检索结果-内蒙古大学图书馆

A novel machine learning approach for numerical simulation on the hybrid nanofluid flow past a converging/diverging channel: Properties of tantalum and alumina nanoparticles

引用

Partial Differential Equations in Applied Mathematics 2025年 13卷

作者： B, Shilpa Chohan, Jasgurpreet Singh Beemkumar, N. Kulshreshta, Ankur Ghodhbani, Refka Othman, Nashwan Adnan Abdullaeva, Barno Khan, M Ijaz Department of Mathematics Dayananda Sagar College of Engineering Karnataka Bengaluru India School of Mechanical Engineering Rayat Bahra University Mohali India Department of Mechanical Engineering School of Engineering and Technology JAIN (Deemed to be University) Karnataka Bangalore India NIMS School of Mechanical & Aerospace Engineering NIMS Institute of Engineering & Technology NIMS University Rajasthan Jaipur India Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq Department of Computer Engineering Al-Kitab University Altun Kupri Iraq Department of Mathematics and Information Technologies Vice-Rector for Scientific Affairs Tashkent State Pedagogical University Tashkent Uzbekistan Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Faculty of Engineering Sohar University Sohar Oman

Convergent and divergent channels have practical uses in the manufacture of fibres and glass, for the production of plastic sheets, the control of molten metal flows, and casting of metals. Also, hybrid nanofluids are being explored as possible working fluids for solar collectors and other high heat flux systems because of their outstanding heat transfer abilities. The present study focuses on exploring the effect of quadratic thermal radiation on the hybrid nanoliquid stream via a convergent/divergent channel, considering the impact of homogeneous-heterogeneous chemical reactions with the suspension of tantalum and alumina nanoparticles on the liquid stream. The governing partial differential equations of the present problem are transformed into dimensionless ordinary differential equations with the help of similarity variables. Further, the resultant equations are solved using the finite element approach. Also, the Laguerre Polynomial-based Physics Informed Neural Network (L-PINN) model is adopted to analyze the fluid flow, heat, and mass transfer characteristics. The significance of pertinent physical parameters on the field variables is depicted with graphical representations. Turbulence, caused by chaotic fluid motion, increases energy dissipation, which can limit the channel's effective flow velocity in stretching convergent channels. A rise in the Reynolds number in a divergent stretchable and shrinkable channel raises the temperature due to improved convective heat transfer. © 2024

关键词： Convergent/divergent channel FEM Homogeneous-heterogeneous chemical reaction Hybrid nanofluid L-PINN Quadratic thermal radiation

来源：评论

学校读者我要写书评

暂无评论

The Impact of Transformer Models and Regression Algorithms on Automated Short Answer Grading

The Impact of Transformer Models and Regression Algorithms o...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Abhijith. N. Nampoothiri M. G. Thushara Pradeesh. N Anand Krishna K. R Abhai Santhosh Abhijith Kumar S Suryan Kumar Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Omnex Software Solutions Pvt. Ltd Chennai India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

Grading short answer questions in higher education often poses significant challenges due to its subjective nature and time-consuming process. As educational institutions expand, the need for efficient and objective grading solutions becomes critical. This paper investigates the use of machine learning and natural language processing to automate the evaluation of short answer responses. Our study employs a two-phase methodology: first, several transformer models—including BERT, Sentence-BERT, T5, Genism, and XLNet—are used to transform text into numerical representations. In the second phase, various regression techniques, such as Linear Regression, Support Vector Machine (SVM), Random Forest, and AdaBoost, are applied to these representations to estimate scores. Our findings indicate that the combination of the BERT model with Random Forest performs the best, demonstrating superior accuracy with the lowest error metrics. This optimal model pairing is proposed for integration into the Ample Learning Management System (LMS) to enhance grading efficiency and provide quicker, more reliable feedback. The significant implications of this research provides teachers with a robust tool for automated grading, which can enhance the educational experience by delivering timely and accurate evaluations.

关键词： Support vector machines Measurement Accuracy Education Forestry Transforms Transformers Numerical models Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Structured Process on FL for Big Data Analysis

Structured Process on FL for Big Data Analysis

引用

Mobile Computing and Sustainable informatics (ICMCSI), International Conference on

作者： Anitha Govindaram J. S. Prasath K. Jayasakthi N. Rajkumar G. Porkodi Jose Anand A Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Thandalam Chennai India Department of Computer Science and Engineering Sapthagiri NPS University Bengaluru Karnataka Department of ECE KCG College of Technology Chennai Tamil Nadu Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Department of Computer Science and Business Systems Vel Tech Multi Tech Dr. Rangaranjan Dr.Sakunthala Engineering College Tamil Nadu

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

The integration of the Internet of Things (IoT) into various aspects of daily life is accelerated by the proliferation of cognitive capabilities and AI-driven applications. Traditional automated systems rely on centralized data storage and dispensation, which may be feasible in specific application scenarios. However, the increasing flexibility of recent IoT networks and rising concerns over data confidentiality are challenging this approach. Federated Learning (FL), a decentralized collaborative AI technique, allows machine learning to occur directly on external IoT devices without the need for data to be centrally aggregated or shared. This paves the way for a wide variety of intelligent IoT applications to be developed. This article presents a thorough analysis of the along with a detailed analysis of the convergence of these two fields. After that, a full analysis of how FL is currently being utilized in several essential applications related to the IoT is provided. These include smart health, mobility, Unmanned Aerial Vehicles (UAVs), infrastructure improvements, and smart industries. In total, 49 publications from the years 2015–2022 were reviewed here. Finally, discuss future study challenges with issues and exposed questions about data with IoT.

关键词： Industries Data privacy Federated learning Smart healthcare Memory Collaboration Internet of Things informatics Mobile computing Convergence

来源：评论

学校读者我要写书评

暂无评论

Learned Primal Dual Splitting for Self-Supervised Noise-Adaptive MRI Reconstruction

arXiv

引用

arXiv 2025年

作者： Janjušević, Nikola Khalilian-Gourtani, Amirhossein Wang, Yao Feng, Li New York University Grossman School of Medicine Radiology Department New YorkNY10016 United States New York University Grossman School of Medicine Neurology Department New YorkNY10016 United States New York University Tandon School of Engineering Electrical and Computer Engineering Department BrooklynNY11201 United States

Magnetic resonance imaging (MRI) reconstruction has largely been dominated by deep neural networks (DNN);however, many state-of-the-art architectures use black-box structures, which hinder interpretability and improvement. Here, we propose an interpretable DNN architecture for self-supervised MRI reconstruction and denoising by directly parameterizing and learning the classical primal-dual splitting, dubbed LPDSNet. This splitting algorithm allows us to decouple the observation model from the signal prior. Experimentally, we show other interpretable architectures without this decoupling property exhibit failure in the self-supervised learning regime. We report state-of-the-art self-supervised joint MRI reconstruction and denoising performance and novel noise-level generalization capabilities, where in contrast black-box networks fail to generalize. © 2025, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Direct ink writing of gradient shear-stiffening elastomer for enhanced toughness and impact resistance

引用

Journal of Industrial and engineering Chemistry 2025年

作者： Gong, Liping Zhao, Chunyu Lu, Hongda Zhang, Qingtian Chen, Zexin Yang, Junjie Yang, Jinyu Sun, Shuaishuai Du, Haiping Li, Weihua School of Mechanical Materials Mechatronic and Biomedical Engineering University of Wollongong Wollongong2522 Australia CAS Key Laboratory of Mechanical Behaviour and Design of Materials Department of Modern Mechanics University of Science and Technology of China Hefei230027 China School of Electrical Computer and Telecommunication Engineering University of Wollongong Wollongong2522 Australia

Shear-stiffening materials have garnered significant attention due to their inherent ability to rapidly respond to changes in strain rate. However, conventional studies on these materials exhibit limited mechanical performance and insufficient structural design, hindering applications in material science and smart mechatronics. Inspired by the gradient structure of a squid beak, this study uses a direct-ink-writing (DIW) technology to develop a novel gradient shear-stiffening elastomer (GSSE). Comprehensive characterizations were conducted to optimize the printability of the shear-stiffening elastomer under various testing conditions, including rheology, compression, and tension. Additionally, the toughness and impact resistance of the elastomer were systematically investigated. It is demonstrated that the biomimetic GSSE exhibits enhanced flexibility, efficient energy dissipation, and outstanding impact resistance. Consequently, this work advances the field of shear-stiffening elastomers for diverse applications by leveraging the gradient structure design strategy to achieve superior mechanical performance under complex loading conditions. © 2025 The Author(s)

关键词： Strain rate

来源：评论

学校读者我要写书评

暂无评论

Simulation-Based Metrological Temperature Ensuring and Control of the Temperature Field in an Induction Furnace Based on Various Parameters

Simulation-Based Metrological Temperature Ensuring and Contr...

引用

International Conference on computer and Automation engineering, ICCAE

作者： Jan Rybář Samuel Emebu Sayed Yousuf Sayed Sohaibullah Zarghoon Lukáš Bartalský Peter Onderčo Andrej Smetánka Radek Matušů Faculty of Mechanical Engineering Institute of Automation Informatization and Measurement Slovak University of Technology Bratislava Slovakia Department of Separation Science LUT School of Engineering Science Lappeenranta-Lahti University of Technology Lappeenranta Finland Department of Auto mechanical Engineering Faculty of Electro-Mechanic Kabul Polytechnic University Kabul Afghanistan Department of Automation and Control Engineering Faculty of Applied Informatics Tomas Bata University in Zlín Zlín Czech Republic

ISBN: (数字)9798331533816

ISBN: (纸本)9798331533823

Induction heating is widely used in industrial furnaces because of its rapid response time and high energy efficiency. To design and optimize these furnaces, computer-aided simulations are essential. This study aims to develop an accurate temperature field model for a square cross-section steel billet in an induction furnace by leveraging various parameters in COMSOL Multiphysics software. The simulation analysis incorporated temperature dynamics, considering skin depth, temperaturedependent, and constant parameters of the steel billet. The datadriven model was converted into a state-space representation utilizing MATLAB's System Identification Toolbox. This conversion facilitated the design of a Linear Quadratic Regulator (LQR) with integral gain and pole placement. Further, these controllers' performance was analyzed, and controllers were successfully implemented to regulate the temperature field of the billet from initial temperature to reference temperature, utilizing the distributed parameter system control circuit.

关键词： Billets Analytical models Temperature Accuracy Computational modeling Furnaces Mathematical models Temperature control Steel Induction heating

来源：评论

学校读者我要写书评

暂无评论

Enhanced Rheumatoid Arthritis Treatment Optimization Through Deep Learning

Enhanced Rheumatoid Arthritis Treatment Optimization Through...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Siva Venkatesh Arcot T. Buvaneswari K.R. Kavitha R. Manickavasagam Suguna M M Muthulekshmi Contact Center Business Unit Cisco Systems INC Little Elm Texas USA Department of Computer Science and Engineering Annapoorana Engineering College (Autonomous) Salem Tamil Nadu India Department of Electronics and Communication Engineering Sona College of Technology Salem Tamil Nadu India Department of Biomedical Engineering Alpha College of Engineering Chennai Tamil Nadu India Department of Computer Science Vinayaka Mission's Kirupananda Variyar Arts and Science College Vinayaka Mission's Research Foundation (Deemed to be University) Salem Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Inflammation and joint destruction are hallmarks of Rheumatoid Arthritis (RA), a chronic autoimmune condition. To improve patient outcomes, it is essential to optimize treatment plans. According to this research, integrating deep learning (DL) methods into a Convolutional Neural Network (CNN) provides a new method to optimize RA treatments. The CNN model is used to decipher intricate medical data, such as imaging and patient records, find trends, and predict how patients react to treatment. To assess the efficacy of the proposed model in predicting ideal treatment methods, it was trained on a large dataset that included patient images and clinical data. The CNN model offers a potential tool for doctors to adapt RA management plans since results show it significantly improves prediction accuracy and treatment personalization. This method allows for data-driven decisions in RA management, improving patient care and enhancing treatment performance.

关键词： Deep learning Adaptation models Accuracy Soft sensors Predictive models Arthritis Data models Convolutional neural networks Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

AGCSNet: High-contrast image-exposure correction with automatic illumination-map attention-based gamma and saturation correction

引用

ETRI Journal 2025年

作者： Kim, Min-ji Deng, Qikang Choo, DongWon Ji, Hyo Chul Lee, DoHoon Research Institute of Computer Information and Communication Pusan National University Busan Korea Republic of Department of Information Convergence Engineering Pusan National University Busan Korea Republic of R&D Team InBic Inc. Seongnam Korea Republic of School of Computer Science and Engineering Pusan National University Busan Korea Republic of

Low-light image enhancement has made significant advancements in recent years. However, enhancing high-contrast images that exhibit both under- and overexposure remains a major challenge. To address this issue, we propose an exposure-correction method called AGCSNet. Two gamma corrections, (Formula presented.) and (Formula presented.), were applied separately to correct for underexposure and overexposure, producing two gamma-corrected images. An illumination map was used to differentiate between the underexposed and overexposed regions in the gamma-corrected images. To mitigate the saturation anomalies caused by the gamma corrections, we introduced a new saturation-correction method with a factor (Formula presented.). Moreover, optimal values for (Formula presented.), and (Formula presented.) can be predicted using our factor-estimation deep-learning model. We evaluated our method on eight datasets. In comparison with over 20 prior methods, our method demonstrates competitive performance with and, in some cases, surpasses state-of-the-art methods that are closely aligned with human visual perception. 1225-6463/$ © 2025 ETRI.

关键词： gamma correction high-contrast image-exposure correction illumination map attention low-light enhancement saturation correction

来源：评论

学校读者我要写书评

暂无评论

SVM-based Predictive Modeling for Sustainable Solar Solutions in Off-Grid Areas

SVM-based Predictive Modeling for Sustainable Solar Solution...

引用

Trends in Material Science and Inventive Materials (ICTMIM), International Conference on

作者： Giriprasad. S S. Sangeetha G Manikandan G Bhuvaneswari B Meenakshi S. Sujatha Department of Electronics and Communication Engineering SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science RMK Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Sri Sairam Engineering College Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

The rising need for sustainable energy solutions in off-grid regions has prompted the investigation of creative predictive modeling methodologies. This research examines Support Vector Machine (SVM) techniques to enhance solar energy production and use. SVM, a powerful machine learning instrument, assesses diverse environmental variables, such as solar radiation, temperature, and humidity, to precisely forecast solar energy production. It presents a SVM model to forecast solar energy production in off-grid areas, optimizing resource distribution and improving sustainability with analysis of environmental variations and energy consumption data. The model improves decision-making for deploying solar systems in distant areas using historical data and real-time observations. The prediction skills of SVM enable the creation of customized solar energy systems that address the specific energy requirements of off-grid settlements. This technique enhances sustainability by optimizing solar installation efficiency, decreasing dependence on fossil fuels, and mitigating environmental consequences. The results indicate that SVM-based predictive modeling substantially enhances the dependability and efficiency of solar energy systems, making them more feasible for off-grid applications. It highlights the capacity of advanced machine learning methodologies to promote sustainable energy solutions, hence aiding the worldwide shift towards renewable energy sources.

关键词： Support vector machines Renewable energy sources Energy consumption Solar energy Production Predictive models Market research Real-time systems Data models Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Delving Into Quaternion Wavelet Transformer for Facial Expression Recognition in the Wild

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Yu Pei, Jialun Si, Weixin Qin, Jing Heng, Pheng-Ann Zhongnan University of Economics and Law School of Information Engineering Wuhan China The Chinese University of Hong Kong Department of Computer Science and Engineering ShaTin Hong Kong Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China The Hong Kong Polytechnic University School of Nursing Kowloon Hong Kong

The Facial Expression Recognition (FER) technique has increasingly matured over time. However, recognizing facial expressions in wild environments poses great challenges in achieving promising performance. The main obstacles arise from various factors, such as illumination changes, head pose variations, and occlusions. To overcome interferences from external environments and improve recognition accuracy, we propose a novel Quaternion Wavelet TRansformer (QWTR) model for FER in the wild. Specifically, we present a Quaternion Value Transformer (QVT) network that combines quaternion multi-head attention with quaternion CNN to capture emotional cues from global and local perception. To preserve the color structure while enhancing image contrast and brightness, we introduce a Quaternion Histogram Equalization (QHE) representation to transform color images into quaternion matrices representation. After that, to alleviate the impact of head pose and occlusion together with feature redundancy, a Quaternion Wavelet Feature Selection (QWFS) scheme is designed to decompose quaternion features and select the most correlated signals. Extensive experiments have been conducted on four in-the-wild FER datasets and several specific FER benchmarks under various conditions. The qualitative and quantitative results demonstrate that QWTR outperforms other state-of-the-art methods in FER benchmarks, e.g., 68.37% vs. 66.31% accuracy on the AffectNet dataset. Code is available at https://***/zy197997312/QWTR-for-FER. © 1999-2012 IEEE.

关键词： Image enhancement

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：