检索结果-内蒙古大学图书馆

IAENG International Journal of Computer Science 2024年第10期51卷 1642-1648页

作者： Geng, Y.X. Wang, L. Wang, Z.Y. Wang, Y.G. School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Automation Design Institute Metallurgical Engineering Technology Co. Ltd. Dalian116000 China

Model performance has been significantly enhanced by channel attention. The average pooling procedure creates skewness, lowering the performance of the network architecture. In the channel attention approach, average pooling is used to collect feature information to provide representative values. By leveraging the central limit theorem, we hypothesize that the strip-shaped average pooling operation will generate a one-dimensional tensor by considering the spatial position information of the feature map. The resulting tensor, obtained through average pooling, serves as the representative value for the features, mitigating skewness during the process. By incorporating the concept of the central limit theorem into the channel attention operation process, this study introduces a novel attention mechanism known as the"Central Attention Mechanism (CAM)." Instead of directly using average pooling to generate channel representative values, the central attention approach employs star-stripe average pooling to normalize multiple feature representative values into a single representative value. In this way, strip-shaped average pooling can be utilized to collect data and generate a one-dimensional tensor, while star-stripe average pooling can provide feature representative values based on different spatial directions. To generate channel attention for the complementary input features, the activation of the feature representation value is performed for each channel. Our attention approach is flexible and can be seamlessly incorporated into various traditional network structures. Through rigorous testing, we demonstrate the effectiveness of our attention strategy, which can be applied to a wide range of computer vision applications and outperforms previous attention techniques. © (2024), (International Association of Engineers). All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Method Based on Global Space-Spectral Attention Mechanism

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-11页

作者： Qin, Rui Wu, Benze Liu, Xinfu Wu, Yirui College of Computer Science and Software Engineering Hohai University Nanjing211100 China Nangjing Research Institute of Electronic Engineering Nanjing210007 China College of Artificial Intelligence and Automation Hohai University Jiangsu Changzhou213200 China

In hyperspectral remote sensing imagery, pixel interactions within defined spatial extents result in the mixing of adjacent pixels. Additionally, the high similarity of adjacent spectra leads to information redundancy, which hinders the extraction of global spatial and spectral correlations. In order to solve the problems of mixed adjacent pixels and redundant adjacent spectra, this work offers a hyperspectral image classification approach that uses a global space-spectral attention mechanism. First, the proposed method’s global spatial attention module uses multi-scale dilated convolution to produce a bigger receptive field to be capable of capturing global spatial correlation and obtain unmixed pixel information. Then, the global spectral attention module designs a spectral domain partition algorithm, using the combination of regional density as well as information entropy as the threshold to divide spectrum into dispersed subsets and eliminate redundant information. The global context information for entire spectral band is fully exploited, and correlation of the global spectral information is extracted. Finally, the two modules combine to provide a global correlation of space and spectrum. Experiments demonstrate that the suggested method obtains overall accuracies of 97.28%, 94.73%, and 95.76% on the three WHU-Hi hyperspectral datasets, surpassing comparison methods. © Shanghai Jiao Tong University 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Applications for Resilience in Manufacturing-A Systematic Literature Review 6

Artificial Intelligence Applications for Resilience in Manuf...

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Maier, Florian A. Puppala, Sivaphani Oberle, Michael Software Defined Energy-Cell Manufacturing Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Fraunhofer Institute for Manufacturing Engineering and Automation IPA Center for Digitalized Battery Cell Manufacturing Stuttgart Germany Fraunhofer Institute for Manufacturing Engineering and Automation IPA Centre for Digital Tools in Manufacturing Stuttgart Germany

ISBN: (纸本)9798350344349

This review provides a structured literature analysis of Artificial Intelligence (AI) applications in enhancing manufacturing resilience. The research is guided by three primary questions addressing the use cases, technologies, and benefits of AI across the five resilience phases: Prepare, Prevent, Protect, Respond, and Recover. Findings from 78 papers reveal that AI significantly contributes to predictive maintenance, risk mitigation, and quality control, with machine learning and deep learning being the predominant technologies. The study highlights the pivotal role of AI in advancing manufacturing towards proactive, resilient, and adaptable operations. The insights gleaned offer a roadmap for future research and practical AI integration in manufacturing, underscoring the value of AI in driving industrial innovation and efficiency. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent Exploration of Solution Spaces Exemplified by Industrial Reconfiguration Management 16

Intelligent Exploration of Solution Spaces Exemplified by In...

引用

16th CIRP Conference on Intelligent Computation in Manufacturing engineering, CIRP ICME 2022

作者： Müller, Timo Maschler, Benjamin Dittler, Daniel Jazdi, Nasser Weyrich, Michael University of Stuttgart Institute of Industrial Automation and Software Engineering Pfaffenwaldring 47 Stuttgart70569 Germany

Many decision-making approaches rely on the exploration of solution spaces with regards to specified criteria. However, in complex environments, brute-force exploration strategies are usually not feasible. As an alternative, we propose the combination of an exploration task's vertical sub-division into layers representing different sequentially interdependent sub-problems of the paramount problem and a horizontal sub-division into self-sustained solution sub-spaces. In this paper, we present a universal methodology for the intelligent exploration of solution spaces and derive a use-case specific example from the field of reconfiguration management in industry 4.0. © 2023 Elsevier B.V.. All rights reserved.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

A Concept for Dynamic and Robust Machine Learning with Context Modeling for Heterogeneous Manufacturing Data 16

A Concept for Dynamic and Robust Machine Learning with Conte...

引用

16th CIRP Conference on Intelligent Computation in Manufacturing engineering, CIRP ICME 2022

作者： Kamm, Simon Sahlab, Nada Jazdi, Nasser Weyrich, Michael Institute of Industrial Automation and Software Engineering University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany

With the increasing amount of available and connected data sources, industrial automation applications such as condition monitoring of a production machine can be improved by considering various data. To gain insights from this data and make it useable, heterogeneous data has to be analyzed intensively. Limited machine learning approaches exist in industrial automation and manufacturing for analyzing data acquired from multiple sources. In this paper, first, a suitable concept for handling heterogeneous data from integration to analysis is presented as well as a multi-layer architecture for the concept's realization. The architecture encapsulates functionalities into the different layers and allows easy extendability and modifiability. Afterwards, a context modeling approach for managing heterogeneous data and existing approaches and algorithms for analyzing this data robustly and dynamically analyzing it are presented. © 2023 Elsevier B.V.. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

5G Indoor Positioning for Manufacturing using Convolutional Neural Networks 56

5G Indoor Positioning for Manufacturing using Convolutional ...

引用

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Vietz, Hannes Ammar, Hamza Ben Haj Baum, Sebastian Jazdi, Nasser Weyrich, Michael University of Stuttgart Institute of Industrial Automation and Software Engineering Pfaffenwaldring 47 Stuttgart70569 Germany

Current disrupting trends in manufacturing like mobile robot-based intralogistics and digital twins require precise indoor positioning. 5G-based positioning has the potential to be more cost-efficient than other positioning systems due to shared hardware for positioning and communication. But first it has to achieve high positioning accuracy and stability. No positioning technique has yet been established as standard in the industry in combination with 5G because traditional positioning approaches can deliver unstable results when multi-path fading, reflections, or missing line-of-sight effects occur. Identifying promising techniques is still an open research topic. It is established in the literature that deep learning-based approaches can mitigate these effects better than traditional ones by learning unique fingerprints that correspond to precise positions. However, fully-connected neural networks tend to overtrain on these fingerprints which again leads to unstable positioning due to a lack of generalization. This can be explained by the inability of fully connected neural networks to learn structural interrelationships in high dimensional data. This is because their input data is flattened, which means the structure is removed. Convolutional neural networks are being widely used with image data and can learn structural interrelationships. This paper presents a technique that uses convolutional neural networks in combination with a channel-smoothing approach to position mobile robots in the research factory ARENA 2036. The results presented in this paper indicate an indoor positioning accuracy similar to other industrial positioning systems, with improved stability compared to a fully-connected approach. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference

关键词： 5G deep learning indoor positioning intralogistics mobile robots

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Adaptive Machine Learning Models using Adversarial and Transfer Learning 56

An Architecture for Adaptive Machine Learning Models using A...

引用

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Kamm, Simon Kumar, Praveen Jazdi, Nasser Weyrich, Michael University of Stuttgart Institute of Industrial Automation and Software Engineering Pfaffenwaldring 47 Stuttgart70550 Germany

Machine Learning and especially deep neural networks are more and more used in industrial applications, because they offer new possibilities to gain knowledge from the available data. The algorithms therefore should work during the lifetime of the industrial system, to which the algorithms are applied for improving the overall performance of the system. However, over the lifetime of an industrial system or application, data sources are likely to change. A sensor may be damaged and delivers faulty values or a new sensor is added to the system. A classical deep neural network will deliver incorrect outputs in case of a faulty sensor or cannot use the additional information coming from a new sensor. In both cases, a retraining with the new input space would be necessary, which requires effort for data collection and training of the network. To address these challenges, this paper proposes an architecture that combines separate approaches, namely the Fast Gradient Sign Method and Transfer Learning. To evaluate the combined architecture, it is applied to a real-world task of failure detection in the Air Pressure System (APS) of an automobile. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference on Manufacturing Systems 2023.

关键词： Adaptive Machine Learning Adversarial Learning Failure Detection Regularization Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of Radio Wave Propagation on Complex Terrains Using Deep Learning Models

Prediction of Radio Wave Propagation on Complex Terrains Usi...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Fan, Shihao Wen, Yinghong Wei, Zhenjie Ren, Jie School of Automation and Intelligence Beijing Jiaotong University Beijing China Institute of Software Engineering Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350350821

In this paper, we propose an innovative model to predict electromagnetic wave propagation on complex terrain, using the Dominant Path Model (DPM) algorithm to generate a dataset, and training a ResNet based wave propagation model. The key innovation is to use stepwise training techniques to apply the progress made by deep learning in the field of images to the prediction of radio wave propagation, in order to improve fitting performance. This method helps to improve the accuracy and adaptability of electromagnetic wave propagation prediction, providing new ideas for the prediction research of large-scale radio wave propagation. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Recommender Systems Performance using Knowledge Graph Embedding with Graph Neural Networks 4

Enhancing Recommender Systems Performance using Knowledge Gr...

引用

4th International Conference on Neural Networks, Information and Communication engineering, NNICE 2024

作者： Wang, Mingye Hu, Xiaohui Du, Yao Beihang University School of Automation Science and Electrical Engineering Beijing China Chinese Academy of Science Institute of Software Beijing China

ISBN: (纸本)9798350394375

Recommender systems are a crucial component in personalized information retrieval, with their performance directly impacting user experience. However, traditional recommender systems often suffer from limitations in handling complex user-item interactions. Recently, knowledge graphs have emerged as valuable resources for enhancing recommendation effectiveness by capturing and utilizing a wide range of information. In this work, we propose a novel Auto-encoder-based structure integrated with Graph Neural Networks (GNN) layers for Knowledge Graph Embedding (KGE) tasks. This model effectively captures and leverages the rich information in knowledge graphs. Further, we combine this advanced GNN-based knowledge graph embedding model and a preference propagation mechanism inspired by RippleNet, to introduce a novel model, GraphRipple, aiming to enhance the recommendation performance. Extensive experiments on multiple datasets demonstrate the effectiveness of GraphRipple in improving recommendation quality. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Knowledge Graph based Simulation Support 28

An Architecture for Knowledge Graph based Simulation Support

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Listl, Franz Georg Fischer, Jan Weyrich, Michael University of Stuttgart Institute of Industrial Automation and Software Engineering Germany Technology Siemens AG Munich Germany

ISBN: (纸本)9798350339918

Discrete-event simulation is a widely used method for modeling complex systems and evaluating their performance in production. However, the management of discrete-event simulation models and their associated data can be challenging, especially when dealing with large and heterogeneous data sets. In this paper, we present a knowledge graph-based framework that facilitates the management of discrete-event simulation models by representing them and their associated data as a knowledge graph. Our framework enables the integration of multiple data sources, supports the reuse of existing models, and enables the support for different applications based on the knowledge graph. Specifically, we demonstrate the application of our framework to the management of discrete-event simulation models in a use case of automatic model generation for a production line. Our results show that our framework provides an effective solution for managing discrete-event simulation models and their associated data, enabling users to easily query, update, and extend the models while maintaining their integrity and consistency. Overall, our work contributes to the development of knowledge-based solutions for managing complex systems and supports the broader adoption of discrete-event simulation in practice. © 2023 IEEE.

关键词： Data integration

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：