检索结果-内蒙古大学图书馆

Network-Based Rail Running Band Anomaly Recognition via Recurrent Attention Graphs

IEEE Transactions on Automation science and engineering 2025年 22卷 15381-15395页

作者： Ni, Xuefeng Fieguth, Paul W. Ma, Ziji Shi, Bo Liu, Hongli Hunan University College of Electrical and Information Engineering Changsha410012 China University of Waterloo Department of Systems Design Engineering WaterlooONN2L 3G1 Canada The Hong Kong University of Science and Technology Department of Computer Science and Engineering Sai Kung Hong Kong

Anomaly detection for rail running bands, the pattern of wheel-rail contact area, is crucial to analyze composite rail irregularities. This paper presents an all-weather vision-based solution for running-band inspection. However, two major algorithmic challenges restrict inspection effectiveness: 1) the identification of high-quality features for diversified and imbalanced data subject to noise and outliers, and 2) inferring implicit anomaly co-occurrence patterns. We regard overall running-band anomaly detection as a multi-label classification problem and develop a novel deep multi-anomaly recognition network via recurrent attention graphs (RAGRN). © 2004-2012 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Revisiting LARS for Large Batch Training Generalization of Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1321-1333页

作者： Do, Khoi Nguyen, Minh-Duong Hoa, Nguyen Tien Tran-Thanh, Long Tran, Nguyen H. Pham, Quoc-Viet Trinity College Dublin School of Computer Science and Statistics Dublin 2 D02PN40 Ireland Pusan National University Department of Information Convergence Engineering Busan46241 Korea Republic of Hanoi University of Science and Technology School of Electrical and Electronic Engineering Hanoi100000 Viet Nam University of Warwick School of Computer Science CoventryCV4 7AL United Kingdom The University of Sydney School of Computer Science DarlingtonNSW2006 Australia Kyung Hee University Department of Computer Science and Engineering Yongin446-701 Korea Republic of

This article investigates large batch training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings. In particular, we first show that a state-of-the-art technique, called LARS with the warm-up, tends to be trapped in sharp minimizers early on due to redundant ratio scaling. Additionally, a fixed steep decline in the latter phase restricts deep neural networks from effectively navigating early-phase sharp minimizers. To address these issues, we propose time varying LARS (TVLARS), a novel algorithm that replaces warm-up with a configurable sigmoid-like function for robust training in the initial phase. TVLARS promotes gradient exploration early on, surpassing sharp optimizers and gradually transitioning to LARS for robustness in later stages. Extensive experiments demonstrate that TVLARS consistently outperforms LARS and LAMB in most cases, with up to 2% improvement in classification scenarios. In all self-supervised learning cases, TVLARS achieves up to 10% performance improvement. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Using Stable Diffusion Model for Text-Driven Generation in Augmented Reality Applications 33rd

Using Stable Diffusion Model for Text-Driven Generation in A...

引用

33rd International Conference on Organization and technology of Maintenance, OTO 2024

作者： Rücker, Kristian Livada, Časlav Galba, Tomislav Baumgartner, Alfonzo Faculty of Electrical Engineering Josip Juraj Strossmayer University in Osijek Computer Science and Information Technology Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (纸本)9783031805967

Rapid advances in science and technology have led to the integration of artificial intelligence (AI) in many areas, including augmented reality (AR). This study explores the application of the Stable Diffusion (SD) model to develop an AR application that generates images based on text descriptions. Using Unity, a versatile game development platform, we implemented this AR application, scripting in C# with Visual Studio 2022. The user interface and functionality of the SD model were managed via the UI Stable Diffusion Automatic 1111 tool, allowing seamless integration and execution of SD functions. This work demonstrates the potential of AI-driven models in enhancing AR experiences and introduces a novel approach to dynamic visual content creation and editing. Furthermore, this technology has significant implications for the maintenance of municipal infrastructure and maintenance organizations. By converting text instructions into visual AR overlays, maintenance teams can improve the accuracy and efficiency of tasks such as inspections, repairs, and infrastructure management, streamlining operations and reducing errors. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Dataset Ratio Influence on kNN Classification Results 33rd

Dataset Ratio Influence on kNN Classification Results

引用

33rd International Conference on Organization and technology of Maintenance, OTO 2024

作者： Gaće, Marin Galba, Tomislav Baumgartner, Alfonzo Livada, Časlav Faculty of Electrical Engineering Josip Juraj Strossmayer University of Osijek Computer Science and Information Technology Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (纸本)9783031805967

Classification is used in many fields today, and for most of them machine learning algorithms can be used to make a decision. This article investigates the effects of different sizes of training and test datasets on the accuracy of classification using both classical k-nearest neighbors (kNN) and weighted k-nearest neighbors (wkNN) methods. This study systematically evaluates how different ratios of training to test data affect classification performance and provides a comprehensive analysis of the interplay between the ratios of the datasets and the parameter k. The results show that the ratio of training to test datasets exerts a more significant influence on classification accuracy than the choice of the parameter k. In particular, extreme ratios, where the training dataset is either much larger or much smaller than the test dataset, lead to suboptimal classification results. This emphasizes the importance of carefully selecting an appropriate balance between training and test data to ensure robust and reliable classification results. By highlighting the critical role of the ratio between datasets, this paper provides valuable insights for optimizing kNN and weighted kNN methods in practical applications. The results have far-reaching implications for the design and implementation of machine learning models and emphasize the need for a balanced data distribution to achieve high classification accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Life Cycle Management of Operational technology – OT 33rd

Life Cycle Management of Operational Technology – OT

引用

33rd International Conference on Organization and technology of Maintenance, OTO 2024

作者： Dorić, Dražen Glavaš, Hrvoje Varga, Fran Faculty of Electrical Engineering Josip Juraj Strossmayer University of Osijek Computer Science and Information Technology Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (纸本)9783031805967

Systematic management of all phases of the lifecycle of an industrial control system, recently referred to as operational technology or OT for short, ensures that the system is up to date, compliant with regulations and in line with changing business requirements. This is especially true for critical infrastructure. In this way, operational resilience is improved, risks are minimized and a proactive approach to maintenance is encouraged, with a focus on safety, efficiency and long-term sustainability. The paper provides an overview of the motivations for systematic lifecycle management of OT systems, offers a description and illustration of lifecycle costs in the CAPEX and OPEX phases, emphasizes the changing role of corrective and preventive maintenance from a lifecycle management perspective, and budgeting for various activities, including cybersecurity and OT system upgrades. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Preventive maintenance

来源：评论

学校读者我要写书评

暂无评论

Topic-aware cosine graph convolutional neural network for short text classification

引用

Soft Computing 2024年第13-14期28卷 8119-8132页

作者： Min, Changrong Chu, Yonghe Lin, Hongfei Wang, Bolin Yang, Liang Xu, Bo Criminal Investigation Police University of China No.83 Tawan St Liaoning Shenyang China School of Computer Science and Technology Dalian University of Technology No. 2 Linggong Road Liaoning Dalian116024 China School of Information Science and Engineering Henan University of Technology No. 100 Lianhua Street Henan Zhengzhou450001 China

Graph Convolutional Network (GCN) has been extensively studied in the task of short text classification (STC), utilizing global graphs that incorporate texts at different levels of granularity to learn text embeddings. However, the GCN-based methods only focus on the alignment between ground-truth labels and predicted labels, overlooking the geometric structure implicitly encoded by the graph. To address this limitation, we propose a novel GCN-based method that is entitled Topic-aware Cosine GCN (ToCo-GCN) for the STC. The ToCo-GCN defines and captures underlying geometric structures of short texts from different categories in the cosine space. Specifically, the ToCo-GCN regards the within-class and between-class geometric structures as constraint, aiming to learn both representative and discriminative short text representations. Moreover, to mitigate the inherent sparsity problem of short texts, the ToCo-GCN augment the text graph with latent topics. Experimental results on 8 STC datasets demonstrate that the ToCo-GCN is superior to state-of-the-art baselines in terms of Accuracy and Macro-F1 score. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Research on the cross-platform information transmission method of industrial internet of things based on XML technology

引用

International Journal of Industrial and Systems engineering 2023年第3期43卷 317-330页

作者： Zhu, Changhong Pan, Tianci School of Computer Science and Engineering Guilin University of Aerospace Technology No. 2 Jinji Road Guangxi Guilin541004 China Department of Information Engineering Bowen College of Management Guilin University of Technology No. 317 Yanshan Street Guangxi Guilin541006 China

Aiming at problems of large error in data feature extraction and high congestion in the traditional information transmission methods, this paper proposes a cross-platform information transmission method of industrial internet of things based on XML technology. Based on the networked information features of extract, SUM function was used to complete the feature fusion. Then, the XML technology is used to obtain the optimal segmentation of tree, and the fitting training of tree data is carried out to realise the safe storage of information. Then, the information distribution probability is obtained according to the nature of XML file, so as to realise the cross-platform transmission of information. According to the simulation results, it can be seen that the data feature extraction error of this method is at least 2.1%, the sample data transmission time is always lower than 6 s, and the transmission process congestion is low, which fully proves its effectiveness. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Structural RC computer aided intelligent analysis and computational performance via experimental investigations

引用

Structural engineering and Mechanics 2024年第3期90卷 253-261页

作者： Huang, Y.C. Lulios, TuMuli Chang, Chu-Ho Noor, M. Nasir Shao, Jen-Chung Chiu, Chien-Liang Lee, Tsair-Fwu Wang, Renata Information Technology Faculty Duy Tân University 254 Nguyen Van Linh Danang Viet Nam Princess Margaret Hospital Funafuti Island Private Mail Bag Tuvalu College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan College of Maritime National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Medical Physics and Informatics Laboratory of Electronics Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Information and Research Center of China 1/9 Road: 2 Block: D Section: 15 Dhaka1216 Bangladesh

This research explores a new finite element model for the free vibration analysis of bi-directional functionally graded (BDFG) beams. The model is based on an efficient higher-order shear deformation beam theory that incorporates a trigonometric warping function for both transverse shear deformation and stress to guarantee traction-free boundary conditions without the necessity of shear correction factors. The proposed two-node beam element has three degrees of freedom per node, and the inter-element continuity is retained using both C1 and C0 continuities for kinematics variables. In addition, the mechanical properties of the (BDFG) beam vary gradually and smoothly in both the in-plane and out-of-plane beam’s directions according to an exponential power-law distribution. The highly elevated performance of the developed model is shown by comparing it to conceptual frameworks and solution procedures. Detailed numerical investigations are also conducted to examine the impact of boundary conditions, the bi-directional gradient indices, and the slenderness ratio on the free vibration response of BDFG beams. The suggested finite element beam model is an excellent potential tool for the design and the mechanical behavior estimation of BDFG structures. © 2024 Techno-Press, Ltd.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Bridging the Physical and Virtual Worlds: A Hand Tracking Gesture Recognition System for XR Applications 1

引用

32nd International Conference on Organization and technology of Maintenance, OTO 2023

作者： Fumić, Matija Livada, Časlav Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University in Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (数字)9783031514944

ISBN: (纸本)9783031514937

Extended reality (XR) is a term that encompasses augmented reality (AR), virtual reality (VR), and mixed reality (MR). These technologies allow users to interact with digital content in immersive and realistic ways. One of the challenges of XR is to provide natural and intuitive ways to control and manipulate the virtual environment. This paper presents the development of a gesture recognition system for hand tracking in extended reality technologies (XR) and its practical applications. The system uses a gesture definition language that allows the user to create custom gestures based on the hand skeleton model. The system was implemented using the Oculus Quest 2 device and the Oculus SDK in the Unity game engine and is compatible with all devices that support hand tracking. The gesture recognition system was implemented using a three-bone thumb and little finger model that is compatible with all hand models that contain four bones. The implementation of this gesture recognition system in XR has several benefits, including increased immersion, improved interaction with virtual objects, and reduced physical fatigue compared to traditional input methods such as controllers or keyboards. This system provides users with a more intuitive and natural way to interact with their virtual environment. Overall, this work demonstrates the feasibility and potential of integrating gesture recognition into XR technologies and its ability to enhance user experience and interaction. The system presented in this work can serve as a foundation for future developments in this area, with potential applications in gaming, education, healthcare, and other fields. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

The 5S Method and Its Strategic Determinants Within the Organization of Production Plants 32nd

The 5S Method and Its Strategic Determinants Within the Orga...

引用

32nd International Conference on Organization and technology of Maintenance, OTO 2023

作者： Crnjac Milić, Dominika Faculty of Electrical Engineering Computer Science and Information Technology in Osijek Josip Juraj Strossmayer University of Osijek Kneza Trpimira 2B Osijek31000 Croatia

ISBN: (纸本)9783031514937

Racing for the global advantage, companies have been paying increasing attention to workplace design, employee safety, workplace satisfaction, labor productivity and product quality. One of the methods that can help them achieve these goals is the 5S method, which is also considered a management tool for better organization and management of the workplace. Although the 5S method is applicable to a wide range of workplaces, using published research results, this paper provides a comprehensive overview of its challenges and benefits in manufacturing companies. They are analyzed and synthesized in a new way and special attention is paid to the method steps and its implementation. The paper points to a wide scope of the method application as companies have to meet various standards and present certificates that guarantee the safety and quality of manufactured products. Since managers are constantly trying to find ways to obtain and maintain them, one of the objectives of this paper is to provide an overview and critical evaluation of existing published research results that show the impact of the method application on increasing the product quality, the production process, health and safety. The methods from the qualitative methodological framework were used and research results that contribute to the scientific discourse related to the results that can be achieved by applying the 5S method in the organization of production plants were presented. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Industrial research

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：