检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Zijie Wang, Yaonan Mo, Yang Zhu, Qing Xie, He Wu, Haotian Feng, Mingtao Mian, Ajmal College of Electrical and Information Engineering Hunan University Changsha410082 China School of Computer Science and Technology Xidian University Xi’an710071 China Department of Computer Science and Software Engineering The University of Western Australia Crawley PerthWA6009 Australia

Point cloud registration is an essential step for free-form blade reconstruction in industrial measurement. Nonetheless, measuring defects of the 3D acquisition system unavoidably result in noisy and incomplete point cloud data, which renders efficient and accurate registration challenging. In this paper, we propose a novel global registration method that is based on the minimum potential energy (MPE) method to address these problems. The basic strategy is that the objective function is defined as the minimum potential energy optimization function of the physical registration system. The function distributes more weight to the majority of inlier points and less weight to the noise and outliers, which essentially reduces the influence of perturbations in the mathematical formulation. We decompose the solution into a globally optimal approximation procedure and a fine registration process with the trimmed iterative closest point algorithm to boost convergence. The approximation procedure consists of two main steps. First, according to the construction of the force traction operator, we can simply compute the position of the potential energy minimum. Second, to find the MPE point, we propose a new theory that employs two flags to observe the status of the registration procedure. We demonstrate the performance of the proposed algorithm on four types of blades. The proposed method outperforms the other global methods in terms of both accuracy and noise resistance. Copyright © 2025, The Authors. All rights reserved.

关键词： Turbomachine blades

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Near-Field Wideband Beamforming with Circular Arrays

Energy-Efficient Near-Field Wideband Beamforming with Circul...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Guo, Yunhui Zhang, Yang Wang, Zhaolin Liu, Yuanwei Ding, Zhiguo Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Khalifa University 6G Center Department of Computer and Communication Engineering Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350351255

The beamforming performance of the uniform circular array (UCA) in near-field wideband communication systems is investigated. Firstly, the unique beam squint effect in near-field wideband UCA systems is analyzed in both the distance and angular domains. It is demonstrated that the generated beams at different frequencies are focused at different locations, resulting in significant beamforming loss. To alleviate this unique beam squint effect and facilitate beamfocusing, an energy-efficient beamforming scheme based on the true-time delay (TTD) architecture is proposed. Specifically, the phase shifters (PSs) and the time delay of TTDs are designed based on the analytical formula for beamforming gain. Additionally, the minimum number of TTDs required to achieve a predetermined beamforming gain while minimizing energy consumption is quantified. Numerical results show that the proposed beamforming scheme effectively eliminates the near-field beam squint and outperforms the conventional schemes in terms of spectral efficiency and energy efficiency. © 2024 IEEE.

关键词： Near field communication

来源：评论

学校读者我要写书评

暂无评论

Expression Recognition and Intelligent Classroom State Mining in Teaching Videos Based on Semi-Supervised Learning Generative Adversarial Network

Expression Recognition and Intelligent Classroom State Minin...

引用

Data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Ruoyu Fan Meiyu Liang Mengran Yin Junping Du Beijing Key Laboratory of Intelligent Communication Software Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

We constructed a student classroom teaching video dataset, constructed a student classroom expression dataset through video frame extraction, face detection, face alignment, and facial extraction, and constructed a student classroom behavior dataset through object detection algorithm. Aiming at the characteristics that the annotation information of the students' classroom expression dataset constructed in this paper is limited and the data of some categories are less, an expression recognition method based on semi-supervised learning generative adversarial network (SSLGAN) is proposed. The problem of limited annotation information is solved through semi-supervised learning, and the problem of less data of some categories is solved through data enhancement of generative adversarial network. An intelligent classroom state mining method that integrates student expressions and behaviors has been proposed, achieving intelligent classroom state mining of teaching videos and automatic evaluation of classroom listening status for individual and overall students in different types of classrooms, such as interactive classes, discussion classes, and self-study classes. Compared with CNN, RMN, Temporal Ensembling and Mean Teacher, the proposed SSLGAN has achieved the highest accuracy in the benchmark dataset FER2013, JAFFE, RaFD and self-built student classroom expression dataset. In the case where there are few labels in the self-built student classroom expression dataset, the accuracy of student expression recognition results still reaches 76%, and the proposed intelligent classroom state mining method that integrates student expressions and behaviors for different types of classrooms also has high accuracy on the self-built student classroom teaching video dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing the Blockchain Technology for Higher Education in the Era of Pandemics: A Systematic Review

Utilizing the Blockchain Technology for Higher Education in ...

引用

International Conference on Information and Communication Systems (ICICS)

作者： Feda'a Al-Tawara Malik Qasaimeh Dania Jarad Raad S. Al-Qassas Department of Software Engineering Princess Sumaya University for Technology Amman Jordan Department of Software Engineering Department of Cyber Security Jordan University of Science and Technology Irbid Jordan Department of Computer Science Princess Sumaya University for Technology Amman Jordan

The availability of important characteristics such as decentralization, permanence, anonymity, and audacity has driven interest in blockchain technology more recently than ever before. This technology has been employed in a variety of applications, including education. Therefore, this research is a systematic review of research that investigates the applications of blockchain technology in higher education institutions in addition to those that present the role of this technology in combating the Corona pandemic, as it focuses on the following main topics: (1) blockchain-based applications and systems that can be used in higher education institutions; and (2) the current state of blockchain challenges in this area that need to be addressed in the future. A detailed analysis of the results of each topic as well as an extensive discussion were conducted based on the results. This review also provides insight into other areas that could benefit from blockchain technology during and after the pandemic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware Multi-view Cross Learning for Edge-based Collaborative Recommendation 29

Knowledge-aware Multi-view Cross Learning for Edge-based Col...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Dai, Yang Meng, Shunmei Gu, Huanhuan Liu, Nan Tu, Longchuan NanJing University of Science and Technology School of Cyberspace Security Nanjing China NanJing University State Key Lab. for Novel Software Technology Nanjing China NanJing University of Science and Technology Department of Computer Science and Engineering Nanjing China Nanjing Sinovatio Technology Co. Ltd. Nanjing China

ISBN: (纸本)9798350330717

In order to effectively overcome the sparsity and cold start challenges of collaborative filtering in actual scenarios, and provide more accurate suggestions, knowledge graphs are commonly utilized in recommender systems. Graph neural networks are increasingly used in knowledge graph-based recommender systems. Nevertheless, conventional recommender systems overlook the relationship information between items and entities as well as the sparse supervision signal, potentially leading to a decline in the actual recommendation performance. In this investigation, we propose KMCL, a Knowledge-aware Multi-view Cross-learning framework for edge-based collaborative recommendation. In contrast to the typical manner of dealing with knowledge graphs, our approach investigates three different graph views to improve users' and items' embedding representations, respectively. Firstly, the merged user-item KG graph is utilized to integrate the multi-hop neighbor information of each user, with the Graph Attention Network assigning various weights to different neighbors. Secondly, Graph Neural Network collects the top-x neighbor nodes for learning in the collaborative view of user-item graph and item-entity graph. Finally, a cross module is developed to share high-level information between embeddings with the same features. In addition, we also introduce the idea of edge computing, which preprocesses and calculates the locally obtained user preferences first, and then inputs them into different views to improve the recommendation efficiency. Experimental results demonstrate that KMCL delivers better suggestions than state-of-the-art baseline models in delivering superior recommendations. Furthermore, our approach maintains higher accuracy in predicting outcomes in less familiar interaction scenarios. © 2023 IEEE.

关键词： Edge Computing Graph Attention Network Knowledge Graph Multi-view Cross Learning Recommender System

来源：评论

学校读者我要写书评

暂无评论

Defect Recognition based on Radon Transform in Pentacene organic thin-film Archimedean interdigitated spirals transistor

Defect Recognition based on Radon Transform in Pentacene org...

引用

2023 International Conference on Clean Electrical Power, ICCEP 2023

作者： Sciuto, Grazia Lo Linde, Sivan Shikler, Rafi Kowol, Pawel Coco, Salvo Capizzi, Giacomo Silesian University of Technology Department of Mechatronics Gliwice Poland Ben-Gurion University of the Negev School of Electrical and Computer Engineering Optoelectronic Organic Semiconductor Devices Laboratory Department of Electrical and Computer Engineering Beer-Sheva Israel Ben-Gurion University of the Negev Ilse Katz Institute for Nanoscale Science and Technology Beer-Sheva Israel University of Catania Department of Electrical Electronics and Informatics Engineering Catania Italy

ISBN: (纸本)9798350348378

In this paper the problem of automatic defects detection in thin film transistor is considered in order to increase the efficiency of electronic devices. An effective approach based on defect pattern recognition in organic transistor is developed using the Radon transform. The adopted design and technology in Pentacene organic thin-film transistor exhibits two interdigitated Archimedean spirals pattern. In the conducted experiments, the images acquisition is performed with a microscope camera to capture the various defects of surface morphology on the top of the examined transistors. The defects detection is obtained by using the Radon transform on each channel (R,G,B) of these images. © 2023 IEEE.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

The Maintenance in Industry 4.0: Assistance and Implementation 32nd

The Maintenance in Industry 4.0: Assistance and Implementati...

引用

32nd European Safety and Reliability Conference, ESREL 2022

作者： Di Nardo, Mario Santillo, Liberatina Carmela Carra, Silvia Monica, Luigi Sara, Anastasi Gallab, Maryam Department of Materials Engineering and Operations Naples Italy Italian Workers’ Compensation Authority Rome Italy MIS-LISTD Laboratory Computer Science Department Rabat Italy

ISBN: (纸本)9789811851834

We are witnessing the fourth industrial revolution in recent years, summarised in the expression "Industry 4.0". This revolution includes both the development of existing technologies and the introduction of new ones. A fundamental aspect of the new model is the implementation of sensors systems, which must be more precise and efficient to be combined with the new technology based on big data, Internet Of Things, neural networks and augmented reality. Maintenance and human factor also retain a fundamental role. As in any industrial model, ordinary and extraordinary maintenance cannot be ignored. In this paper, maintenance is defined as a hybrid between "preventive" and "on condition" ones, while taking the positive aspects of both. A preliminary framework for remotely implementing a maintenance 4.0 procedure is defined. A practical application of such methodology in Industry 4.0 through new human-machine interfaces (supported by augmented reality) is then presented for a water boiler. The proposed solution is connected to humans’ role in industry 4.0, which seems, at first glance, to be decreasing, but, in reality, new and ever greater skills are required. With this in mind, new ways of implementing maintenance can be able to optimise organisational processes. © 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.

关键词： Condition based maintenance

来源：评论

学校读者我要写书评

暂无评论

Prediction of Covid-19 using Machine Learning and Deep Learning approaches: A data driven study

Prediction of Covid-19 using Machine Learning and Deep Learn...

引用

Circuits, Power and Intelligent Systems (CCPIS), International Conference on

作者： Thanzina Akhter Labannya Barua Mahmuda Sultana Abdul Kadar Muhammad Masum Department of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Software Engineering Daffodil International University Dhaka Bangladesh

COVID-19 is generated by the SARS-CoV2 virus, which has caused an outbreak around the world. Since 2020, it has been labeled a pandemic. Due to the daily growth in the number of cases, this takes time for demonstrating the laboratory data, and as a result, treatment and resource limits have emerged. Because of such limitations the necessity for making decisions using clinical data with prognostic algorithms has emerged. Forecasting algorithms could positively relieve the pressure on healthcare systems by correctly identifying the disease. We employ the following machine learning models in this research: RF, SVM, hybrid RF-SVM and deep learning: ANN, CNN, LSTM, CNN-LSTM models and laboratory data is being used to develop clinical forecasting models that will help medical professionals to figure out the patients that are most likely to develop COVID-19. Our models' prediction ability is measured using recall, F1-score, precision, accuracy and AUC scores. The models were verified using train test method and cross validation strategy. The assessment shows that most of our prediction models can reliably identify patients with COVID-19 disease, amidst the hybrid CNN-LSTM model outperforming the others with an accuracy of 89.5 percent,0.93 F1-score, 0.91 in precision,0.97 in recall, and AUC of 0.70, whereas among the machine learning models the hybrid ensemble outperforms other ML models with an accuracy of 92%. Predictive models obtained from laboratory findings have been found to be successful in predicting COVID-19 infection, which can help medical experts administer resources more effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learned Video Compression With Refined Adaptive Flow Pyramid And Coordinate-Aware Attention

Learned Video Compression With Refined Adaptive Flow Pyramid...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qian Huang Wenting Liu Xin Li Yiming Wang College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In video compression, motion estimation and motion compensation are critical for achieving efficient encoding. Although the commonly used SpyNet and bilinear interpolation have contributed in improving the compression efficiency, they still have limitations. SpyNet often loses details and fails to fully utilize the feature extraction capabilities of deep networks. Furthermore, bilinear interpolation inherently attenuates high-frequency information, leading to frame blurring and distortion. In this paper, we propose a novel video compression algorithm. To overcome the limitations of SpyNet, we propose a refined adaptive flow pyramid network. This network uses a multi-scale feature pyramid to capture more details. Moreover, we use an iterative cost volume refinement engine that improves the feature representation of the network and iteratively improve the accuracy of motion estimation. In addition, to overcome the limitation of bilinear interpolation, we propose a coordinate-aware attention module, which captures more high-frequency information to improve the accuracy of motion compensation. Experimental results show that our method outperforms VTM-13.2 (LDP) in terms of PSNR.

关键词： Interpolation Adaptive systems Costs Acoustic distortion Accuracy Motion estimation Video compression Feature extraction Motion compensation Speech processing

来源：评论

学校读者我要写书评

暂无评论

Beyond pixels:Learning from multimodal hyperspectral superpixels for land cover classification

引用

science China(Technological sciences) 2022年第4期65卷 802-808页

作者： HONG DanFeng WU Xin YAO Jing ZHU XiaoXiang Key Laboratory of Computational Optical Imaging Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Remote Sensing Technology Institute German Aerospace Center(DLR)Wessling 82234Germany Data Science in Earth Observation Technical University of MunichMunich 80333Germany

Despite tons of advanced classification models that have recently been developed for the land cover mapping task,the monotonicity of a single remote sensing data source,such as only using hyperspectral data or multispectral data,hinders the classification accuracy from being further improved and tends to meet the performance *** this reason,we develop a novel superpixel-based subspace learning model,called Supace,by jointly learning multimodal feature representations from HS and MS superpixels for more accurate LCC *** can learn a common subspace across multimodal RS data,where the diverse and complementary information from different modalities can be better combined,being capable of enhancing the discriminative ability of to-be-learned features in a more effective *** better capture semantic information of objects in the feature learning process,superpixels that beyond pixels are regarded as the study object in our Supace for *** experiments have been conducted on two popular hyperspectral and multispectral datasets,demonstrating the superiority of the proposed Supace in the land cover classification task compared with several well-known baselines related to multimodal remote sensing image feature learning.

关键词： classification hyperspectral image land cover multimodal multispectral image remote sensing subspace learning superpixels

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：