by generating false reporting. To address the unbalance issues of performance in speed, scalability and security, this paper proposes a new blockchain-based CTI model, which combines consortium blockchain and distributed reputation management systems to achieve automated analysis and response of tactical threat intelligence. In addition, the novel consensus algorithm of consortium blockchain that is fit for CTI sharing and exchange introduced in this paper. The new consensus algorithm is called "Proof-of Reputation" (PoR) consensus, which meets the requirements of transaction rate and makes the consensus in a creditable network environment through constructing a reputation model. Finally, the effectiveness and security performance of the proposed model and consensus algorithm is verified by experiments. Copyright © 2021, The Authors. All rights reserved.

关键词： Cybersecurity

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：