检索结果-内蒙古大学图书馆

PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models

IEEE Access 2025年 13卷 85390-85406页

作者： Khan, Michel Gokan Guarese, Renan Johnson, Fabian Wang, Xi Vincent Bergman, Anders Edvinsson, Benjamin Romero, Mario Vachier, Jeremy Kronqvist, Jan KTH Royal Institute of Technology School of Engineering Sciences Stockholm Sweden KTH Royal Institute of Technology Digital Futures Stockholm Sweden KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden AstraZeneca Slovakia KTH Royal Institute of Technology School of Industrial Engineering and Management Stockholm Sweden Linköping University Department of Science and Technology Sweden

We introduce PerfCam, an open source Proof-of-Concept (PoC) digital twinning framework that combines camera and sensory data with 3D Gaussian Splatting and computer vision models for digital twinning, object tracking, and Key Performance Indicators (KPIs) extraction in industrial production lines. By utilizing 3D reconstruction and Convolutional Neural Networks (CNNs), PerfCam offers a semi-automated approach to object tracking and spatial mapping, enabling highly accurate digital twins that capture real-time KPIs such as availability, performance, Overall Equipment Effectiveness (OEE), and rate of conveyor belts in the production line. We validate the effectiveness of PerfCam through a practical deployment within realistic test production lines in the pharmaceutical industry and contribute an openly published dataset to support further research and development in the field. The results demonstrate PerfCam’s ability to deliver actionable insights through its precise digital twin capabilities, underscoring its value as an effective tool for developing usable digital twins in smart manufacturing environments and extracting operational analytics. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Predictive Channel State Information Feedback in Multiple Input Multiple Output Using Improved Recurrent Neural Network

Predictive Channel State Information Feedback in Multiple In...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Srinivasa Rao Bittla Zaed Balasm Zabiha Khan T. Saravanan Senbagam K Independent Researcher Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India Department of Electronics and Communication Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering Technology Mamallapuram India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

In modern era, Multiple Input Multiple Output (MIMO) technology is a crucial element in wireless technology, where accurate prediction of Channel State Information (CSI) feedback is critical for beamforming, optimal resource allocation. However, due to traditional compression techniques based on quantization such as scalar and vector quantization which introduces errors in CSI feedback, which leads to inaccurate channel estimation. To overcome these challenges, an Improved Recurrent Neural Network (IRNN) based CSI feedback mechanism is proposed with an integrated self-attention mechanism to improve the prediction accuracy. Initially, a system based on downlink massive MIMO and Orthogonal Frequency Division Multiplexing (mMIMO-OFDM) is considered. This system consists of multiple gNodeBs (gNBs), which serve multiple User Equipments (UEs). These multiple gNBs transmits Reference Signals (RSs) to enable UEs, to estimate and provide CSI feedback. Furthermore, IRNN based channel predictors are deployed at both the gNBs and UEs, which learn the temporal relationships among CSI data and refine the feedback information. The proposed IRNN is improved by integrating self-attention mechanism. Finally, the proposed IRNN outperformed RNN by achieving better results in Normalized Mean Squared Error (NMSE) of -26.500, precoding gains of 0.998, cosine similarity of 0.998 and spectral efficiency of 1.425.

关键词： Recurrent neural networks Accuracy Spectral efficiency System performance Precoding OFDM Predictive models Integrated circuit modeling Channel state information Gain

来源：评论

学校读者我要写书评

暂无评论

Decentralized Intrusion Detection in Peer-to-Peer Networks using Stacking Ensemble Model

Decentralized Intrusion Detection in Peer-to-Peer Networks u...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： R. Renuga Devi Rame Riadhusin Anu D Swarnateja R R. Revathi Department of Computer Science and Applications SRM Institute of Science and Technology India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Artificial Intelligence and Data Science Nitte Meenakshi Institute of Technology Bengaluru India Department of Information Technology Dhanalakshmi Srinivasan College of Engineering and Technology India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In recent years, due to the rise in Peer to Peer (P2P) networks has brought a significant way in which the data is shared and services are offered over the internet. These P2P networks make use of decentralized architecture in which nodes directly interact and exchange resources. However, due to the use of decentralized architecture, the P2P networks are exposed to various security threats such as data breaches, and other malicious attacks. In this research, Stacking Ensemble Model (SEM) is proposed for network intrusion detection in P2P networks. Initially, the data is considered from network intrusion detection dataset and then preprocessed with data imputation and min-max normalization effectively handles the missing values and rescales the data into significant range. After that, Recursive Feature Elimination (RFE) is incorporated to select optimal features from preprocessed data based on feature importance. Finally, the proposed SEM effectively detects the intrusion in P2P networks which enhances the security. From the results, the proposed SEM model obtained a better outcome in terms of accuracy, precision, recall, and F1-score compared to the existing K-Nearest Neighbor (KNN) by accomplishing 97.20%, 94.71%, 96.62%, and 95.65%, respectively.

关键词： Computational modeling Stacking Network intrusion detection Predictive models Nearest neighbor methods Feature extraction Imputation Data models Peer-to-peer computing Security

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Health Care Computing and Assessments in Oman: an Effectual Study

Artificial Intelligence in Health Care Computing and Assessm...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Wilfred Blessing N. R Hemalatha Gunasekaran Hariharan B. Jaber Saleh Salim Al Jabri Kavitha S. J Sutherlin Subitha G. College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Engineering Stella Mary's College of Engineering Aruthenganvilai Tamil Nadu India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Health care plays a vital responsibility in a human life span. World countries targets to provide better care for their citizens. Digital transformations and innovations in Artificial Intelligence (AI) technologies helps in deep for the novel solutions to speed-up the decision making process in health management and patient consulting. AI branches including Machine Learning (ML), Deep Learning (DL), Neural Networks (NN), Natural Language Processing (NLP) and so forth can support innovations in heal care domain. This paper presents the comprehensive and noble review on recent existing tools and techniques and also recommends advanced techniques for health care industry that are to be used in Sultanate of Oman. Furthermore, overcoming AI challenges are resulted and presented through the study. This work mainly aimed to produce the multiple dimensions and challenges that helps to develop AI powered real-life applications in health care support system.

关键词： Deep learning Technological innovation Ethics Reviews Decision making Surgery Medical services Natural language processing Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Anisotropic field suppression of Morin transition temperature in epitaxially grown hematite thin films

引用

Physical Review Materials 2025年第3期9卷 034410-034410页

作者： Haoyu Liu Hantao Zhang Josiah Keagy Qinwu Gao Letian Li Junxue Li Ran Cheng Jing Shi Department of Physics & Astronomy University of California Riverside California 92521 USA Department of Electrical & Computer Engineering University of California Riverside California 92521 USA Department of Physics Southern University of Science and Technology Shenzhen 518055 China

We have demonstrated the existence of the Morin transition in epitaxially grown hematite thin films exceeding a critical thickness. The Morin transition temperature can be suppressed by magnetic fields applied both parallel and perpendicular to the Dzyaloshinskii-Moriya (DM) vector, exhibiting a distinct anisotropic behavior that is consistent with bulk hematite crystals. Detailed analysis explains the anisotropic behavior and provides a method for determining the DM strength, which remains nearly constant across the sample thickness over four orders of magnitude. Our findings obtained with transport measurements offer a valuable approach for studying antiferromagnetic spin configurations in thin films and nanodevices.

关键词： Anisotropy

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease Prediction and Online Consultation for Accessible Medical Support 2

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease P...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Wilfred Blessing, N.R. Gunasekaran, Hemalatha Hariharan, B. Al Jabri, Jaber Saleh Salim Kavitha, S.J. Sutherlin Subitha, G. College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman SRM Institute of Science and Technology Kattankulathur Department of Computational Intelligence Tamil Nadu India Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Tamil Nadu Aruthenganvilai India

ISBN: (纸本)9798331505745

Improvements in patient care and early disease detection possibilities are two of the ways artificial intelligence is transforming the healthcare industry. Alzheimer's disease, a neurodegenerative disease that worsens with time, is among the most difficult diseases to exactly identify in early stages. Patients thus delay in treatment and experience a decline in their quality of life. Research is still under progress, thus knowledge about how AI-driven prediction models could be combined with readily available healthcare services remains lacking. This work presents a special artificial intelligence-powered system consisting of DenseNet-based deep learning for Alzheimer's disease prediction with an online consultation platform. The proposed approach analyzes brain MRI data and classifies Alzheimer's stages with higher accuracy using a DenseNet architecture, well-known for its exceptional performance in the field of feature extraction. Comprising three thousand magnetic resonance imaging (MRI) images, the dataset has been preprocessed for noise reduction and tuned for models performance. At 98.5%, the DenseNet model exceeded other methods including VGGNet and ResNet in accuracy. © 2025 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Exploring Few-Shot Learning to Enhance NLP's Cross-Domain Capabilities

Exploring Few-Shot Learning to Enhance NLP's Cross-Domain Ca...

引用

Computing for Sustainability and Intelligent Future (COMP-SIF), International Conference on

作者： T. Suresh Balakrishnan Gururama Senthilvel. P U. Samson Ebenezar L. Karthikeyan Kishan B S Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai India Department of Mechanical Engineering BMS Institute of Technology and Management Bangalore India

ISBN: (数字)9798331538538

ISBN: (纸本)9798331538545

Here, few shot learning (FSL) has been identified as a valuable method for improving the flexibility of NLP when dealing with new and different datasets with small amounts of training data. Most of the traditional NLP models are affected by shift since they are based on a big data set of a different domain. To overcome this challenge, FSL facilitates training of models to extrapolate from a few examples and not necessarily from numerous samples that may be present in LMMs. In this paper, I delve into meta-learning, prompt-based learning, and transfer learning as some of the methods that can be applied to boost NLP's cross-domain performance. We explain how these methods contribute to enhance performance in the use of fewer resources and evaluate the efficiency of those techniques on textual classification, sentiment analysis, and machine translation. Also, the pretrained GPT and BERT are beneficial to few-shot learning as it takes place through contextual learning. Based on our results, the conclusion is made that the application of FSL techniques in NLP pipelines enhances generalization and reduces the time and expenses on data annotation. Yet, some of the challenges that are associated with text analytics are data bias, sensibility of the prompts and computational problems. Finally, we propose some future works for FSL such as: the proposal of a new FSL model that combines traditional supervised and unsupervised learning; the presentation of a new FSL model based on a reinforcement learning theory. Hence, with the use of FSL, NLP models can perform well in different domains of application with little to no labeled data hence transferring knowledge to different domains to increase efficiency and scale in knowledge.

关键词： Metalearning Training Adaptation models Computational modeling Transfer learning Training data Data models Few shot learning Sustainable development Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

MDAAF: masked domain adversarial adaptation framework for unsupervised domain adaptive semantic segmentation

引用

Pattern Analysis and Applications 2025年第2期28卷 1-24页

作者： Chouhan, Avinash Sur, Arijit Chutia, Dibyajyoti Aggarwal, Shiv Prasad North Eastern Space Applications Centre Meghalaya Umiam 793103 India Department of Computer Science and Engineering Indian Institute of Technology Assam Guwahati 781039 India

Unsupervised domain adaptation (UDA) is an important task that transfers learned knowledge from the source domain to the unseen target domain. Domain shift is the major challenge faced by UDA methods for aerial data, which is caused by differences in appearance, distribution, decision boundary, sensor platforms, capturing conditions, etc. Mix representations combine inputs of both domains, which are helpful for the generation of domain-consistent features using self-training. Domain alignment at multiple levels is required for effective adaptive segmentation between domains. In this work, we proposed a Masked Domain Adversarial Adaptation Framework (MDAAF), which consists of the Masked Domain Adversarial Adaptation Network (MDAANet), Masked Domain Dual Adaptation (MDDA) approach, Joint Adversarial Alignment (JAA), Consistency Enforcement (CE), and Feature Dissimilarity-based Alignment (FDA) for effective UDA. The proposed MDAAF achieves the all-level adaptation (input, feature, and output) to handle domain shift issues using multi-level features generated by MDAANet with MDDA. FDA increased the inter-class feature dissimilarities, CE attained input-consistent output adaptation, and JAA achieved combined adaptation at the input–output level. MDAAF achieved state-of-the-art results on six benchmark domain adaptation tasks with performance improvement in the 1.5–10% range from previous methods. The trained model weights and implementation code are available at https://***/chouhan-avinash/MDAAF/tree/master/. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Consistency enforcement Feature dissimilarity based alignment Joint adversarial alignment Masked domain dual adaptation

来源：评论

学校读者我要写书评

暂无评论

A 41.32Gb/s 1.8 pJ/bit Collaborative Baud-Rate CDR With Background Eye-Climbing Algorithm and Low-Power Global Clock Distribution

引用

IEEE Journal of Solid-State Circuits 2025年

作者： Kim, Jihee Park, Jia Shin, Jiwon Kim, Hanseok Kim, Kahyun Shin, Haengbeom Park, Ha-Jung Choi, Woo-Seok Georgia Institute of Technology Department of Electrical and Computer Engineering AtlantaGA30332 United States Inter University Semiconductor Research Center Seoul National University Department of Electrical and Computer Engineering Seoul08826 Korea Republic of Samsung Electronics Hwaseong18448 Korea Republic of

This article presents design techniques for an energy-efficient multi-lane receiver (RX) with baud-rate clock and data recovery (CDR), which is essential for high-throughput low-latency communication in high-performance computing systems. The proposed low-power global clock distribution not only significantly reduces power consumption across multi-lane RXs but is capable of compensating for the frequency offset without any phase interpolators (PIs). To this end, a fractional divider (FDIV) controlled by CDR is placed close to the global phase locked loop. Moreover, in order to address the suboptimal lock point of conventional baud-rate phase detectors, the proposed CDR employs a background eye-climbing algorithm (ECA), which optimizes the sampling phase and maximizes the vertical eye margin (VEM). Fabricated in a 28 nm CMOS process, the proposed 43.32Gb/s RX shows a low integrated fractional spur of -40.4 dBc at a 2500 ppm frequency offset. Furthermore, it improves bit-error-rate (BER) performance by increasing the VEM by 26 mV. The entire RX achieves the energy efficiency of 1.8 pJ/bit with the aggregate data rate of 128 Gb/s. © 1966-2012 IEEE.

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

Understanding barriers affecting the adoption and usage of open access data in the context of organizations

引用

Data and Information Management 2025年第1期9卷

作者： Çaldağ, Murat Tahir Gökalp, Ebru Baskent University Department of Technology and Knowledge Management Ankara06790 Turkey Hacettepe University Department of Computer Engineering Ankara Turkey University of Cambridge Department of Engineering CambridgeCB2 1TN United Kingdom

Data and information are growing exponentially due to advances and innovations in information and communication technologies. This growth forces organizations to gain new capabilities to compete or stay current in their marketplace. Open Access Data (OAD), resulting from the open source movement, is seen as a double-edged sword from the management perspective. It can potentially provide enormous social and economic value, such as transparency, participation culture, innovativeness, and accountability to organizations, governments, and, more importantly, citizens. Although the benefits of organizational adoption are significant, most OAD-related projects fail cause of organizational barriers and resistance to adoption. This study first aims to find these organizational barriers on adopting OAD to raise awareness of the obstacles organizations must overcome. Towards this aim, after conducting a systematic literature review (SLR) and an expert panel, a research model based on the technology – Organization – Environment (TOE) framework is proposed in this study. As a result of SLR, 97 barriers were identified from ten primary studies. After critically examining these barriers, a research model classifying 22 crucial barriers to organizational OAD adoption based on the TOE framework is proposed. Another significant contribution of this study is to draw attention to under-researched barriers in the literature, such as Power and Control, Political Commitment, Inter-Organizational Trust, IT Governance, and Competitive Pressure. © 2023 The Authors

关键词： Open Data

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：